Systems and methods for mapping, targeting, labeling, coordinating, classifying, and organizing data

Abstract

Systems and methods for mapping, targeting, labeling, coordinating, classifying, and organizing data are described herein.

Description

TITLESYSTEMS AND METHODS FOR MAPPING, TARGETING, LABELING, COORDINATING, CLASSIFYING, AND ORGANIZING DATACROSS REFERENCE TO RELATED APPLICATIONS

[0001] This international application claims priority to United States Provisional Application No. 63 / 534,986, filed on August 28, 2023, United States Provisional Application No. 63 / 545,404, filed on October 24, 2023, United States Provisional Application No. 63 / 615, 105, filed on December 27, 2023, United States Provisional Application No. 63 / 549,763, filed on February 5, 2024, United States Provisional Application No. 63 / 552,281, filed on February 12, 2024, United States Provisional Application No. 63 / 566,518, filed on March 18, 2024, United States Provisional Application No. 63 / 637,129, filed on April 22, 2024, and United States Provisional Application No. 63 / 677,753, filed on July 31, 2024, each of which is incorporated by reference in its entirety into this disclosure.FIELD

[0002] This application relates to medical systems, and more particularly, systems and methods for mapping, targeting, labeling, coordinating, classifying, and organizing data.BRIEF SUMMARY OF SELECTED EXAMPLES

[0003] Provided herein is a method for generating an output having a segmented input, the method comprising: receiving an input from a user; identifying a landmark within the input; segmenting the input into a plurality of segments to form the segmented input; generating a path or a path group based on the landmark; encoding the path or the path group based on the plurality of segments; and generating the output having the segmented input with the encoded path or path group.

[0004] In certain examples, the step of identifying a landmark within the input comprises training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library. In certain examples, the method further comprises coordinating the segmented output with other coordinate systems.

[0005] Also provided herein is a system for generating an output having a segmented input, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platformincluding a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, from the input device, an input from a user; identify, using the data processing module, a landmark within the input; segment, using the data processing module, the input into a plurality of segments to form the segmented input; generate, using the data processing module, a path or a path group based on the landmark; encode, using the data processing module, the path or the path group based on the plurality of segments to form an encoded path or encoded path group; and generate, using the generation module, the output having the segmented input with the encoded path or the encoded path group.L0006 J Also provided herein is a method for detecting a reference point or reference area on a physical object, the method comprising: aligning the reference point or reference area to spatial data, custom axis data, database data, detected features, or combinations thereof, wherein the detected features include topology, morphology, diagnosis, color, counts, surface area, or combinations thereof; and calculating and encoding the point or area in relation to the detected and aligned reference point or reference area with progressive and proportional segmentation.

[0007] Also provided herein is a system for detecting a reference point or reference area on a physical object, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processorexecutable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: align, using the data processing module, the reference point or reference area to spatial data, custom axis data, database data, or to detected features, wherein the detected features include topology, morphology, diagnosis, color, counts, surface area, or combinations thereof; and calculate and encode, using the data processing module, the point or area in relation to the detected and aligned reference point or reference area with progressive and proportional segmentation.

[0008] Also provided herein is a method for generating an embedded output, the method comprising: receiving an input from the user; processing the input to form processed input; and applying an embedded label based on the processed input to the input to generate the embedded output.

[0009] In certain examples, the step of processing the input to form processed input comprises identifying and recording medical information in the input; selectively generating a description of the input based on the medical information; and selectively generating visualizations based on the medical information. In certain examples, the step of processing the input to form processed inputTcomprises training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library. In certain examples, the embedded label includes medical information, including the description of the medical information, the visualizations based on the medical information, or combinations thereof. In certain examples, the embedded label includes an encoded portion. In certain examples, the step of applying an embedded label based on the processed input to the input to generate the embedded output includes depersonalizing the medical information to generate depersonalized medical information, and wherein the embedded label includes the depersonalized medical information.

[0010] Also provided herein is a system for generating an embedded output, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from the user; processing, using the data processing module, the input to form processed input; and applying, using the generation module, an embedded label based on the processed input to the input to generate the embedded output.

[0011] Also provided herein is a method for regenerating decoded data, the method comprising: scanning an embedded output having an embedded label to generate decoded data; and regenerating the decoded data.

[0012] In certain examples, the embedded label includes an encoded portion. In certain examples, the step of scanning an embedded output having an embedded label to generate processed data includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library. In certain examples, the method further comprises a step of authenticating a user before the step of regenerating processed data, wherein if the user unauthenticated, the decoded data only includes depersonalized medical information, and if the user is authenticated, the decoded data includes the medical information without being depersonalized.

[0013] Also provided herein is a system for regenerating decoded data, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: scan,using the data processing module, an embedded output having an embedded label to generate decoded data; and regenerating, using the generation module, the decoded data.

[0014] Also provided herein is a method for detecting and reconciling spatial errors within an input, the method comprising: receiving an input from a user, wherein the input includes a marker on an anatomic representation; determining if the marker includes a spatial error; if the marker includes the spatial error, generating an output based on a rectified input; and if the marker does not include the spatial error, generating an output based on the input.

[0015] In certain examples, the step of determining if the marker includes a spatial error includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library.

[0016] Also provided herein is a system for detecting and reconciling spatial errors within an input, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from a user, wherein the input includes a marker on an anatomic representation; determine if the marker includes a spatial error; if the marker includes the spatial error, generate an output based on a rectified input; and if the marker does not include the spatial error, generate an output based on the input.

[0017] Also provided herein is a method for generating an output based on non-semantic similarity, the method comprising: receiving an input from a user to identify paths and at least one diagram in a library of diagrams and paths, wherein the input includes an uncoordinated component, wherein the uncoordinated component is a coded, language-based, symbol-based or mixed description, and wherein the paths include at least one path, path segment, or path group; calculating the non-semantic similarity between the input and other paths in the library, wherein the non-semantic similarity includes coordinate similarity, positional similarity, spatial similarity, or combinations thereof; optionally, calculating the non-semantic similarity on new visualizations by overlaying or underlaying and aligning other paths in the library with the anatomic features present in the diagram; generating maps, avatars, illustrations, or visualizations based on the non- semantic similarity as outputs.

[0018] Also provided herein is a system for generating an output based on non-semantic similarity, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mappingplatform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from a user to identify paths and at least one diagram in a library of diagrams and paths, wherein the input includes an uncoordinated component, wherein the uncoordinated component is a coded, language-based, symbol-based or mixed description, and wherein the paths include at least one path, path segment, or path group; calculate, using the data processing module, the non-semantic similarity between the input and other paths in the library, wherein the non-semantic similarity includes coordinate similarity, positional similarity, spatial similarity, or combinations thereof; optionally, calculate the non-semantic similarity on new visualizations by overlaying or underlaying and aligning other paths in the library with the anatomic features present in the diagram; and generate maps, avatars, illustrations, descriptions, visualizations, or combinations thereof based on the non-semantic similarity as outputs.

[0019] Also provided herein is a method for improving reproduction and generation of anatomic site visualizations, descriptions, maps, and relationships, the method comprising: receiving at least one coordinate-based path, path segment, or path group linked to at least one anatomic representation identified with the input, and the input serving as a reference to a map-diagram pair; rendering at least the reference map-diagram pair, in whole or in part, on a display; selectively rendering, additional data in the input related to the map-diagram pair on the display; and selectively generating new maps, images, avatars, relationships, and descriptions based on coordinate similarity, positional similarity, or spatial similarity regardless of semantic similarity.

[0020] Also provided herein is a system for improving reproduction and generation of anatomic site visualizations, description, maps, and relationships, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processor-executable instructions stored on the medium, the processorexecutable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, at least one coordinate-based path, path segment, or path group linked to at least one anatomic representation identified with the input, and the input serving as a reference to a map-diagram pair; render, using the processor, at least the reference map-diagram pair, in whole or in part, on the display; selectively render, using the processor, additional data in the input related to the map-diagram pair on the display; and selectively generate, using the generation module, new maps, images, avatars, relationships, and descriptions based on coordinate similarity, positional similarity, spatial similarity, or combinations thereof regardless of semantic similarity.

[0021] Also provided herein is a method for generating a description of a plurality of markers on an anatomic representation, the method comprising: receiving an input from a user, wherein the input includes the plurality of markers on the anatomic representation; determining the relationship between each of the plurality of markers; and generating a description of the input, wherein the description of the input includes a description of the relationship between each of the plurality of markers or a visualization of the plurality of the markers with the description of the relationship.

[0022] In certain examples, the step of determining the relationship between each of the plurality of markers includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library.

[0023] Also provided herein is a system for generating a description of a plurality of markers on an anatomic representation, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processorexecutable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from a user, wherein the input includes the plurality of markers on the anatomic representation; determine, using the data processing module, the spatial relationship between each of the plurality of markers; and generate, using the generation module, a description of the input, wherein the description of the input includes a description of the spatial relationship between each of the plurality of markers or a visualization of the plurality of the markers with the description of the spatial relationship.

[0024] Also provided herein is a method for generating a visualization of a global period of a procedure or a diagnosis, the method comprising: receiving an input from the user, wherein the input includes a record of a patient having the procedure or the diagnosis related to the patient; determining the one or more anatomic sites associated with the procedure or the diagnosis; determining the global period of the procedure or diagnosis; and generating the visualization of the global period of the procedure or diagnosis.

[0025] In certain examples, the step of determining the one or more anatomic sites associated with the procedure or the diagnosis includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a library of procedures and diagnoses. In certain examples, the step of determining the global period of the procedure or diagnosis includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a library of procedures and diagnoses. Incertain examples, the step of generating the visualization of the global period of the procedure or diagnosis includes generating the visualization which includes an anatomic representation having the anatomic sites affected by the procedure or diagnosis with indicia in each anatomic site showing whether the site is in the global period.

[0026] Also provided herein is a system for generating a visualization of a global period of a procedure or a diagnosis, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processorexecutable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from the user, wherein the input includes a record of a patient having the procedure or the diagnosis related to the patient; determine, using the data processing module, the one or more anatomic sites associated with the procedure or the diagnosis; determine, using the data processing module, the global period of the procedure or diagnosis; and generate, using the generation module, the visualization of the global period of the procedure or diagnosis.

[0027] Also provided herein is a method for determining a billing code for a procedure or diagnosis, the method comprising: receiving an input from the user, wherein the input includes a procedure or the diagnosis related to the patient; determining the one or more anatomic sites associated with the procedure or the diagnosis; determining the billing code based on the procedure or diagnosis and the one or more anatomic sites associated with the procedure or the diagnosis; and generating an output having the billing code for the procedure or diagnosis.

[0028] In certain examples, the step of determining the one or more anatomic sites associated with the procedure or the diagnosis includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a library of procedures and diagnoses. In certain examples, the step of determining the billing code based on the procedure or diagnosis and the one or more anatomic sites associated with the procedure or the diagnosis includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a library of billing codes. In certain examples, the step of generating an output having the billing code for the procedure or diagnosis includes generating a justification for selecting the higher or lower reimbursing code in natural language based on the billing code matched with the procedure or diagnosis in the input and the anatomic sites affected by the procedure or diagnosis.

[0029] Also provided herein is a system for generating a visualization of a global period of aprocedure or a diagnosis, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processorexecutable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from the user, wherein the input includes a procedure or the diagnosis related to the patient; determine, using the data processing module, the one or more anatomic sites associated with the procedure or the diagnosis; determine, using the data processing module, the billing code based on the procedure or diagnosis and the one or more anatomic sites associated with the procedure or the diagnosis; and generate, using the generation module, an output having the billing code for the procedure or diagnosis.

[0030] Also provided herein is a method for verifying a billing code for a procedure or diagnosis, the method comprising: receiving an input from a user, wherein the input includes a billing code and the one or more anatomic sites affected by the procedure or the diagnosis; determining the one or more anatomic sites covered by the billing code; determining whether the one or more anatomic sites covered by the billing code matches the one or more anatomic sites affected by the procedure or the diagnosis; if the one or more anatomic sites covered by the billing code does not match the one or more anatomic sites affected by the procedure or the diagnosis, determining a correct billing code for the one or more anatomic sites affected by the procedure or the diagnosis to generate a verified billing code based on the correct billing code; if the one or more anatomic sites covered by the billing code does match the one or more anatomic sites affected by the procedure or the diagnosis, generate the verified billing code based on the billing code of the input; and generating an output, wherein the output includes the verified billing code.

[0031] In certain examples, the step of determining the one or more anatomic sites covered by the billing code includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a library of billing codes. In certain examples, the step of determining a correct billing code for the one or more anatomic sites affected by the procedure or the diagnosis to generate a verified billing code based on the correct billing code includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a library of billing codes.

[0032] Also provided herein is a system for verifying a billing code for a procedure or diagnosis, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processor-executable instructionsstored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from a user, wherein the input includes a billing code and the one or more anatomic sites affected by the procedure or the diagnosis; determine, using the data processing module, the one or more anatomic sites covered by the billing code; determine, using the data processing module, whether the one or more anatomic sites covered by the billing code matches the one or more anatomic sites affected by the procedure or the diagnosis; if the one or more anatomic sites covered by the billing code does not match the one or more anatomic sites affected by the procedure or the diagnosis, determine, using the data processing module, a correct billing code for the one or more anatomic sites affected by the procedure or the diagnosis to generate a verified billing code based on the correct billing code; if the one or more anatomic sites covered by the billing code does match the one or more anatomic sites affected by the procedure or the diagnosis, generate, using the data processing module, the verified billing code based on the billing code of the input; and generate, using the generation module, an output, wherein the output includes the verified billing code.

[0033] Also provided herein is a method for encoding a medical visualization into an encoded string, the method comprising: rendering the medical visualization on a display, wherein the medical visualization includes an anatomic representation having plurality of predefined anatomic sites and at least one of the predefined anatomic sites includes a marker; receiving instructions from a user to encode the medical visualization into the encoded string; and generating an output having the encoded string, wherein the encoded string includes an anatomic site identification portion, a laterality portion, a description of the marker portion, an anatomic representation identification portion, a modifier portion, a prefix portion, a suffix portion, a deviation x-axis portion, a deviation y-axis portion, a deviation z-axis portion, an axial definition portion, an angle portion, an order type portion, an order position portion, a central zone portion, time deviation portion, a synonym portion, or combinations thereof.

[0034] In certain examples, the method further comprises a step of the user disposing a marker on at least one of the predefined anatomic sites prior to the step of rendering the medical visualization on the display.

[0035] Also provided herein is a system for encoding a medical visualization into an encoded string, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communicationwith the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: render, using the processor, the medical visualization on the display, wherein the medical visualization includes an anatomic representation having a plurality of predefined anatomic sites and at least one of the predefined anatomic sites includes a marker; receive, using the input device, instructions from a user to encode the medical visualization into the encoded string; and generate, using the generation module, an output having the encoded string, wherein the encoded string includes an anatomic site identification portion, a laterality portion, a description of the marker portion, an anatomic representation identification portion, a modifier portion, a prefix portion, a suffix portion, a deviation x-axis portion, a deviation y-axis portion, a deviation z-axis portion, an axial definition portion, an angle portion, an order type portion, an order position portion, a central zone portion, time deviation portion, a synonym portion, or combinations thereof.

[0036] Also provided herein is a method for decoding an encoded string into a medical visualization, the method comprising: receiving an encoded string from a user; and generating an output having the medical visualization based on the encoded string, wherein the encoded string includes an anatomic site identification portion, a laterality portion, a description of the marker portion, an anatomic representation identification portion, a modifier portion, a prefix portion, a suffix portion, a deviation x-axis portion, a deviation y-axis portion, a deviation z-axis portion, an axial definition portion, an angle portion, an order type portion, an order position portion, a central zone portion, time deviation portion, a synonym portion, or combinations thereof.

[0037] In certain examples, the step of generating an output having the medical visualization based on the encoded string includes determining the anatomic representation based on the anatomic representation identification portion; determining the anatomic site where the marker is disposed within based on the anatomic site identification portion; determining the laterality modifier that describes the position of the anatomic site relative to the anatomic representation based on the laterality portion; determining the description of the marker based on the description of the marker portion; determining modifiers based on the modifier portion; determining prefixes based on the prefix portion; determining suffixes based on the suffix portion; determining the deviation in the x-axis based on the deviation x-axis portion; determining the deviation in the y- axis based on the deviation y-axis portion; determining the deviation in the y-axis based on deviation z-axis portion; determining the axial definitions based on axial definition portion; determining the angle of interpretation for each axis, a rotation of a path, plane, custom axis, or combinations thereof based on the angle portion; determining the order type based on the order type portion; determining the order type position based on the order type position portion; determining the description of the central zone based on the central zone portion; determining thedeviation in time based on the time deviation portion; determining any synonyms based on the synonym portion; or combinations thereof.

[0038] Also provided herein is a system for decoding an encoded string into a medical visualization, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an encoded string from a user; and generate, using the generation module, an output having the medical visualization based on the encoded string, wherein the encoded string includes an anatomic site identification portion, a laterality portion, a description of the marker portion, an anatomic representation identification portion, a modifier portion, a prefix portion, a suffix portion, a deviation x-axis portion, a deviation y-axis portion, a deviation z-axis portion, an axial definition portion, an angle portion, an order type portion, an order position portion, a central zone portion, time deviation portion, a synonym portion, or combinations thereof

[0039] Also provided herein is a method for generating a spatial description for a marker on an anatomic representation, the method comprising: rendering an anatomic representation on a display, wherein the anatomic representation includes a plurality of predefined anatomic sites, a plurality of predefined direction planes, or combinations thereof, wherein each of the direction planes overlap one or more of the predefined anatomic sites; receiving an input from a user, wherein the input includes a name of anatomic site, a description of the anatomic site, a procedure for the anatomic site, a diagnosis for the anatomic site, or combinations thereof; rendering a marker on the anatomic representation based on the anatomic site of the input on the display; determining the spatial description of the marker based on a spatial relationship of the marker with an overlapping direction plane of the predefined direction planes, an adjacent direction plane of the predefined direction planes, or combinations thereof; and generating an output having the spatial description of the marker.

[0040] In certain examples, the step of rendering a marker on the anatomic representation based on the anatomic site of the input includes a step of processing the input to determine the anatomic site of the input. In certain examples, the step of processing the input to determine the anatomic site of the input includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library. In certain examples, the anatomic representation includes one or more velocity centers and the input includes temporal data, and wherein the temporal data includes the date ofanalysis / patient data capture and a change in the position of a condition across one or more anatomic sites. Tn certain examples, the method further comprises a step of determining the tempo or velocity of a condition progression based on a direction of the condition relative to one or more the direction planes, one or more velocity centers, the change in the position of a condition, or combinations thereof. In certain examples, the method further comprises a step of generating a prediction matrix to capture, analyze, research, and / or predict progression of health data over time with velocity centers and direction planes.

[0041] Also provided herein is a system for decoding an encoded string into a medical visualization, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: render, using the processor, an anatomic representation on the display, wherein the anatomic representation includes a plurality of predefined anatomic sites, a plurality of predefined direction planes, or combinations thereof, wherein each of the direction planes overlap one or more of the predefined anatomic sites; receive, using the input device, an input from a user, wherein the input includes a name of anatomic site, a description of the anatomic site, a procedure for the anatomic site, a diagnosis for the anatomic site, or combinations thereof; render, using the processor, a marker on the anatomic representation based on the anatomic site of the input on the display; determine, using the data processing module, the spatial description of the marker based on a spatial relationship of the marker with an overlapping direction plane of the predefined direction planes, an adjacent direction plane of the predefined direction planes, or combinations thereof; and generate, using the generation module, an output having the spatial description of the marker.

[0042] Also provided herein is a method for capturing, analyzing, researching, and predicting progression of health data, the method comprising: receiving an input having health data, wherein the input is text-based, visual-based, audio-based, and / or based on an interaction with the anatomic representation; capturing data related to time / temporal, anatomy, diagnosis, morphology, or other characteristics in relation to directional centers or direction planes; and processing the captured data into categories and context.

[0043] Also provided herein is a system for capturing, analyzing, researching, and predicting progression of health data, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processorexecutable instructions stored on the medium, the processor-executable instructions defining amapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input having health data, wherein the input is text-based, visual-based, audio-based, and / or based on an interaction with the anatomic representation; capture, using the data processing module, data related to time / temporal, anatomy, diagnosis, morphology, or other characteristics in relation to directional centers or direction planes; and process, using the data processing module, the captured data into categories and context.

[0044] Also provided herein is a method for estimating a surface area of a region of interest, the method comprising: receiving instructions from a user to estimate the surface area of the region of interest; determining a number of anatomic sites within the region of interest; determining an estimation of the surface area of the region of interest based on the number of anatomic sites within the region of interest; and generating an output with the estimation of the surface area of the region of interest.

[0045] In certain examples, the step of determining a number of anatomic sites within the region of interest includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library. In certain examples, the step of determining an estimation of the surface area of the region of interest based on the number of anatomic sites within the region of interest includes adding together the average surface area of each anatomic site within the number of anatomic sites to generate an estimation of the surface area of the region of interest. In certain examples, the step of generating an output with the estimation of the surface area of the region of interest includes displaying the number of anatomic sites within the region of interest with indicia within each anatomic site to represent the average surface area of said anatomic site.

[0046] Also provided herein is a system for estimating a surface area of a region of interest, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, instructions from a user to estimate the surface area of the region of interest; determine, using the data processing module, a number of anatomic sites within the region of interest; determine, using the data processing module, an estimation of the surface area of the region of interest based on the number of anatomic sites within the region of interest; and generate, using the generation module, an output with theestimation of the surface area of the region of interest.

[0047] Also provided herein is a method for correlating mixed inputs, the method comprising: receiving a plurality of inputs from a user, wherein at least one of the inputs includes an audio component and at least another input includes a visual component; determining context between the audio component and the visual component; and generating an output having standardized data based on the context between the audio component and the visual component.

[0048] In certain examples, the audio component includes medical information related to a shorthand for an unspecified anatomic site and the visual component includes a visual representation of the shorthand correlated to an anatomic site. In certain examples, the step of determining context between the audio component and the visual component includes a step of identifying the shorthand for the unspecified anatomic site in the audio component and a step of identifying the anatomic site correlated with the shorthand in the visual component. In certain examples, the step of identifying the shorthand for the unspecified anatomic site in the audio component includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a library of common shorthand terms. In certain examples, the step of identifying the anatomic site correlated with the shorthand in the visual component includes training, iteratively and / or recursively, the identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library. In certain examples, the standardized data includes the medical information from the audio component with the anatomic site correlated with the shorthand.

[0049] Provided herein is a system for correlating mixed inputs, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, a plurality of inputs from a user, wherein at least one of the inputs includes an audio component and at least another input includes a visual component; determine, using the data processing module, context between the audio component and the visual component; and generate, using the generation module, an output having standardized data based on the context between the audio component and the visual component.

[0050] Also provided herein is a method for filtering audio, the method comprising: receiving an input from a user, wherein the input includes audio; determining if the audio includes undesirable noise; if the audio includes undesirable noise, at least substantially removing the undesirable noisefrom the audio of the input; and generating an output having filtered audio, wherein the filtered audio is the audio with the undesirable noise substantially removed therefrom.

[0051] Also provided herein is a system for filtering audio, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processor-executable instructions stored on the medium, the processorexecutable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from a user, wherein the input includes audio; determine, using the data processing module, if the audio includes undesirable noise; if the audio includes undesirable noise, at least substantially remove, using the data processing module, the undesirable noise from the audio of the input; and generate, using the generation module, an output having filtered audio, wherein the filtered audio is the audio with the undesirable noise substantially removed therefrom.

[0052] Also provided herein is a method for encoding a skeleton-based diagnosis or procedure into an encoded string, the method comprising: receiving an input from the user, wherein the input includes a diagnosis or procedure related to an anatomic region of a skeleton system, a laterality modifier of the anatomic region, whether the diagnosis or procedure involves an open or closed fracture, a fracture subtype, and a specific anatomy of the anatomic region where the diagnosis or procedure occurs; and generating an output having the encoded string, wherein the encoded string has a diagnosis or procedure portion, a laterality modifier portion, a fracture open or closed portion, a fracture subtype portion, and a specific anatomy portion.

[0053] Also provided herein is a system for encoding a skeleton-based diagnosis or procedure into an encoded string, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processorexecutable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from the user, wherein the input includes a diagnosis or procedure related to an anatomic region of a skeleton system, a laterality modifier of the anatomic region, whether the diagnosis or procedure involves an open or closed fracture, a fracture subtype, and a specific anatomy of the anatomic region where the diagnosis or procedure occurs; and generate, using the generation module, an output having the encoded string, wherein the encoded string has a diagnosis or procedure portion, a laterality modifier portion, a fracture open or closed portion, a fracture subtype portion, and a specific anatomy portion.

[0054] Also provide herein is a method for processing an input having health data, the method comprising: receiving an input having a description related to health data; analyzing the description for anatomic site names, anatomic site name synonyms, laterality, modifiers, magnitude modifiers, laterality synonyms, modifier synonyms, magnitude modifier synonyms, directional synonyms, or combinations thereof to generate normalized data; and generating an output based on the normalized data, wherein the output includes a path that is selected, coordinated, targeted, described, translated, visualized, mapped, normalized, and / or encoded based on its spatial location or relationship, data-based location or relationship, context, directional location or relationship, or combination thereof.

[0055] In certain examples, the step of analyzing the description for anatomic site names, anatomic site name synonyms, laterality, modifiers, magnitude modifiers, laterality synonyms, modifier synonyms, magnitude modifier synonyms, directional synonyms, or combinations thereof to generate normalized data includes training, iteratively and / or recursively, the identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a modifier library. In certain examples, the step of analyzing the description for anatomic site names, anatomic site name synonyms, laterality, modifiers, magnitude modifiers, laterality synonyms, modifier synonyms, magnitude modifier synonyms, directional synonyms, or combinations thereof to generate normalized data includes analyzing the description for other data, wherein the other data includes symptoms, and wherein the step of generating an output based on the normalized data includes generating diagnostic recommendations, timelines, summaries, considerations, encodings, follow up questions, or combinations thereof.

[0056] Also provided herein is a system for processing an input having health data, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input having a description related to health data; analyze, using the data processing module, the description for anatomic site names, anatomic site name synonyms, laterality, modifiers, magnitude modifiers, laterality synonyms, modifier synonyms, magnitude modifier synonyms, directional synonyms, or combinations thereof to generate normalized data; and generate, using the generation module, an output based on the normalized data, wherein the output includes a path that is selected, coordinated, targeted, described, translated, visualized, mapped, normalized, and / or encoded based on its spatial location or relationship, data-based location or relationship, context, directional location or relationship, orcombination thereof.BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The patent or application file contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing(s) will be provided by the Office upon request and payment of the necessary fee.

[0058] FIG. 1: a schematic of a system, according to some embodiments of the disclosure.

[0059] FIG. 2: a schematic demonstrating the processing of an input by a data processing module, according to some embodiments of the disclosure.

[0060] FIG 3: a drawing of an anatomic representation, according to some embodiments of this disclosure.

[0061] FIG. 4: a grid of segments used for segmentation methods, according to some embodiments of this disclosure.

[0062] FIG. 5: an example of proportional and progressive segmentation of an input where the input includes a group of areas of interest, according to some embodiments of this disclosure.

[0063] FIG. 6: an example of proportional and progressive segmentation of an input where the input includes an isolated path, according to some embodiments of this disclosure.

[0064] FIG. 7: an example of an embedded label, according to some embodiments of this disclosure.

[0065] FIG. 8: an example interface of the GUI that allows a user to select which medical information to include in the embedded label, according to some embodiments of this disclosure.

[0066] FIG. 9: example anatomic representations that show two markers in multiple dimensions with high coordinate and spatial similarity, but high semantic dissimilarity, according to some embodiments of this disclosure.

[0067] FIG. 10: an example anatomic representation that shows the relationship between different defined paths, which is used to determine the target position of a first example marker and a second example marker, according to some embodiments of this disclosure.

[0068] FIG. 11: two example interfaces of the graphical user interface showing a visualization encoded into the encoded string, according to some embodiments of this disclosure.

[0069] FIG. 12: two example anatomic representations having velocity centers and direction planes, according to some embodiments of this disclosure.

[0070] FIG. 13: example anatomic representations having velocity planes that can be associated with anatomy data (such as hierarchical terminology) and to visual anatomic sites, according to some embodiments of this disclosure.

[0071] FIG. 14: an example anatomic representation that has been segmented into a plurality of predefined sites, which can enable volumetric and spatial analysis and measurements fromlanguage, code, or symbols describing anatomic sites, distributions, and modifiers of anatomic sites, according to some embodiments of this disclosure.

[0072] FIG. 15 an example anatomic representation having a marker thereon. The marker represents a closed transverse fracture of the middle phalanx of the ring index finger, according to some embodiments of this disclosure.

[0073] FIG. 16A-16T: examples of methods described herein, according to some embodiments of this disclosure.DETAILED DESCRIPTION

[0074] Throughout this disclosure, various publications, patents, and published patent specifications are referenced by an identifying citation. The disclosures of these publications, patents, and published patent specifications are hereby incorporated by reference into the present disclosure in their entirety to more fully describe the state of the art to which this invention pertains.

[0075] The disclosed systems and methods can relate to managing, organizing, visualizing, and analyzing health-related data. The systems and methods can build off the systems and methods disclosed within U.S. Application No. 18 / 225,872, filed on July 25, 2023, which is incorporated by reference to the extent that no conflict exists between such information and the other statements and drawings set forth herein. In the event of such conflict, including a conflict that would render invalid any claim herein or seeking priority hereto, then any such conflicting information in such incorporated by reference material is specifically not incorporated by reference herein. In certain examples, the systems and methods described herein can be combined with the claims recited in U.S. Application No. 18 / 225,872.

[0076] The system and methods can process various inputs, including text, audio, and visual data, to generate processed health data. The systems and methods can utilize anatomic representations and allows users to create and populate templates with health data. The systems and methods can handle multidimensional data and generate predictions, recommendations, and conclusions based on data analysis. The systems and methods can employ customized axes and proportional progressive segmentation to represent relationships between paths and anatomic sites. The systems and methods also can include a data processing module with libraries for training machine learning models and artificial intelligence. The systems and methods can perform volumetric and spatial analysis and enable 3D hierarchical model projection to 2D images that can be output into a plurality of layers in certain formats such as scalable vector graphics. Additionally, the systems and methods can align representations of physical objects or anatomywith nearby physical objects using sensors. The systems and methods can have practical applications in various domains, such as healthcare, record generation, record summarization, record calculation, and medical imaging.

[0077] References in the specification to “an embodiment” “embodiments,” “an example,” or “examples” indicate that the embodiment described may include a particular feature, structure, or characteristic, but not every embodiment may necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. The terms “for example,” or “e.g.,” indicate one or more non-limiting examples, even when the “non-limiting” term is not expressly written in the description.

[0078] As used herein, any method or process that include a generation step can include generating the subject from scratch, selecting a predefined subject from the libraries described herein, or populating a predefined template of the subject from the libraries described herein. As used herein, the term “encoded” can include encoded, encrypted, or combinations thereof. As used herein, the term “decoded” can include decided, decrypted, or combinations thereof. In certain embodiments, the term anatomic representation can include non-anatomic representations of other objects.

[0079] Traditional systems and methods have not applied, enhanced, translated, encoded, described, and coordinated language, maps, physical objects, language-vision pairs, visionlanguage pairs, image libraries to standardized or normalized data. Existing geographic map coordinate systems may not be suitable for mapping highly variable physical objects that typically have some constants (e.g. human anatomy has some constant features, such as two pupils, but pupillary height and distance is highly variable among individuals), so a proportionally segmented encoding system is a novel way to coordinate to physical locations on physical objects or in multidimensional space. Additionally, traditional systems and methods have not tracked, visualized, analyzed, communicated, translated, and / or described relative positions, surface areas, distributions, intensities, and / or other characteristics (e.g., morphology, diagnosis, evolution) in a proportional, normalized, and / or standardized manner. Moreover, traditionally, marking up data on paper (e.g., filling in a form), having conversations with another participant (e.g., a patient and a physician), and / or adding data to a data repository takes substantial human effort and expertise to input to coordinate, organize, and normalize all the data to a template.

[0080] FIG. 1 illustrates an example of a system 100. The system 100 can include a processor 102, a medium 104, a display 106, an input device 108, and an output device 110.

[0081] The processor 102 is in communication with the medium 104. The processor 102 can include any type of general or specific purpose processor. In certain examples, the processor 102 can include multiple processors. Non-limiting examples of the processor 102 include one or moregeneral -purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASTCs), processors based on a multi-core processor architecture, or combinations thereof. The processor 102 can be located on the input device 108, the output device 110, or a separate device, e.g., one or more servers, a phone, a tablet, a laptop, a computer, a headset, etc. In certain examples, the processor 102 is a quantum processor.

[0082] The medium 104 is a tangible, physical, non-transitory computer readable medium with processor-executable instructions stored thereon. The medium 104 is in communication with the processor 102. The medium 104 can be one or more memories and of any type suitable to the local application environment and can be implemented using any suitable volatile or nonvolatile data storage technology such as a semiconductor-based memory device, a magnetic memory device and system, an optical memory device and system, fixed memory, and removable memory. For example, the medium 104 can comprise of any combination of random-access memory (RAM), read only memory (ROM), static storage such as a magnetic or optical disk, hard disk drive (HDD), solid state drive (SSD), or any other type of non-transitory machine or computer readable media. The medium 104 can store inputs, outputs and various network types, such as neural networks and / or artificial neural networks; and models such as data models, language models, language-vision models, vision-language models, coordinated language models, and / or other models; engines such as search engines, research engines, anatomy-data engines, nonanatomy data engines, generation engines, dissection and categorization engines, coordinated language model engines, encoding engines, summarization engines, data-blocking engines, analysis engines, record generation engines, translations engines, morphology mapping engines, form processing engines, mapping engines, coding engines, search engines, and / or visualization engines; and / or capabilities such as artificial intelligence, machine learning, augmented reality, virtual reality, spatial computing, and / or computer vision. The medium 104 can be located on the input device 108, the output device 110, or a separate device, e.g., one or more servers, a phone, a tablet, a laptop, a computer, a headset, etc.

[0083] The processor-executable instructions can define a mapping platform and when executed by the processor 102, can render a graphical user interface (GUI) 112 on the display 106 thereby enabling a user to interface with the mapping platform. The GUI 112 can include one or more interfaces, also known as screenshots, with interactable objects, e.g., anatomic representations.

[0084] The mapping platform can include one or more modules. Non-limiting examples of the modules include a data processing module 1 14 and a generation module 1 16. Each of the plurality of modules can communicate with each other. It should be appreciated that these modules can be combined into fewer modules or separated into additional modules, as desired by one skilled in theart.

[0085] The data processing module 1 14 can be configured to process and convert data received from the input device 108 or other modules into processed data, as shown in FIG. 2, which can be used as an input or output for other modules. The data processing module 114 can also be configured to receive and store templates, each comprising a set of fields, on the medium 104. In certain examples, the data processing module 114 also stores, on the medium 104, a timeline of clinical activity, e.g., a timeline for a selected anatomical location, a particular diagnosis, etc., various different databases, with non-limiting examples including databases related to anatomy, modifiers of anatomy, anatomy visualizations (e.g., representations), health, patient, user, entity (e.g., a practice with multiple physical locations), permissions, and / or encounter data.

[0086] The data processing module 114 can include a library of models, including, language models, language-vision models, vision-language models, and / or other data and / or spatial models working separately or together, forming a coordinated language model engine. Various models can work omnidirectionally as shown in one example, with a language model, a vision-language model, and a language- vision model working together to form an example model that coordinates language, semantics, code, and vision. Non-limiting output examples include translations, coordinates, paths, maps, visualizations, pins, distributions, images, interactive language, encodings, relationships, diagnoses, morphologies, detections, categorizations, timelines, histories, forms, labels, descriptions, avatars, libraries, calculations, symbols, bookmarks, filenames, modified metadata, modified data, organized data, collated data, vertices, groups, axial changes such as mirroring, axial definitions, offsets, color coded legends, heatmaps, texture and pattern application, skin tone, skin type, procedures, tracking points, dynamic anatomic addresses, or combinations thereof. It should be appreciated that the aforementioned functions of the modules are non-limiting examples, and other aspects will be discussed throughout the disclosure.

[0087] Non-limiting example of models within the library of models include: a language model describing anatomy and relationships, morphology, and health data with healthcare language and synonyms in various linguistic languages; a vision-language model using computer vision, augmented reality, virtual reality, or artificial intelligence to detect and describe anatomy which can also calculate coordinates for each detection; a language- vision model that receives language, code or symbols to generate visualizations of anatomy and other health findings related to anatomy, morphology, or procedures; and / or a language-vision model that uses language to plot points and distributions (e.g. coordinates) on visualizations that contain anatomy. The data processing module 1 14 can be configured to process a received visualization for use within the mapping platform, e.g., processing a received image from the input device 108.

[0088] In certain examples, the data processing module 114 includes the following libraries (orcombinations thereof): a visual library, a cross-mapping library, a library of procedures, a library of billing codes, a library of common shorthand terms, a library of sounds, a modifier library, a vector database, or combinations thereof. It should be appreciated that these libraries may be combined or that other libraries may be employed within the scope of this disclosure. The vector database can enable semantic search to create a retrieval augmented generation (RAG) model.

[0089] The visual library can include medical documentation, such as anatomical illustrations / anatomic representations with predefined anatomical regions correlated with anatomic information, including an anatomic site name, description of the anatomic site, or combinations thereof. Each of the anatomic representations can be correlated to a particular anatomic representation identification number. In addition, each of the predefined anatomic sites in each of the anatomic representations can be correlated to particular anatomic site identification number. The cross-mapping library can include templates of other coordinate systems coordinated with the segmentation method described herein. The library of procedures and diagnoses can include a list of procedures and diagnosis. Each of the procedures and diagnosis can be associated with the anatomic sites affected by said procedure or diagnosis with a relevant global period. The library of billing codes can include standard billing codes, e.g., CPT codes copyrighted to AMA or other similar codes. Each of the billing codes can relate to a particular procedure or diagnosis at particular anatomic sites, and anatomic representation identification number can be organized into a range, hierarchy, multiple ranges, or combinations thereof to enable selection of a billing code. The library of common shorthand terms can include a list of shorthand terms for anatomic sites, diagnoses, procedures, orders, prescriptions, treatments, recommendations, morphologies, measurements, dates, other health data, or combinations thereof to be correlated with said anatomic sites. The library of sounds can include audio signatures for undesirable noises. Nonlimiting examples of undesirable noises can include common background noises, healthcare intercom announcements, healthcare machine sounds, music, or combinations thereof. The modifier library can include anatomic site names, anatomic site name synonyms, laterality, modifiers (e.g., prefixes, suffixes, central zone modifiers, directional modifiers), magnitude modifiers, central zone components, laterality synonyms, modifier synonyms, magnitude modifier synonyms, directional synonyms correlated to anatomic sites.

[0090] Throughout this disclosure, the visual library can include maps, anatomic maps, object maps, avatars, avatar maps, images, vectors, coordinates, one or more knowledge bases, languagevision pairs, vision-language pairs, paths, path groups, custom axes, videos, scanned records, anatomic site list data, modifier data, laterality data, three-dimensional (3D) images or multimedia, or combinations thereof. In certain embodiments, the visual library may be used to select, target, isolate, display, plot, highlight, calculate, coordinate, generate, translate, encode, describe, 1summarize or combinations thereof anatomy information, patient information, health information, object information, or combinations thereof. In certain embodiments, the visual library, languagevision pairs, or vision-language pairs contain labeled data in association with the images such as anatomic information, morphology information, skin type information, skin tone information, diagnosis information, procedure information, or combinations thereof. In certain examples, machine learning is supervised, unsupervised, or combinations thereof. In certain embodiments, the visual library also contains digital slides linked to diagnosis information, microscopic description information, gross description information, patient demographics, or combinations thereof which can be sources of truth for training models described herein.

[0091] The generation module 116 can be configured to correlate and select one of templates based on user input, e.g., a selected procedure, a location on an anatomic region, etc., and populate the set of fields of the selected template, e.g., text describing the selected procedure, text describing the location of the anatomic region, a multimedia item associated with the anatomic site of the patient, etc. The generation module 116 can be further configured to output health records, such as digital data to the GUI 112 and output data to the output device 110, e.g., a printer, to generate physical outputs, such as labels, images, forms, maps, and / or other health records and generate a database record suitable for an electronic health based on the populated template.

[0092] The display 106 can be in communication with the medium 104. The display 106 facilitates presentation of the GUI 112. The display 106 can be located on the input device 108, the output device 1 10, or a separate device. Non-limiting examples of the display 106 can include different display technologies, such as cathode ray tubes (CRT), liquid crystal displays (LCD), Organic light emitting diodes (OLED), electronic paper (e-ink), etc.

[0093] The input device 108 can be in communication with the medium 104 and the display 106. The input device 108 enables a user to interact with the mapping platform, e.g., via the GUI 112. The input device 108 can be the same as the output device 110 or a separate device. In certain examples, the display 106 is on the input device 108. Non-limiting examples of the input device 108 include tablets, smartphones, computers, headsets, cameras, scanners, goggles, sensors, speakers, microphones, other electronic devices, etc. In certain embodiments, the input device 108 includes an image capturing device configured to scan a physical representation with markups of the anatomic representation, as will be discussed in further detail below. The input device 108 can be configured to enable a user to transmit data to the mapping platform, for example, text, images, and video. The mapping platform can receive a multiple of different inputs via the input device 108. Non-limiting examples of inputs can include text, language, code, coordinates, images, illustrations, visualizations, handwriting, typed characters, QR codes, avatars, 3D models, videos, eye movements, gestures, markups, annotations, selection on the GUI 112, and / or voice as non-limiting examples. The input can also be paper, such as a map or visualization (e.g., representation) printed on paper (which is subsequently digitize and sent be the input device 108), or an electronic device combined with paper, such as a pen that detects the position of the markup and / or annotation as a user marks up a paper, as other non-limiting examples.

[0094] In certain embodiments, the input device 108 is a touch screen that has a combination of embedded sensors, light sources (e.g. laser light, spectral light, ultraviolet light, infrared light, polarized light, etc.), polarizers, filters, lenses, cameras, lasers, rulers, embedded color gradients, Light Detection and Ranging (LIDAR), processor, wireless communication module, internal storage, communication port, battery, graphical processor unit (GPU), microphone, speaker, physical button, contact microscopy, high resolution image sensor, and / or a charging port.

[0095] FIG. 2 illustrates a schematic demonstrating the processing of an input by the data processing module 114 according to some embodiments. The input from the input device 108 or from a previous output can be processed by the data processing module 114 comprising language models, vision-language models, language-vision models, other models, or combinations thereof to communicate in a coordinated language model type model. The data processing module 114 can receive the input and generate an output that includes processed data. The output can be presented on the GUI 112, saved to the medium 104, and / or sent the output device 110, or combinations thereof. The output can be recycled back into the system 100 as an input.

[0096] FIG. 3 illustrates an example of an anatomic representation 118, also known as a diagram, displayed on the GUI 112. The anatomic representation 118 can have a plurality of predefined anatomic sites, also known as paths 120, with custom axes and segmentation instructions. In certain embodiments, paths 120 have associated relational instructions, modifiers, angles, direction planes, laterality, prefixes, central zone descriptors, suffixes, synonyms, or combinations thereof. An example path 121 is shown with additive color coding shown in grayscale shading. Paths 120 are coordinated, grouped (e.g., in path groups), ordered, and layered with identifiers such as those for the anatomic site name, translation or code. In certain embodiments, single identifiers are unique, while in certain embodiments multiple identifiers are combined to form unique identifiers. Each path 120 highlighted may have one or more custom axes 122 (shown in solid white lines outlined in FIG. 3), axial definitions 124 (with each custom axis shown as white letter outlined in black in FIG. 3, with “S” meaning Superior, “L” meaning Lateral, “I” meaning Inferior, and “M” meaning Medial), angles (as illustrated by the non-right angles of the axes 122 in this embodiment), segmentation instructions 126 (to describe segmentation in the path 120 through language, code, symbols, highlighting, pattern application, and visually) as illustrated by triangles pointed at a custom position on the custom axis and defined by a percentage, proximity, or deviation from center or custom offset; a color, pattern, texture, pin,multiple pins, multiple patterns or textures, area of self, area relative to group, area relative to diagram area relative to multiple diagrams, area relative to multiple groups, opacity, intensity, or other metadata associated with it. Each of the paths 120 may also be within one or more direction planes 128. The direction plane 128 is shown in FIG. 3 as being split into two direction planes 128 illustrated as solid black lines outlined in white that are split by a gray line 130 outlined in white. The direction planes 128 can be independent of the paths 120 and transect them, as shown in the embodiment crossing multiple paths 120 with a different angle from the custom axes 122 of the paths 120. Direction planes 128 can be square, rectangular, or uniquely shaped and curved. Direction planes 128 can have one or more directional instructions 132 shown in FIG. 3 as black arrows with white outlines connected to single black letters with white outlines. In this nonlimiting example for the direction planes 128, “A” means anterior, “S” means Superior, “I” means Inferior, “P” means Posterior, “L” means Lateral, “M” means Medial. Two or more direction planes 128 can belong to a direction group 134, which also has its own set of directional group instructions 136, as shown in FIG. 3. The directional group instructions 136 are shown as black arrows with white outlines connected to black letters with white outlines in the embodiment, with “Sup” meaning Superior, “Lt” meaning Left, “Rt” meaning Right, and “Inf’ 132 meaning inferior in FIG. 3. A direction group 134 can also be formed by a path group, such as all of the paths 120 illustrated on the left face in FIG. 3. Each of the paths 120, path group, direction plane 128, and direction group 134 can have its own custom ordering, properties, rotation, axial definition, order, topography, pattern, color, opacity, intensity, or texture. Layering and ordering of paths 120 are shown by the legend 138 (shown in FIG. 3 and which may be color-coded) correlating with the tip of the cursor 140 when shown on the GUI 112. Each path 120, path group, direction plane 128, or direction group 134 may have metadata such as identifiers, axial definitions 124, segmentation instructions 126, central definitions (e.g., how do we define the center of the path? With a term “central” or “mid” or “midline” as some examples), prefixes and suffixes, laterality such as left, right, or bilateral. Paths 120 do not have to be contiguous as one skilled in the art would know (such as a compound path in vector graphics). The metadata derived from a map position, such as the cursor 140 in this embodiment, communicates with the processor 102 to transform, translate, relate, calculate, and correlate the data delivered from the data processing module 114, which can be on the medium 104. When two or more points of interest exist on the same path 120 or on the same or similar direction plane 128, the points can be related to one another with natural and coded language by calculating their positions relative to the custom axial definitions through communication with the data processing module 114. Since paths 120 do not need to have custom axial definitions, and since it may be desirable to describe relationships between two pins on different paths 120, the axial definitions of a path group, a direction plane 128, or a direction group134 act as relationship calculator to relate the points with natural and coded, machine readable language through interaction between the medium 104, the processor 102, and / or other components of the system 100. When points of interest are to be related to one another, the magnitude based on the deviation from center of the custom axis of the path 120, path group, direction plane 128, and / or direction group 134 as one example; and / or the magnitude of physical distance between the points of interest (e.g. pixels in any direction as one example) is used to apply “magnitude modifiers” such as “barely” and “very” to describe relationships and / or to omit directional semantic descriptions that may be confusing to human interpretation. For example, if a point is directly above another point (+y on y axis) and minimally changed on the (x axis), the x axis description can be omitted by the data processing module 114 to minimize human confusion in the interpretation of the relational description.

[0097] Various methods are described herein. While these methods are shown and described as a series of actions, it is to be understood and appreciated that the methods are not limited by the order of acts, as some acts may in accordance with these methods, occur in the order shown and / or described, in different orders, concurrently with other acts described herein, and / or be omitted.

[0098] As shown in FIG. 16A, a method 200 for generating an output having a segmented input can comprise a step 202 of receiving an input from the user; a step 204 of identifying a landmark within the input; a step 206 of segmenting the input into a plurality of segments to form a segmented input; a step 208 of generating a path or a path group based on the landmark; a step 210 of encoding the path or the path group based on the plurality of segments; and a step 212 of generating the output having the segmented input with the encoded path or path group.

[0099] The step 202 can include the user sending the input to the system 100 via the input device 108. Non-limiting examples of the input can include medical records, for example, videos, images, anatomic representations / diagrams / maps, forms, or combinations thereof. The input can be saved on the medium 104. In certain embodiments, the input can define custom segmentation (e.g., by drawing, shading, or otherwise selecting) areas on an object within the input to which to attach data. The defined custom segmentation can define a new area of interest on the object that can be automatically described, calculated, encoded, tracked, or combinations thereof, e.g., by the data processing module 114, to generate processed data. In certain embodiments, the defined custom segmentation can be thought of like a "legal description" for the defined area on the object like would be done for parceling of land, which is improved by applying proportional and progressive segmentation to objects with variable sizes but similar physical properties. In certain embodiments, the object is a map, avatar, or image of anatomy. In certain embodiments, the object is a physical object like a piece of paper. In certain embodiments, the object is a digitized object on the GUI 112 in communication with the input device 108.

[0100] The landmark can include an anatomic site, a group of anatomic sites, two or more points on the input, an area of interest, or a group of areas of interest. In certain examples, the step 204 includes a user manually designating where the landmark resides in the input. This can be accomplished by the input be presented on the GUI 112. The user can mark where the landmark resides in the input using the GUI 112.

[0101] In other examples, the step 204 includes comparing the input to a visual library in the data processing module 114. This can be accomplished using artificial intelligence, machine learning models, algorithms, or other similar means. The visual library can include medical documentation, such as anatomic representations with predefined anatomic sites or predefined groups of anatomic sites correlated with anatomic information, including an anatomic site name. It should be appreciated that the predefined anatomic site can include a hierarchy of sub-anatomic sites within anatomic sites correlated with anatomic information. If the input substantially matches one of the anatomic representations, landmarks can be identified based on matched predefined anatomic sites within the matched anatomic representation. In certain embodiments, the input is matched based on vision, language, text, code, or images.

[0102] In certain examples, the step 204 comprises training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm. The training data can include the visual library of the data processing module 114. The identification machine learning model can receive the input and output the identification of the landmark within the input based on matched predefined anatomic sites within the matched anatomic representation. It should be appreciated that the landmark can include one or more landmarks based on the input. Non-limiting examples for the machine learning algorithms includes span categorization-based algorithms, range categorization-based algorithms, or other similar algorithms, or combinations thereof. In certain embodiments, the training data for span categorization includes a knowledge base containing standardized anatomic site names, anatomic site synonyms, lateralities, modifiers, custom axes, custom axial definitions, symbolic descriptions or groups, coded descriptions, language descriptions, coordinate based descriptions, hierarchical relationships, diagnosis information, morphology information, skin type information, symptom information, procedure information, or combinations thereof.

[0103] The step 206 can include proportionally segmenting the input into the plurality of segments to form the segmented input. Each segment can be further segmented into a plurality of subsegments. In certain examples, the segmentation is performed progressively. For example, FIG. 4 shows an example grid of segments 214. A top right segment 216 of the grid of segments 214 is segmented further into a grid of subsegments 218. A bottom right subsegment 220 of the grid of subsegments 218 is segmented further into a grid of sub-sub-segments 222. It should beappreciated that this hierarchy of segments within segments can be increased or decreased depending on the desired accuracy, precision, or combinations thereof.

[0104] In certain examples, the number of segments can be to the third power as shown in FIG. 4. In other examples, the number of segmentations can be to the level of single individual pixels or to pixel groupings in digital images. The segmentation can be performed across three- dimensional space (e.g., added a third dimension to the grid shown in FIG. 4). Further axes may also be added to facilitate multidimensional inputs. Proportional segmentation can mean the segments are not necessarily perfectly square, and they are shown as rectangles. Each segment can be proportionally segmented based on the parent grid in certain embodiments. In other embodiments, segmentation can be progressively changed based on the shape of each segment or based on custom segmentation boundaries. Segmentation boundaries can be non-rectangular, curved, convex, concave, and / or irregularly shaped.

[0105] The step 208 can include generating a path or a path group that corresponds to the landmark. For example, the landmark may correspond to a single path, however, in other examples, the landmark may be capable of being segmented further into distinct sub-landmarks to form a path group.

[0106] The step 210 can include encoding the path or the path groups based on its relation to the plurality of segments, e.g., encoding its spatial position related to the plurality of segments. For example, FIG. 4 shows a grid of six segments encoded with the following meaning: TL = Top Left; T = Top Center; TR = Top Right; L = Left Center; C = Center; R=Right Center; BL=Bottom Left; B=Bottom Center; BR=Bottom Right. The example path 224 shown in FIG. 4 can be encoded as TR-BR-C indicating that it points to the top right segment of the first grid of segments 214, the bottom right segment of the sub-grid of subsegements 218, and the center segment of the second sub-grid of segments 222. Generated descriptions can be language-based, math-based, code-based, coordinate-based, or combinations thereof. With proportional and progressive segmentation enabled by the system 100, aligning normalized and / or standardized map data to objects adjusts for objects of different shapes and sizes, generating normalized and standardized data as processed data. The description can include or be capable of, together with other data, calculate the surface area of said defined area. As one non-limiting example, by aligning an anatomic map or avatar to two different people of two different sizes, the "legal descriptions" can be normalized to be similar with similar calculations (e.g., the same body surface area with the same description would be a different actual area).

[0107] The step 212 can include presenting the output on the GUI 112 on the display 106. In certain examples, the output is a digital file or a printed physical document. In certain examples, the output is sent to the output device 110 or used as a training data for identification machinelearning model. The output can be saved on the medium 104. In certain examples, the method can further include a step 226 of coordinating the segmented output with other coordinate systems. The step of coordinating the segmented output with other coordinate systems can include cross mapping the segmented output with other coordinate systems using templates in a cross-mapping library of the data processing module 114. The cross-mapping library can include templates of other coordinate systems coordinated with the segmentation method described herein.

[0108] In certain embodiments, the system 100 can be configured to generate the output having the segmented input. For example, the input device 108 can be configured to receive the input from a user. The data processing module 114 can be configured to process the input to identify the landmark within the input. The data processing module 114 can be configured to segment the input into the plurality of segments; generate the path or path group based on the landmark; and encode the path or the path group based on the plurality of segments. The generation module 116 can be configured to generate the output having the segmented input. In certain examples, the data processing module 114 can be further configured to coordinate the segmented output with other coordinate systems by cross mapping the segmented output with the other coordinate systems the cross-mapping library of the data processing module 114. In certain examples, the data processing module 114 can be further configured to calculate the surface area within the path or the path groups based on the plurality of segments.

[0109] FIG. 5 illustrates an example of proportional and progressive segmentation of an input where the input includes a group of areas of interest 228. The group of areas of interest 228 is the United States. The example landmark 230 shown in FIG. 5 can be encoded as US-BR-TC-TR-C. The system 100 is enabled to target the correct location using the coordinated models, for example, instead of using latitude and longitude, to find the location. Breaking down the automatic encoding shown in FIG. 5, US means the group of areas of interest 228 defining the United States, BR determines the first next segment of interest is in the bottom right segment of the path group, TC determines the next segment of interest is in the Top Center segment of the BR segment, TR determines the next segment of interest is in the Top Right segment of the TC segment, and in the next segment of interest C determines we are in the Center of the preceding TR segment. As shown in FIG. 5, some segments can be void spaces 232, such as the US-TR space and the US- BR-BR space, which means there are no map elements related to the US path group in this embodiment. However, other path groups (not shown) could occupy space within the void space 232. For example, Canada could be a different path group located in at least US-C, US-RC, US- TC; and US-TR; and North America could be another path group located in this grid that is proportionally expanded to include Canada and Central America. Of note, expanded path groups may change the grid in certain embodiments, so localization with progressive and proportionalsegmentation is relative to the largest path group (in this case, US) defined by the encoding and / or to the paths within the path group (in this case, 50 US states). In certain embodiments the surface area of each segment and subsegment is calculated based on void space, map space, highlighted space, and / or other variables (e.g., highlighted space, drawn space, selected space, lassoed space, associated diagnosis, associated count, associated morphology, associated description, or combinations thereof).

[0110] Segments can have different proportions. For example, segments can be taller than the segments are wide resulting in the same localization targeting relative to the path group based on the encoding generated by the system 100. Other embodiments segment, coordinate, and encode locations on physical objects, anatomy, geography, floor plans, microscopic coordinates, macroscopic coordinates, and other mappable locations. In certain embodiments, the localization enabled by the system 100 can simultaneously coordinate and / or relate to other coordinate systems such as geographic coordinates (including, for example, latitude, longitude, and elevation), anatomic map coordinates, fictional map coordinates, physical object coordinates, 3D coordinates, avatar coordinates, image coordinates, and / or tracked coordinates (e.g. in videos or photo series that change over time) as non-limiting examples. In certain examples, as the borders of paths or path groups change, as defined by bounding boxes, the segmentation layout (e.g., of the grid) can dynamically change with it (e.g., perspective warp, rotation, scaling).

[0111] FIG. 6 illustrates an example isolated path 234 with progressive segmentation relative to the path and custom encoding. FIG. 6 is an isolated path with progressive segmentation relative to the path along with custom encoding of the localization based on the proportional grid generated by the generation module 116. The encoding US-OH-TR-C-BR locates and / or targets the point 236 within the grid in FIG. 6. The encoding US-OH-TR-C-BR means the following: US = United States path group; OH = Ohio isolated path to segment; TR= Top Right; C = Center; BR = Bottom Right. In this example, the partial void space may contain other paths such as another state (e.g. the bottom right grid 238 contains approximately 25% isolated path for Ohio, and 75% for other states); and the surface area within each path segment relative to the grid can be processed (e.g. by the data processing module 1 14) for actual surface area of the path relative to each grid item. The black silhouette of Ohio surrounded by the bounding box in FIG. 6 also demonstrates path isolation and targeting enabled by the system 100.

[0112] Systems and methods described herein enable a novel mapping and spatial encoding and coordination system for physical objects, land, sea, anatomy, maps, void spaces, descriptions, and area calculations. Compared to latitude and longitude and elevation, the system 100 can also be layered with different sizes of layers, creating multidimensional space, spatial relationships, and data based relationships; and additional paths, path groups, and path segments can have variousmeanings attached to them. Furthermore, in certain embodiments, a Segment Anything Model (SAM) within the data processing module 1 14 can be used, which uses artificial intelligence to cut out and define areas of interest within 2D, 3D, or other dimensions of space / video spaces. In certain embodiments, the system 100 uses segmented and sub-segmented landmarks within the cut out and applies custom axes or direction planes to segments, subsegments, and segment groups; and automatically codifies or encodes locations within each segment and related to each segment.

[0113] As shown in FIG. 16B, a method 300 can include a step 302 of detecting a reference point or reference area on a physical object; a step 304 of aligning the reference point or reference area to spatial data, custom axis data, database data, or to detected features (topology, morphology, diagnosis, color, counts, surface area, etc.); and a step 306 of calculating and encoding the point or area in relation to the detected and aligned reference point, with progressive and proportional segmentation.

[0114] With respect to FIG. 16C, a method 400 for generating an embedded output can comprise a step 402 of receiving an input from the user; a step 404 of processing the input; and a step 406 of applying an embedded label to the input to generate the embedded output.

[0115] The step 402 can include the user sending the input to the system 100 from the input device 108. Non-limiting examples of the input can include medical records, for example, videos, images, anatomic representations / diagrams / maps, or combinations thereof. The input can be saved on the medium 104.

[0116] The step 404 can include identifying medical information from the input and recording said medical information on the medium 104; generating a description of the input based on the medical information; generating visualizations based on the medical information, e.g., line art of anatomic regions, including descriptions of anatomic sites, other medical information, or combinations thereof. This can be accomplished by comparing the input to the visual library and determining the description on the input or generating the visualizations of the input based on matched information in the visual library of the data processing module 114. The medical information can include diagram information, diagnosis information, patient information, or combinations thereof.

[0117] In certain examples, the step 404 comprises training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm. The training data can include the visual library of the data processing module 114. The identification machine learning model can receive the input and output the medical information within the input based on matched information in the visual library of the data processing module 1 14. Nonlimiting examples for the machine learning algorithms includes span categorization-based algorithms, range categorization-based algorithms, or other similar algorithms, or combinationsthereof. In certain embodiments, visualizations are selected from standardized visualizations in the visual library rather than being generated, to enable reproducibility over time.

[0118] The step 406 can include embedding the embedded label having the medical information, including a description of the medical information, visualizations based on the medical information, or combinations thereof, in the input. In certain examples, the embedded label includes an encoded portion. The encoded portion can be presented as a QR code, bar code, or other similar form of encoding information. In certain examples, the medical information can include translated descriptions, encodings, symbols, diagnosis information, patient information, other health-related data, or combinations thereof.

[0119] The step 406 may be accomplished manually or automatically. For example, the embedded label can be automatically applied to the header, footer, or other portions of the input to generate the embedded output. In certain examples, the embedded label is superimposed over a portion of the input. The embedded label can be scaled according to the desired dimensions of the embedded output. For example, if the embedded output is in a A4 standard, the embedded label can be scaled to fit within said dimensions. In certain embodiments, the QR code is sized correctly based on the output paper size so that readability is ensured. In certain examples, the step 406 includes presenting the input with the embedded label on the GUI 112 on the display 106. In certain examples, the input with the embedded label is sent to the output device 110 or used as a training data for identification machine learning model. The input with the embedded label can be saved to the medium 104.

[0120] With reference to FIG. 7, an example embedded label 408 is shown. The embedded label 408 includes example medical information 410, including a description of the medical information and a visualization based on the medical information, and an example encoded portion 412. As described herein, the embedded label 408 can be applied to the header, footer, or other portions of the input to generate the embedded output. The embedded output can be a digital file or a printed physical document.

[0121] As shown in FIG. 8, an interface 414 of the GUI 112 can allow the user to select which medical information to include in the embedded label. In certain examples, the user can select where the medical information will be located within the embedded label. For example, as shown in FIG. 8, the user can choose to position the diagram information on the top right, top left, bottom left, or bottom right portion of the embedded label. The user can choose to position the diagnosis information on the top right, top left, bottom left, or bottom right portion of the embedded label. The user can further choose to position the patient information on the top right middle, top left middle, bottom left middle, or bottom right middle portion of the embedded label. A portion or all of the medical information in the embedded label can be encoded as the encoded portion. Incertain examples, the encoded portion is provided in addition to the medical information in the embedded label. It should be appreciated that other layouts of the digital label are contemplated within the scope of this disclosure.

[0122] The step 406 can further include depersonalizing the medical information to generate depersonalized medical information and applying the embedded label having the depersonalized medical information to the input to generate the embedded output. Depersonalizing the medical information can include removing / obfuscating portions of the medical information that ties the medical information to a particular patient. For example, depersonalizing the medical information can include removing information that cannot be shared due to the Health Insurance Portability and Accountability Act of 1996 (HIPAA), or other similar patient privacy laws, guidelines, or policies. In certain embodiments, the identifiable medical information is kept in a standardized location related to the embedded header, label, or image to enable batch deidentification.

[0123] In certain embodiments, the system 100 can be configured to apply the embedded label to the received input to generate the embedded output. For example, the input device 108 can be configured to send the input from the user. The data processing module 114 can be configured to process the input. The data processing module 114 can be further configured to identify medical information from the input and record said medical information; generate a description of the input based on the medical information; generate visualizations based on the medical information, e.g., line art of anatomic regions, including descriptions of anatomic sites and other medical information; or combinations thereof. The generation module 116 can be further configured to generate the embedded output with the embedded label. The embedded output can be a digital file or a printed physical document.

[0124] With respect to FIG. 16D, a method 500 for regenerating decoded data can comprise a step 502 of scanning the embedded output with the embedded label to generate decoded data; and a step 504 of regenerating the decoded data.

[0125] The step 502 can include the user scanning the encoded portion of the embedded label with the image capturing device of the input device 108. In certain examples, a computer automatically scans the encoded portion of the embedded label. In certain examples, the step 502 includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm. The training data can include the visual library of the data processing module 114, e.g., anatomic representations with predefined anatomic sites correlated with anatomic information and the input with the embedded label. The identification machine learning model can receive the encoded portion of the embedded label and output the decoded data. Non- limiting examples for the machine learning algorithms includes span categorization-based algorithms, range categorization-based algorithms, or other similaralgorithms, or combinations thereof.

[0126] The step 504 can include outputting the decoded data to the user. For example, presenting the decoded data on the GUI 112 on the display 106 that includes medical information processed from the input; a description of the input based on the medical information; and visualizations based on the medical information, e.g., line art of anatomic regions, including descriptions of anatomic sites, other medical information, or combinations thereof. In certain examples, the encoded portion links to a static record of the patient, e.g., the medical information linked to by the encoded portion is always the same. In other examples, the encoded portion links to a living record of patient, e.g., the medical information linked to by the encoded portion can be updated, and once updated, the encoded portion links to the updated medical information. The decoded data can be sent to the output device 110 and / or saved on the medium 104.

[0127] The method can further include a step 506 of authenticating the user before the step 504. The step 506 can include confirming a password of the user, an occupation of the user, other similar factors, or combinations thereof. If the user is unauthenticated, the decoded data may only include depersonalized medical information. If the user is authenticated, the decoded data may include the medical information without being depersonalized.

[0128] In certain embodiments, the system 100 can be configured to regenerate the decoded data by scanning the encoded portion of the embedded label. For example, the image capturing device of the input device 108 can configured to scan the encoded portion of the embedded label. The generation module 116 can be configured to regenerate the processed data, e.g., medical information processed from the input; the description of the input based on the medical information; and the visualizations based on the medical information, e.g., line art of anatomic regions, including descriptions of anatomic sites, other medical information, or combinations thereof. In certain embodiments, backup codes, coordinates, diagram identifiers, or combinations thereof are included on the label and can regenerate the anatomy information, anatomy visualizations, diagnosis information, other health data, or combinations thereof.

[0129] In certain embodiments, the patient information and protected health information is always presented in a standardized location, e.g., at the top right of the label. This can allow the system 100 to perform analytics, e.g., with the data processing module 114, e.g., just on the left side of the label. The embedded label data can be redacted or cropped out by the system 100, automatically, to provide de-identified data sets useful in research. In certain embodiments, the data in the embedded label can also be used to generate a symbolic filename, and the symbolic filename can also be used to generate a detailed description about the image. In certain embodiments, QR codes can re-create the visualization and other health data (e.g., order, pin color, pin type, morphology, diagnosis, patient demographics, etc. as non-limiting examples) at differenttime points and in different systems. In certain embodiments, output document dimensions are used to determine the dimensions of the embedded label data. Then, in certain embodiments, when the image is faxed with the embedded labels, the integrity and readability of the labels is maintained. This can allow for faxing at lower resolution without loss of the regeneration data and with a taxable generated visualization.

[0130] In certain embodiments, the taxable generated visualization is line art with a consistent pin size regardless of diagram size. In certain embodiments, the visualization is modified from the visual library stored of images of the data processing module 114, stored on medium 104, and the images can be modified by the generation module 116 or other modules in the system 100. In certain embodiments, the pin location and order marker are variable. In certain embodiments, the received fax is used as an input to regenerate health data in a different system. In certain embodiments, the received fax image is a closeup, dermoscopy image, report (e.g., spectral imaging report; genetic report), or is uninterpretable, so the digital label communicates the reproducible anatomic location with enhanced readability. In certain embodiments, the embedded labels evolve or compound over time with new or updated information as it becomes available. In certain embodiments, multiple embedded labels are added in a sequence such as a chronological sequence, with different and evolving visualizations associated with the different information.

[0131] Some non-limiting examples of different information can be different anatomic views, different pin or area information, different or evolving diagnosis information, different images, different names, different codes, different languages, and different stories. In certain embodiments, embedded labels contain visual descriptions and / or visualizations, language descriptions, and / or coded descriptions of anatomic sites in multimedia. The system 100 enables generation (e.g., through the generation module 116) of a visual representation of a multimedia location wherein the location is an anatomic site, and at least one of a language-based description, a code-based description, a coordinate-based description, a calculated description, a symbolic description for use on a label. The label can be a physical label on a physical document, or a digital label embedded in a digital file stored in the medium 104. The label or its components can also include other information such as diagnosis information, morphology information, symptom information, procedure information, patient information, or other health data. The digital label or its individual components can be selected to include over selected areas of the image, or in a header, footer, or other border of the image, with alternative, customizable, and definable positions for display of the stored information embodied in FIG. 8. Digital labels are stored, with or without images, reports, graphs, and other multimedia, on the medium 104.

[0132] In certain embodiments, identifiable information can be obfuscated in the image at the time of capture. In certain embodiments, the digital label can be shown on the GUI 112 at time ofimage capture; and when the capture device contains a display screen, the generated anatomic visualization can be shown over the camera as an alignment overlay. In certain embodiments, the alignment overlay can be adjusted for rotation, scale, and angle. In certain embodiments the code can be a barcode or QR code, a dynamic anatomic address code string, a mixture of codes and language and symbols, or combinations thereof. In certain embodiments, the embedded label data stored in the medium 104 can be analyzed by artificial intelligence, machine learning and other processing (e.g., data processing module 114) to output organized and summarized health data (e.g., by the generation module 116).

[0133] FIG. 8 as detailed above, shows various alternative options to layout the digital information stored in the medium 104. In certain embodiments, the embedded label data can be used to re-generate the same exact anatomic site target or visualization on a map, avatar, or new image with the correct language and context. This does not just apply to pins, but can also be used to generate site regions, groups, and distributions. In certain embodiments, multiple labels can also be used to regenerate an ordered and organized list and map locations.

[0134] Faxed black-and-white poor-quality photos are the current state of the art to maintain regulatory compliance in the United States and are the most common way to transmit photos in healthcare. In certain current workflows, at the time of photograph, a physical label with patient information is manually filled in with a date, initials of photographer, lesion order, and a handwritten anatomic site (that may be incorrect or imprecise). The physical label may be stuck onto the patient’s body before the photograph is taken. In certain embodiments of the system 100, a digital label containing this information plus a generated, selectively modified, or selectively displayed visualization (e.g., from a visual library in the medium 104) and optionally other information is generated (e.g., by the generation module 116) to create an improved and automatic labeling and visualization method for photos captured by the input device 108. This digital label is stored and embedded on the multimedia, such as a JPEG image, PNG image, SVG image, PDF image, or video as some non-limiting examples. In certain embodiments, when a still / static version of the multimedia is later faxed, the generated, selectively modified, or selectively displayed visualization faxes with less distortion or pixelation artifact. In certain embodiments, the generated visualizations are line art isolated from a standardized collection within a visual library for better quality faxing and better reproducibility. In certain embodiments, faxed codes included on the label, such as QR codes or dynamic anatomic address codes as non-limiting examples, are applied. In certain embodiments, when the static version of the multimedia is received as a fax, the embedded label can be used as an input to the system 100 to regenerate, organize, remap, order, and describe the image and / or to generate new forms that contain the generated visualization, location, diagnosis, patient information, or other information automatically filled in.In certain embodiments, the code strings in the embedded label are used to generate or open specific multidimensional buckets linked to the anatomic site, distribution, and / or region so that additional information can be added relevant to the same anatomic site, distribution, and / or region.

[0135] This non-limiting embodiment illustrates an improvement in the current state of the art, which does not generate accurate, precise, or isolated anatomic visualizations for digital labels and visibly embed them into multimedia. The labels also fax and print well and can be used as a new input to regenerate precise anatomic descriptions, location data, visualizations, patient data and to generate, collate and summarize new data about the site, region distribution, or location in a context aware manner.

[0136] In certain embodiments, digital labels stored on the medium 104 and embedded into multimedia contains at least a generated, selectively modified, or selectively displayed visualization representative of the anatomy in the photograph, and also includes translated descriptions, encodings, symbols, diagnosis information, patient information, and other health data. In certain embodiments, the digital label code can be a QR code that is placed over the multimedia, in a header, footer, or around the multimedia. In certain embodiments, the digital label contents can be selected by the user for hiding or display, and the location of the label components can be selected.

[0137] In certain embodiments, the input device 108 can be configured to facilitate the user interacting with the system 100 using eye tracking. This can be used to generate anatomic site descriptions and visualizations based on a physical object, person, map, avatar, or other similar form. In certain embodiments, eye tracking sensors are used as input to an input device 108. The focal point of the user’ s eye can be used to create a multidimensional, enhanced text description, code description, symbolic description, and to generate, selectively modify, or selectively display a visualization of a pin, distribution segment, or distribution, and to interact with lists, and to generate storage buckets in which to store information, and to display multidimensional anatomy. In certain embodiments, the eye tracking interacts with hand gestures (e.g. pointing, pinching, touching a physical object as non-limiting examples) to interact with anatomy and health data, and the GUI 112 such as with dropping a pin, moving a pin, selecting a different level of hierarchy, reordering a list to dynamically reorder on a map, or combinations thereof.

[0138] In certain embodiments, the eye focal point on the GUI 112 can also open up a camera function on the input device 108, such as a wearable headset that contains the image capture device, to initiate camera capture and automatically store the image in the correct data bucket. Data buckets stored on the medium 104 can be multidimensional when they involve multidimensional health data, like with anatomy. In certain embodiments, capturing an image or other multimedia of a patient, person or other physical object automatically generates a language-based description of the location, a coded description (e.g., that is progressively and proportionally segmented), a symbolic description, and a visualization from a library stored in the data processing module 114 on the medium 104. In certain embodiments, the generated visualization has its own custom defined coordinates in at least a path, path segment, path group, distribution, or direction plane. In certain embodiments, the input device 108 can capture multimedia and simultaneously generate standardized anatomy data and visualizations about the multimedia. In certain embodiments, the input device 108 captures, describes, encodes, and / or generates visualizations (using the described systems and methods) relative to physical objects in augmented reality, virtual reality, spatial reality, or mixed reality.[00139 J The systems and methods described herein can be used for generating pathology reports wherein there are language components, coded components, clinical recommendation components, diagnosis components with codes, closeup view components, far out view components, digital slide components (e.g., with different lighting settings, staining properties, zoom levels, polarizations, fluorescence properties, cross-mappings, images, links to clinical images, links to dermatoscopic images, links to clinical and microscopic morphology standards, anatomic sites, anatomy based considerations, and / or links to patient information). Each component can be translatable into a desired language or code set based on coordination within the system 100. In certain embodiments, image analysis of the slide references the coordinated language model within the system 100 for instructions on describing the position, slide number, area within the slide with specific findings, and also generates descriptions of the findings on the slide and descriptions of the microscopic findings and a pathology-based diagnosis.

[0140] With respect to FIG. 16E, a method 600 for detecting and reconciling spatial errors within an input can include a step 602 of receiving an input from the user, wherein the input includes a marker on an anatomic representation; a step 604 of determining if the marker includes a spatial error; if the marker includes the spatial error, a step of 606 of generating an output based on a rectified input; and if the marker does not include the spatial error, a step of 608 generating an output based on the input. In certain examples, spatial errors are spatial similarities.

[0141] The step 602 can include the user sending the input to the system 100 via the input device 108. The input can be saved on the medium 104. Non- limiting examples of the input can include videos of anatomic representations / diagrams / maps, images of anatomic representations / diagrams / maps, or combinations thereof. The marker can be at least one particular location marked on the anatomic representation by the user. For example, the marker may be a position selected by the user on an anatomic representation presented by the GUI 1 12 on the display 106. In other examples, the marker is indicia on a physical document having the anatomic representation that was subsequently digitized.

[0142] The step 604 can include comparing the marker with the visual library in the data processing module 1 14. This can be accomplished using artificial intelligence, machine learning models, computer vision models, or other similar means. The visual library can include medical documentation, such as anatomic representations with predefined anatomic sites correlated with anatomic information, e.g., site descriptions having custom coordinates, paths, path segments, groups, planes, and / or axes, or combinations thereof. If the input substantially matches one of the anatomic representations, the marker can be identified based on the matched predefined anatomic sites.

[0143] In certain examples, the step 604 comprises training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm. The training data can include the visual library of the data processing module 114. The identification machine learning model can receive the input and output a corrected marker within the input based on coordinate similarity, spatial similarity, deviations, proximities, and calculative similarity based on matches within the visual library of the data processing module 114. Non-limiting examples for the machine learning algorithms includes span categorization-based algorithms, range categorization-based algorithms, or other similar algorithms, or combinations thereof.

[0144] If the marker includes a spatial error, an output is generated in step 606 based on the rectified input, the correct position matched from the visual library. If the marker does not include a spatial error, an output is generated in step 608 based on the original input. Non-limiting examples of the output includes medical information processed from the input; a description of the input based on the medical information; and visualizations based on the medical information, e.g., line art of anatomic regions, including descriptions of anatomic sites, other medical information, or combinations thereof. In certain examples, the step 608 includes presenting the output on the GUI 112 on the display 106. In certain examples, the output is a digital file or a printed physical document. In certain examples, the output is sent to the output device 110 or used as a training data for identification machine learning model. The output can be saved on the medium 104.

[0145] In certain embodiments, the system 100 can be configured to detect and reconcile spatial errors within a received input. For example, the input device 108 can be configured to send the input from the user, wherein the input includes a marker on the anatomic representation. The data processing module 114 can be configured to determine if the marker includes a spatial error. If the marker includes a spatial error, the generation module 116 can be configured to generate the output based on the corrected marker. If the marker does not include a spatial error, the generation module 1 16 can generate the output based on the original input.

[0146] With respect to FIG. 160, a method 1600 for generating outputs based on non-semantic similarity comprises a step 1602 of receiving an input, wherein the input is a coded, language-based, symbol-based or mixed description (herein uncoordinated component of input) to identify at least one path, path segment, or path group (herein paths) and at least one standardized diagram in a library of standardized diagrams and paths; a step 1604 of calculating coordinate similarity, positional similarity, or spatial similarity (herein non-semantic similarity) between the input and other paths in the library, wherein coordinates can define areas or points; a step 1606 of optionally, calculating non-semantic similarity on new visualizations by overlaying or underlaying and aligning other paths in the library with the anatomic features present in the visualizations; and a step 1608 of generating maps, avatars, semantic descriptions, semantic relationships, calculated descriptions, calculated relationships, illustrations, visualizations, or combinations thereof based on non-semantic similarity as outputs. Outputs may have custom coordinates, axes, borders, paths, groups, and other properties based on the calculations. Generated outputs can also be describable and relatable in a desired coded, linguistic, symbolic, or mixed language. Inputs may also optionally include coordinates and instructions specific to the paths.

[0147] FIG. 9 shows a first example anatomic representation 610 having a first marker 612 (markers are also known as pins) and a second example anatomic representation 614 having a second marker 616. The first marker 612 and the second marker 616 are shown in multiple dimensions in FIG. 9 with high coordinate and spatial similarity, but high semantic dissimilarity. The system 100 can reconcile and compare these and apply these to other images and visualizations. In practice, a fraction of a pixel can mean a difference in clinical staging, billing code selection, risk assessment, and more. In certain embodiments, a plurality of maps, avatars, and defined site descriptions stored on the medium 104 having custom coordinates, paths, path segments, groups, planes, and / or axes is used to compare language and spatial relationships. In other embodiments, the exact path and point relationship to the path is determined in a code string, and that information is used to reproduce the path and visualization on itself (the same source visualization) as well as on other images, videos, or multimedia, as well as other paths with coordinate, spatial, and / or positional similarity. In certain embodiments, the methods and systems described herein is used instead of overlaying or underlaying maps on multimedia. In other words, in certain embodiments, the path and diagram defined in the code string serve as a reference path and diagram for other paths and diagrams to generate new multidimensional maps and relationships. This enables coordinate similarity, spatial similarity, and positional similarity to be accounted for regardless of semantic similarity / dissimilarity and / or code similarity / dissimilarity. In certain embodiments, multiple pins, paths, path segments, or path groups can be shared rather than just one at a time, and when multiple are shared, they may be part of different list groups, diagnosis groups, or other groupings. In certain embodiments, a shared QR code or a URL can open up at least one standardized image, with an optionally highlighted and optionally sub-segmented path (or path group or path segment) correlating with the translated description for the site and more. Coordinate similarity, spatial similarity, and / or positional similarity are used to generate and / or describe and / or calculate relationships with other anatomic sites and new multidimensional maps by combining spatially related areas despite their semantic descriptions. This can allow for multidimensional map and target generation on new images and multimedia as well, by using the custom coordinates and relationships established in the system 100 for one reference site and pulling a plurality of other reference sites in to generate new maps. Machine learning and artificial intelligence can assist with this process of multidimensional map building, by generating new map data from alignment of at least one reference site stored in a library on the medium 104 as one non-limiting example.

[0148] In certain embodiments, retrieving a standardized visualization from the library stored on the medium 104 with defined or custom coordinates, axes, planes, segments, and path relationships can solve labeling and language interpretation problems that have semantic dissimilarity but coordinate similarity, positional similarity, spatial similarity, or combinations thereof. This can be 2 dimensional, 3 dimensional, 4 dimensional (over time), or multidimensional. In one non-limiting embodiment, a lesion is on the border of multiple neighboring paths, path segments, path groups, and language-based descriptions. Slight differences in the pin placement, such as from mistyping misclicking, or mistouching when a touchscreen is used as the input device 108 as one nonlimiting example, generates descriptions with little semantic similarity, but similar coordinate and spatial similarity. The system 100 can reconcile semantic dissimilarity, code dissimilarity, and descriptive dissimilarity by using coordinate similarity, spatial similarity, deviations, proximities, and calculative similarity through interpretation with standardized anatomic maps in certain embodiments. A non-limiting practical application example of relying on high non-semantic similarity would be in medical record summarization or collation when an anatomic area of interest may be summarized with completely different descriptions for anatomic sites in different records.

[0149] As shown in FIG. 16F, a method 700 for improving reproduction and generation of anatomic site visualizations, description, maps, and relationships, comprises a step 702 of receiving, from the input device 108, at least one coordinate-based path, path segment, or path group linked to at least one anatomic representation identified with the input, and the input serving as a reference to map-diagram pairs; a step 704 of rendering, using the processor 102, at least the reference map-diagram pair or pairs on the display 106; a step 706 of selectively rendering, using the processor 102, additional data in the input related to the map-diagram pair or pairs; and a step 708 of selectively generating, using the generation module 116, new maps, images, avatars, relationships, and descriptions based on coordinate similarity, positional similarity, spatialsimilarity, or combinations thereof regardless of semantic similarity.

[0150] As shown in FIG. 16G, a method 800 for generating a description of a plurality of markers on an anatomic representation comprises a step 802 of receiving an input from a user, wherein the input includes the plurality of markers on the anatomic representation; a step 804 of determining the relationship between each of the plurality of markers; and a step 806 of generating a description of the input, wherein the description of the input includes a description of the relationship between each of the plurality of markers or a visualization of the plurality of the markers with the description of the relationship. In certain examples, the relationship between each of the plurality of markers includes a spatial relationship, a coordinate-based relationship, positional relationship, data-based relationship, or combinations thereof. In certain embodiments, the description of the relationship is in language that is human readable, machine readable, or combinations thereof.

[0151] The step 802 can include receiving the input from the user via the input device 108. The input can be saved on the medium 104. Non-limiting examples of the input can include videos of anatomic representations / diagrams / maps, images of anatomic representations / diagrams / maps, or combinations thereof. The plurality of markers can include at least two particular locations marked on the anatomic representation by the user. For example, the marker may be positions selected by the user on the anatomic representation presented by the GUI 112 on the display 106. In other examples, the markers are indicia on a physical document having the anatomic representation that was subsequently digitized.

[0152] The step 804 can include comparing the plurality of markers with the visual library in the data processing module 114. This can be accomplished using artificial intelligence, machine learning models, or other similar means. The visual library can include medical documentation, such as anatomic representations with predefined anatomic sites correlated with anatomic information, e.g., site descriptions having custom coordinates, paths, path segments, groups, planes, and / or axes, or combinations thereof. If the input substantially matches one of the anatomic representations, the plurality of markers can be identified based on the matched predefined anatomic sites.

[0153] In certain examples, the step 804 includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm. The training data can include the visual library of the data processing module 114. The visual library can have medical documentation, such as anatomic representations with predefined anatomic sites correlated with anatomic information, e.g., site descriptions having custom coordinates, paths, path segments, groups, planes, and / or axes, or combinations thereof. The identification machine learning model can receive the input and output the relationship between each of the plurality ofmarkers within the input based on coordinate similarity, spatial similarity, deviations, proximities, calculative similarity, or combinations thereof based on the matched information from the visual library. Non-limiting examples for the machine learning algorithms includes span categorizationbased algorithms, range categorization-based algorithms, or other similar algorithms, or combinations thereof.

[0154] The step 806 can include generating the description of relationship between each of the plurality of markers or generating a visualization of the plurality of markers with description of the relationship between each of the plurality of markers. In certain examples, the relationship between each of the plurality of markers also includes the relationship between the each of the plurality of markers with nearby landmarks within the input. In certain examples, the relationship between the each of the plurality of markers includes natural language for added accuracy, precision, or human comprehensibility. For example, if one of the markers is in close proximity and under a second one of the markers, the relationship can include the one of the markers is just under the second one of the markers. In certain examples, the step 806 includes presenting the description of relationship between each of the plurality of markers or generating a visualization of the plurality of markers with description of the relationship between each of the plurality of markers on the GUI 112 on the display 106. In certain examples, the description of relationship between each of the plurality of markers or the visualization of the plurality of markers with description of the relationship between each of the plurality of markers is included in a digital file or a printed physical document. In certain examples, the description of relationship between each of the plurality of markers or the visualization of the plurality of markers with description of the relationship between each of the plurality of markers is sent to the output device 110 or used as a training data for identification machine learning model. In certain examples, the description of relationship between each of the plurality of markers or the visualization of the plurality of markers with description of the relationship between each of the plurality of markers is saved on the medium 104.

[0155] In certain embodiments, the system 100 can be configured for generating the description of the plurality of markers on the anatomic representation. For example, the input device 108 can be configured to send the input from the user, wherein the input includes the plurality of markers on the anatomic representation. The data processing module 114 can be configured to determine the relationship between each of the plurality of markers. The generation module 116 can generate the description of the input. The description of the input includes the description of the relationship between each of the plurality of markers or a visualization of the plurality of markers with the description of the relationship between each of the plurality of markers.

[0156] With the use of language, vision, code, or symbols in a coordinated language model, thesystem 100 is able to determine relationships between two or more anatomic sites or pins. In certain embodiments, language descriptions are generated or analyzed to describe such relationships with greater accuracy and precision than is possible with current models. For example, as shown in FIG. 10, an example anatomic representation 808 shows the relationship between different defined paths, as defined in the data processing module 114, is used to determine the target position of a first example marker 810 and a second example marker 812. For example, the first example marker 810 generated description would be the “Left Anterior Lower alveolar ridge mucosa just under the Lower Left Canine”; and second example marker 812 generated description “Left Anterior Lower alveolar ridge mucosa just under the Lower Left 1st Bicuspid.” The system 100 can also describe the relationships between the paths in generated natural language, such as “1 is anterior and medial from 2” as one non-limiting example.

[0157] The system 100 can also uses the paths to determine context; or the reverse wherein context is used to determine the paths. For example, the teeth of this non-limiting example are that of an adult; so differently spaced targets and / or different descriptions would be used. As one skilled in the art would know, countless examples would exist for these relationships due to synonyms, language sequences, and context. Continuing this non-limiting example with synonyms and different sequences, “Anterior Lower left alveolar ridge mucosa just below the universal tooth #22” would mean the same thing as the former example description for pin 1. The language combined with the coordinate-based relationships between two or more paths can determine a precise and accurate description. This is an improvement on systems that rely on intrinsic axial definitions and direction planes, as it relies on actual physical relationships between defined anatomic sites and between pins. In certain embodiments, the models stored on the medium 104 and processed with the data processing module 114 are enabled by the system 100 to describe and / or relate two or more sites using nearby different paths / extrinsic paths rather than custom axes and / or direction planes related to self / intrinsic paths. As in other embodiments, paths can mean named site with or without custom axes, path groups, path segments, shapes, coordinate groups, ranges, coordinates, or other physically defined spaces. As one skilled in the art would know, these concepts can be used to describe other physical objects and relationships outside of the anatomical context.

[0158] In certain embodiments, span categorization is used to generate visualization of textbased descriptions of anatomy and anatomy relationships. In certain embodiments, text that describes anatomic site, laterality, prefixes, suffixes, central zones, other modifiers, or combinations thereof are captured in a span categorization model and coordinated to a selection in the visual library. In certain embodiments, anatomic sites can have language that includes modifiers, like the “Central forehead” includes language component “Central” that can also becategorized as a modifier. In certain embodiments, category preference is given to anatomic site, greater than laterality, greater than other modifiers in a span categorization model. In certain embodiments there can be multiple modifiers of the same type (e.g. lateralities, prefixes, suffixes, enhanced directional modifiers, central zone descriptors, modifier synonyms, magnitude modifiers, axial modifiers) and the modifier order within the string, or the modifier order within the type, can matter in selecting, targeting, generating, or combinations thereof a visualization and / or coordinates. In other certain embodiments, the order, type, or combination thereof of the modifiers does not affect the ability to select, target, generate, or combinations thereof a visualization and / or coordinates. As one non-limiting example, the anatomic site terms are shown in “quotes” in this brief list; and the modifiers are shown outside of quotes: Right (Superior) Anterior Lateral “Proximal lower leg” ; Right (Anterior) Lateral “Proximal lower leg”; Right (Proximal) Lateral “Anterior surface of lower leg” ; Right (Proximal Anterior) Lateral “Lower leg” ; Right (Proximal Anterior) Lateral Lower leg; Lateral (Proximal Anterior) Lower Right “Leg.” The order of the modifiers does not matter, and inclusion of a modifier in a defined anatomic site name (e.g. “Proximal lower leg” contains two terms that are also modifiers: “Proximal” and “Lower”) also does not matter in this example, as each of these language based descriptions coordinate to the same region (e.g. dynamic anatomic address; e.g. with span categorization). In certain embodiments, an axis or direction can be described in semantically dissimilar terms. As one nonlimiting example, FIG. 10 illustrates targeted shading of the “Left (Posterior) Side wall of ala nasi” but it is still considered correct to describe the targeted shading as the “Left (Lateral) Side wall of ala nasi” where the “Lateral” modifier is semantically dissimilar from the “Posterior” modifier. In certain embodiments, paths, path groups, or direction planes may have more than one custom axial definition. In certain embodiments, span categorization can enable coordination of semantically dissimilar modifiers to a similar target, visualization, description, or combination thereof. In certain embodiments, an anatomic site description with modifiers can be visualized, targeted, selected or combinations thereof in an alternate angle, rotation, reflection, or combination thereof such as in a mirrored view. In certain embodiments, language, code, symbols, or combinations thereof is progressively or regressively segmented, categorized, or combinations thereof to generate or select a target, map location, avatar location, object location, visualization, coordinates, paths, or combinations thereof. In certain embodiments, the aforementioned correlates with language- to- visualization or language-to-target capabilities of the system 100. In certain embodiments, when two or more sites are described in a span that includes language, text, code, symbols, or a combination of inputs, the relationship between the described sites can be visualized in a generated visualization by the generation module 116. In certain embodiments, when two or more sites are selected or otherwise targeted as inputs on an anatomy visualization, the system 100generates, via the generation module 1 16, coordinated, reproducible, coded, translated, and related descriptions.

[0159] Using Range categorization and filtering capabilities of the system 100, certain features of areas of interest may be ascertained as well - not just anatomic site names and codes. As one non-limiting example, if an imaging set from a study has a large dataset of closeup skin images using confocal microscopy or spectral imaging or dermoscopy, and researchers need to filter out the images on “bony prominences” like the extensor surfaces of the elbow and knee, where the skin is more stretched, the system 100 can accomplish this task automatically through relationships with language, coordinates, paths, and imaging.

[0160] With reference to FIG. 16H, a method 900 for generating a visualization of a global period of a procedure or a diagnosis comprises a step 902 of receiving an input from the user, wherein the input includes a record of a patient having the procedure or the diagnosis related to the patient; a step 904 of determining one or more anatomic sites associated with the procedure or the diagnosis; a step 906 of determining the global period of the procedure or diagnosis; a step 908 of generating the visualization of the global period of the procedure or diagnosis.

[0161] The step 902 can include receiving the input from the user via the input device 108. Non-limiting examples of the input can include a medical record of the patient, having a history of one or more procedures or diagnoses. The input can be saved on the medium 104.

[0162] The step 904 can include comparing the procedure or the diagnosis to a library of procedures and diagnoses in the data processing module 114. The library of procedures and diagnoses can include a list of procedures and diagnosis. Each of the procedures and diagnosis are associated with the anatomic sites affected by said procedure or diagnosis with the relevant global period. The global period is the period of time in which services are bundled with a specific procedure or diagnosis on anatomic site(s) and additional billing cannot occur unless it is unrelated to the specific procedure or diagnosis. The global period can be established by relevant healthcare authorities such as the AMA or defined by Medicare. If the procedure or diagnosis in the input matches one of the procedures or the diagnoses in the library of procedures and diagnoses, the anatomic sites affected by the procedure or diagnosis are determined based on the anatomic sites associated with the matched procedure or the diagnosis in the library of procedures and diagnoses.

[0163] The step 904 can include training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm. The training data can include the library of procedures and diagnoses in the data processing module 114. The identification machine learning model can receive the input and output which anatomic sites are affected by the procedure or diagnosis based on the anatomic sites associated with the matched procedure or the diagnosis in the library of procedures and diagnoses. Non-limiting examples forthe machine learning algorithms includes span categorization-based algorithms, range categorization-based algorithms, or other similar algorithms, or combinations thereof.

[0164] The step 906 can include comparing the procedure or the diagnosis to the library of procedures and diagnoses in the data processing module 114. If the procedure or diagnosis matches one of the procedures or the diagnoses in the library of procedures and diagnoses, the global period for the procedure or diagnosis is determined based on the global period associated with the matched procedure or the diagnosis in the library of procedures and diagnoses.

[0165] The step 906 can include training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm. The training data can include the library of procedures and diagnoses in the data processing module 114. The identification machine learning model can receive the input and output the global period of the procedure or diagnosis based on the global period associated with the matched procedure or the diagnosis in the library of procedures and diagnoses. Non-limiting examples for the machine learning algorithms includes span categorization-based algorithms, range categorization-based algorithms, or other similar algorithms, or combinations thereof. The anatomic sites can be categorized in structured data ranges and / or relationships within the library of procedures and diagnoses.

[0166] The step of 908 can include generating the visualization which includes an anatomic representation having the anatomic sites affected by the procedure or diagnosis with indicia in each anatomic site showing whether the site is in the global period. The indicia can include text, color codes, map points, or other visualizable means to show whether the anatomic site is in the global period along with the procedure. In certain examples, the step 908 includes presenting the visualization on the GUI 112 on the display 106. In certain examples, the visualization is included in a digital file or a printed physical document. In certain examples, the visualization is sent to the output device 110 or used as a training data for identification machine learning model. The visualization can be saved on the medium 104. In certain examples, the visualization of the global period is shown on an anatomic map, avatar, or image. In certain examples, the global period is an amount of time associated with a procedure, diagnosis, or combinations thereof, and each procedure or diagnosis is associated with a separate anatomic location. In certain embodiments, each procedure or diagnosis is displayed simultaneously on an anatomic representation.

[0167] In certain embodiments, the one or more anatomic sites is defined in a numerical range, alphabetical range, hierarchical relationship, an another range, or combinations thereof, to define range categories including structured data ranges, data relationships, or combinations thereof. In certain embodiments, a single anatomic site can belong to multiple ranges.

[0168] In certain embodiments, the system 100 can be configured for generating a visualizationof a global period of a procedure or a diagnosis. For example, the input device 108 can be configured to send the input from the user. The input includes a record of patient, wherein the record of the patient includes the procedure or the diagnosis related to the patient. The data processing module 114 can be configured to determine the one or more anatomic sites associated with the procedure or the diagnosis; and determine the global period of the procedure or diagnosis. The generation module 1 16 can be configured to generate the visualization of the global period of the procedure or diagnosis.

[0169] By coordinating procedures to anatomic sites and calculating remaining global periods and showing those on visualizations, the system 100 can visually show the user which procedures / diagnoses are still under a global period and which are not. This has implications in the billing process and helps to determine which wound checks and suture removal are billable and which are not, as a practical implementation. In certain embodiments, attributes associated with anatomic site and other information, e.g., a surgical procedure that has its own attributes, e.g., a time period such as a “global period’- defined on the medium 104, can be used to calculate and coordinate information onto a visualization. A practical application is visually plotting “global periods” onto anatomic visualizations. In certain embodiments, global periods are defined in the medium 104 in association with procedures and are a period of time in which services are bundled with a specific procedure on a specific anatomic site and additional billing cannot occur unless it is unrelated to that procedure. Calculation of the remaining global period (e.g., by the data processing module 114) along with a visual representation on a diagram or map can clearly show the user on the GUI 112 what can or cannot be billed for with a generated or plotted visualization.

[0170] With respect to FIG. 161, a method 1000 for determining a billing code for a procedure or diagnosis can comprise a step 1002 of receiving an input from the user, wherein the input includes a procedure or the diagnosis related to the patient; a step 1004 of determining the one or more anatomic sites associated with the procedure or the diagnosis; a step 1006 of determining the billing code based on the procedure or diagnosis and the one or more anatomic sites associated with the procedure or the diagnosis; and a step 1008 of generating an output having the billing code for the procedure or diagnosis.

[0171] The step 1002 can include the user sending the input via the input device 108. The input can be saved on the medium 104. Non-limiting examples of the input can include a medical record of the patient, having a history of one or more procedures or diagnoses. In certain examples, the step 1002 can include selectively receiving updates from the user based on the initial procedure or diagnosis. For example, if the initial procedure relates to basal cell carcinoma on the right medial cheek, and later the physician discovers the tumor actually extends onto and predominantly affects the nose, the physician can send an update via the input device 108 to account for the newprocedure or diagnosis.

[0172] The 1004 can include comparing the procedure or the diagnosis to a library of procedures and diagnoses in the data processing module 114. If the procedure or diagnosis in the input matches one of the procedures or the diagnoses in the library of procedures and diagnoses, the anatomic sites affected by the procedure or diagnosis are determined based on the anatomic sites associated with the matched procedure or the diagnosis in the library of procedures and diagnoses. In certain examples, the step 1004 can include updating the one or more anatomic sites associated with the procedure or diagnosis based on the update received from the user.

[0173] The step 1004 can include training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm. The training data can include the library of procedures and diagnoses in the data processing module 114. The identification machine learning model can receive the input and output which anatomic sites are affected by the procedure or diagnoses based on the anatomic sites associated with the matched procedure or the diagnosis in the library of procedures and diagnoses. Non-limiting examples for the machine learning algorithms includes span categorization-based algorithms, range categorization-based algorithms, or other similar algorithms, or combinations thereof. The anatomic sites can be categorized in structured data ranges and / or relationships within the library of procedures and diagnoses.

[0174] In certain embodiments, where a procedure or diagnosis overlaps two or more anatomic sites or regions, defined by visual relationships, data-based relationships, or combinations thereof, the most appropriate billing code is selected and verified based on a plurality of factors such as surface area, location of primary diagnosis, reimbursement amount, or combinations thereof.

[0175] The step 1006 can include comparing the anatomic sites affected by the procedure or diagnosis to a library of billing codes in the data processing module 114. The library of billing codes can include standard billing codes, e.g., CPT codes copyrighted to AMA or other similar codes. Each of the billing codes relates to a particular procedure or diagnosis at particular anatomic sites. If the procedure or diagnosis in the input and the anatomic sites affected by the procedure or diagnosis match or substantially match one of the billing codes, the billing code is determined based on the billing code matched with the procedure or diagnosis in the input and the anatomic sites affected by the procedure or diagnosis. In certain examples, the step 1006 can include updating the billing code based on the update received from the user. In certain embodiments, the system can determine where the tumor predominantly affects and can suggest an alternate billing code based on the anatomic site or anatomic site range (e.g., through range categorization).

[0176] The step 1006 includes training, iteratively and / or recursively, an identification machinelearning model using training data and a machine learning algorithm. The training data can include the library of procedures and diagnoses and the library of billing codes in the data processing module 114. The identification machine learning model can receive the procedure or diagnosis in the input and the anatomic sites affected by the procedure or diagnosis based on the billing code matched with the procedure or diagnosis in the input and the anatomic sites affected by the procedure or diagnosis. Non-limiting examples for the machine learning algorithms includes span categorization-based algorithms, range categorization-based algorithms, or other similar algorithms, or combinations thereof.

[0177] The step 1008 can include displaying the billing code on the GUI 112 on the display 106. In certain examples, the step 1008 can include generating a digital file or a printed physical document having the billing code. In certain examples, the step 1008 can include generating a justification for selecting the higher or lower reimbursing code in natural language based on the billing code matched with the procedure or diagnosis in the input and the anatomic sites affected by the procedure or diagnosis.

[0178] In certain embodiments, the system 100 can be configured to determine a billing code based on a procedure or diagnosis. For example, the input device 108 can be configured to send the input from the user. The input includes the procedure or the diagnosis related to the patient. The data processing module 114 can be configured to determine the one or more anatomic sites associated with the procedure or the diagnosis; and determine the billing code based on the procedure or diagnosis and the one or more anatomic sites associated with the procedure or the diagnosis. The generation module 116 can be configured to generate the output having the billing code.

[0179] With respect to FIG. 16J, a method 1100 for verifying a billing code for a procedure or diagnosis comprises a step 1102 of receiving an input from a user, wherein the input includes a billing code and the one or more anatomic sites affected by the procedure or the diagnosis; a step 1104 of determining the one or more anatomic sites covered by the billing code; a step 1106 of determining whether the one or more anatomic sites covered by the billing code matches the one or more anatomic sites affected by the procedure or the diagnosis; if the one or more anatomic sites covered by the billing code does not match the one or more anatomic sites affected by the procedure or the diagnosis, a step 1108 of determining the correct billing code for the one or more anatomic sites affected by the procedure or the diagnosis to generate a verified billing code; and a step 1110 of generating an output, wherein the output includes the verified billing code.

[0180] The step 1102 can include the user sending the input via the input device 108. The input can be saved on the medium 104. Non-limiting examples of the input can include a billing code for a procedure or diagnosis and the medical record of the patient that includes a history of the oneor more anatomic sites associated with the procedure or the diagnosis.

[0181] The step 1104 can include comparing the hilling code with the library of hilling codes in the data processing module 114. If the billing code matches or substantially matches of the billing codes in the data processing module 114, the one or more anatomic sites covered by the billing code can be determined based on particular anatomic sites associated with the matched billing code.

[0182] The step 1104 can include training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm. The training data can include the library of billing codes in the data processing module 114. The identification machine learning model can receive the input and output the anatomic sites covered by the billing code can be determined based on particular anatomic sites associated with the matched billing code from the library of billing codes. Non-limiting examples for the machine learning algorithms includes span categorization-based algorithms, range categorization-based algorithms, or other similar algorithms, or combinations thereof. The anatomic sites can be categorized in structured data ranges and / or relationships within the library of procedures and diagnoses.

[0183] The step 1106 can include comparing the one or more anatomic sites covered by the billing code with the one or more anatomic sites affected by the procedure or the diagnosis. If the one or more anatomic sites covered by the billing code matches or substantially matches the one or more anatomic sites affected by the procedure or the diagnosis, the billing code can be verified as being correct.

[0184] If the one or more anatomic sites covered by the billing code does not match or substantially match the one or more anatomic sites affected by the procedure or the diagnosis, the process proceeds to step 1108. This can include comparing the anatomic sites affected by the procedure or diagnosis to the library of billing codes in the data processing module 1 14. If the procedure or diagnosis and the anatomic sites affected by the procedure or diagnosis match or substantially match one of the billing codes, the billing code is determined based on the billing code matched with the procedure or diagnosis in the input and the anatomic sites affected by the procedure or diagnosis.

[0185] The step 1108 includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm. The training data can include the library of procedures and diagnoses and the library of billing codes in the data processing module 114. The identification machine learning model can receive the procedure or diagnosis and the anatomic sites affected by the procedure or diagnosis and output the corrected billing code based on the billing code matched with the procedure or diagnosis in the input and the anatomic sites affected by the procedure or diagnosis. Non-limiting examples for the machinelearning algorithms includes span categorization-based algorithms, range categorization-based algorithms, or other similar algorithms, or combinations thereof.

[0186] In certain embodiments, where a procedure or diagnosis overlaps two or more anatomic sites or regions, defined by visual relationships, data-based relationships, or combinations thereof, the most appropriate billing code is selected and verified based on a plurality of factors such as surface area, location of primary diagnosis, reimbursement amount, or combinations thereof.

[0187] The step 1110 can include displaying the verified billing code billing code on the GUI 112 on the display 106. In certain examples, the step of generating an output, wherein the output includes a verified billing code can include generating a digital file or a printed physical document having the verified billing code. The verified billing code can be the original billing code that was verified as being correct or the corrected billing code when the original billing code was found to be incorrect. The verified billing code can be saved on the medium 104.

[0188] In certain embodiments, the system 100 can be configured to verify the billing code for the procedure or diagnosis. For example, the input device 108 can be configured to send the input from the user. The data processing module 114 can be configured to determine the one or more anatomic sites covered by the billing code; determine whether the one or more anatomic sites covered by the billing code matches the one or more anatomic sites affected by the procedure or diagnosis; and if the one or more anatomic sites covered by the billing code does not match the one or more anatomic sites affected by the procedure or the diagnosis, determine the correct billing code for the one or more anatomic sites affected by the procedure or the diagnosis. The generation module 116 can be configured to generate the output having the verified billing code.

[0189] Enhanced billing code accuracy and precision is enabled by the system 100, wherein a procedure or billable healthcare service linked to anatomy is located in two distinct defined anatomic regions or zones. A practical application of this technology is where a procedure such as a skin cancer removal through Mohs surgery for a basal cell carcinoma on the Right (Inferior) Paranasal region (which is also describable by the system 100 as the Right (Medial) cheek since this term belongs to the cheek in certain embodiments, as one non- limiting example. The multi- step Mohs procedure reveals that the tumor actually extends onto and predominantly affects the nose, but this is not known until further during the procedure because the extent of the tumor was not grossly visible.

[0190] After evaluation of the final wound, and an image of the final wound from the Mohs surgery, a flap closure originating from the nasal bridge is decidedly the best surgical repair to manage and close the final wound defect, in this non-limiting example. In this continued nonlimiting example, the basal cell carcinoma is already linked to the Right Medial Paranasal area, which is part of the cheek in this embodiment. Linking and selecting a billing code, such as a CPTcode for a flap I adjacent tissue transfer on the cheek, to the cheek can result in lower reimbursement in certain embodiments when compared to linking and selecting a billing code for a flap / adjacent tissue transfer on the nose. The nose selection may actually more appropriate in certain embodiments because the surgical defect in this non- limiting example, and the tissue being moved in this non-limiting example, is predominantly on the nose.

[0191] In certain embodiments, in addition to linking to or selecting standardized billing codes, the generated and selectively enhanced anatomy codes and other codes can be appended or otherwise linked to the billing code. The system 100 can combine multiple codesets with one nonlimiting example being 14040_125-L which generates combined coding to link the concepts of CPT code 14040 as shown in Table 1 with an anatomic site code 125-L for the “Left Chin.” In certain other embodiments, concepts from more than 1 knowledge base are combined to generate and store unique, more accurate, specific, and reproducible codes containing variables like anatomic site, anatomic range, anatomic visualization, anatomic coordinates, anatomic category, size, count, measurement, diagnosis category (e.g. benign vs. malignant, inflammatory rash vs. lesion, fracture vs. sprain, etc.), cross-map data, primary diagnosis, additional diagnoses, duration, historical information, and other variables as non-limiting examples. In certain examples, the combined codes are enabled by the generation module 116 and / or the data processing module 114, and stored in and / or selected from the physical medium 104. In certain embodiments, the input device 108 is a LIDAR scanner or other image capture technology, and the data processing module 114 calculates measurements, counts or other quantitative metrics, or combinations thereof of an area of interest based on the received input to generate calculated data, and combines the calculated data with anatomic site information (e.g. from range categorization, site selection, site generation, site target, or combinations thereof), diagnosis information, or other information, or combinations thereof available in the system 100 to generate, e.g. via the generation module 116, to select, or to modify, or combinations thereof the correct billing code.

[0192] Through billing code optimization, the system 100 can analyze the anatomic locations and the fact that the removal and the repair are distinct, separate, and identifiable procedures, and appropriately suggest the higher reimbursing code, and write a justification for selecting the higher reimbursing code in natural language.

[0193] The reverse is also true in this non-limiting example and has practical application in being of interest to insurers who reimburse for procedures in certain embodiments. If a surgery was billed on the nose, but predominantly extended onto the cheek, the system 100 can alert the insurer of this discrepancy and possible overpayment. Non-limiting example of CPT codes copyrighted to the AMA.Table 1

[0194] In certain embodiments, the system 100 will automatically select the correct procedure code not only based on the calculated (e.g., by the data processing module 114) or input measurement (e.g., by the input device 108), but also on the reported anatomic site. Taking this example further, the system 100 can analyze spatial data related to the procedure like anatomic sites, ratio of involved surface areas when they are in different code categories like the examples in the above table.

[0195] Other embodiments include multidimensional data that is differentially determined based at least 3 characteristics of detections, with characteristics including but not limited to these examples: x-axis position relative to paper or digital form or image; x-axis position relative to diagram or entry box or field; containment within entry box or field; y-axis position relative to paper or digital form or image; y-axis position relative to diagram or entry box or field; color of detection; intensity of detection; characters of detection; dictionary matches of detection; context of detection (e.g. user context; label context); shape of detection; area or other measurement of detection; calculation of detection.

[0196] For example, a point, a dot, a shape, a character, a label, a shading, or other markup or annotation can have different meanings based on its position on a map, avatar, image, form, or template and based on other features that add dimensionality to the data. Other non-limiting examples of other features can mean color, user context, color differentials (e.g. gray standard pencil markings versus black ink pen), label context (e.g. is it in a medical context, inpatient context, outpatient context, etc.), user context (is the user a patient, a healthcare practitioner, a computer, etc.), label order, label meaning, user intention, etc.

[0197] In one non-limiting embodiment, a label marked as “psoriasis” on a paper map along with shading on anatomic diagrams in the same color, the system 100 would apply multidimensional anatomic distribution descriptions, apply diagnosis codes, calculate body surface area, calculate intensity / severity, recommend prescriptions, pull up past prescriptions for the disease, generate warnings based on allergies and other risk factors (e.g. patient drinks alcohol,patient is of child-bearing age), etc. Changing the label in this example to “soriasis” the system 100 could automatically present the multidimensional information in Spanish. Before changing language, the system 100 could perform cross-checks such as user country or user preferences.

[0198] In another similar non-limiting embodiment, the user could label a patient image as “psoriasis” and the system 100 would determine and describe the areas of involvement, surface area, morphological characteristics, and features, and generate follow-up questions. In certain embodiments, such as paper embodiments, markup type and color differentials can also be used to delineate items that are meant for manual entry and confirmation versus automatic entry, to add checks and balances to the system 100. For example, in some embodiments pencil input may be meant for notes that are not automatically input; and pen input may be meant for automatic input.

[0199] Further clarifying non-limiting embodiments include progressive and regressive component and concept grouping to describe anatomic distributions, diagnoses, other health data, and their components. In some embodiments, both antecubital fossas and popliteal fossas in the context of the skin can be associated with a “flexural distribution” and contextually or automatically linked to diseases likely to affect these sites, such as atopic dermatitis as a nonlimiting example. Continuing this example, the antecubital fossas can be regressively broken down into the right antecubital fossa and left antecubital fossa. This linkage occurs in the system 100 through the coordinated language model.

[0200] Another non-limiting example includes the anatomic sites that contain apocrine glands, such as the armpits, under breasts, and groin areas, which are commonly linked to a diagnosis of hidradenitis suppurativa. However, the face, scalp, and perineum also have apocrine glands and may be linked to other diagnoses. The system 100 can process (e.g., through the data processing module 114) findings for these features.

[0201] Yet another non-limiting example includes the genetic profile for different anatomic sites. For example, skin on the palms and soles contain genetically different keratin profiles than skin on the arms and legs. In this example, K9 type keratin (Keratin 9 is typically on the palmoplantar skin, which creates a thicker keratin layer as seen on the palms and soles) is expressed in the palmoplantar skin (and is known as a fact in the data processing module 1 14). And, if only the palmoplantar skin is affected by a diagnosis, the system 100 can determine that a genetic defect or an antibody affecting a specific keratin, such as keratin K9 in this non-limiting example, is a key to the diagnosis and appropriate testing to order, such as to diagnose a condition like epidermolytic palmoplantar keratoderma as one non-limiting example.

[0202] The system 100 is capable of dissecting and combining (e.g., through the data processing module 114) linguistic, semantic, spatial, coded, directional, relational, and / or contextual concepts simultaneously to generate (e.g., through the generation module 116) recommendations,visualizations, avatars, maps, diagnoses, and other health data.

[0203] Other non-limiting examples of detected, automatically classified, and described data could include AO / OTA Fracture and Dislocation Classification for Long-bone Fractures - determined on X-rays or other imaging; and / or through user interaction with multimedia. Currently, this classification does not differentiate data based on laterality in its encodings; nor does it describe the direction of a fracture which could have clinical relevance or epidemiological relevance. Automatic enhanced descriptions enabled by the system 100 not only add data; but does so without the need for additional cognition.

[0204] With reference to FIG. 16K, a method 1200 for encoding a medical visualization into an encoded string can include a step 1202 of rendering the medical visualization on the display 106, wherein the medical visualization includes an anatomic representation having a plurality of predefined anatomic sites and at least one of the predefined anatomic sites includes a marker; a step 1204 of receiving instructions from a user to encode the medical visualization into the encoded string; a step 1206 of generating an output having the encoded string, wherein the encoded string includes an anatomic site identification portion, a laterality portion, a description of the marker portion, an anatomic representation identification portion, a modifier portion, a prefix portion, a suffix portion, a deviation x-axis portion, a deviation y-axis portion, a deviation z-axis portion, an axial definition portion, an angle portion, an order type portion, an order position portion, a central zone portion, time deviation portion, a synonym portion, or combinations thereof.

[0205] The step of 1202 can include rendering the medical visualization on the GUI 112 on the display 106. The medical visualization can include the anatomic representation having the plurality of predefined anatomic sites. At least one of the predefined anatomic sites includes the marker. In certain examples, the method includes a step 1208 of the user disposing a marker on at least one of the predefined anatomic sites prior to the step of rendering the medical visualization on the display 106. The user can dispose the marker on at least one of the predefined anatomic sites using the GUI 112. In certain examples, the user disposes the marker on a paper form of the anatomic representation, which is subsequently digitized and presented on the display 106. The visual library in the data processing module 114 can include a plurality of anatomic representations, e.g., diagrams of anatomical parts. Each of the anatomic representations is correlated to a particular anatomic representation identification number. In certain embodiments, each of the predefined anatomic sites in each of the anatomic representations is correlated to particular anatomic site identification number.

[0206] The step of 1204 can include the user sending the instructions via the input device 108.The step of 1206 can include presenting the encoded string on the GUI 112 on the display 106. Incertain examples, the output is a physical document or digital file having the encoded string. In certain examples the output is sent to the output device 110. The output can be saved on the medium 104. The anatomic site identification portion of the encoded string correlates to the anatomic site identification number correlated to the anatomic site that the marker is disposed within. The laterality portion correlates to a laterality modifier that describes a position of the anatomic site relative to the anatomic representation, e.g., directions such as left, right, or other similar terms. The description of the marker portion correlates to a laterality modifier that describes a position of the marker relative to the anatomic site that the marker is within. The anatomic representation identification portion correlates to the anatomic representation number correlated to the anatomic representation. The modifier portion can correlate to one or more of a prefix, suffix, central zone descriptor, directional modifiers determined by custom axes, directions, laterality, descriptive modifiers, or combinations thereof. The prefix portion can correlate to prefix modifiers. The suffix portion can correlate to suffix modifiers. The deviation x-axis portion correlates to the position of the marker, namely, the deviation in the x-axis from the center of the anatomic site that the marker is within. The deviation y-axis portion correlates to the position of the marker, namely, the deviation in the y-axis from the center of the anatomic site that the marker is within. The deviation z-axis portion correlates to the position of the marker, namely, the deviation in the z-axis from the center of the anatomic site that the marker is within. The axial definition portion correlates to the name of each axis. The angle portion correlates to the angle of interpretation for each axis, a rotation of a path, plane, custom axis, or combinations thereof. The order type portion correlates to the stylizing of the label of the marker, e.g., Chinese, Arabic, Roman, or other numerals. The order position portion correlates to the order of the marker compared to other markers, e.g., is the marker listed before or after another marker. The central zone portion correlates to a description of the central zone. The time deviation portion correlates to a deviation in time. The synonym portion correlates to any synonyms for the preceding portions or combinations thereof.

[0207] In certain embodiments, the modifier portion correlates to language, text, symbolic, coded, or other description that separately modifies the description of an anatomic site, describes the position within the anatomic site, describes a direction or magnitude of direction related to the anatomic site, or combinations thereof. In certain embodiments, modifiers terms can also include terms like “left” and “right” but be separate from the laterality portion. In one non-limiting example, the term “Median (Left) Central Forehead” has a laterality of “Median”, a modifier of “Left” and a site name defined by the anatomic site identification number that includes a modifier “Central”.

[0208] In certain examples, the encoded string further includes a diagnosis portion. Thediagnosis portion correlates to a particular diagnosis, e.g., Basal Cell Carcinoma. In certain examples, the encoded string further includes a comment portion. The comment portion correlates to comments provided by the user related to the marker and anatomic representation. In certain embodiments, portions can comprise characters that are numerical, alphanumerical, text-based, symbol based, image based, or combinations thereof.

[0209] In certain embodiments, the anatomic site identification portion and the anatomic representation identification number or string portion are required and the other portions (a laterality portion, a description of the marker portion, a modifier portion, a prefix number or string portion, a suffix number or string portion, a deviation x-axis portion, a deviation y-axis portion, a deviation z-axis portion, an axial definition portion, a synonym portion, and angle portion, an order type portion, and an order position portion, or combinations thereof) enable progressive refinement and target selection.

[0210] In certain embodiments, the system 100 can be configured to encode the medical visualization into the encoded string. The display 106 can be configured to display the medical visualization. The input device 108 can be configured to send the instructions from the user to encode the medical visualization into the encoded string. The generation module 116 can be configured to generate the output having the encoded string.

[0211] With respect to FIG. 16L, a method 1300 for decoding an encoded string into a medical visualization can include a step 1302 of receiving an encoded string from a user; a step 1304 of generating an output having the medical visualization based on the encoded string. The encoded string includes an anatomic site identification portion, a laterality portion, a description of the marker portion, an anatomic representation identification portion, a modifier portion, a prefix portion, a suffix portion, a deviation x-axis portion, a deviation y-axis portion, a deviation z-axis portion, an axial definition portion, an angle portion, an order type portion, an order position portion, a central zone portion, time deviation portion, a synonym portion, or combinations thereof.

[0212] The step 1302 can include the user sending the encoded string via the input device 108. The encoded string includes an anatomic site identification portion, a laterality portion, a description of the marker portion, an anatomic representation identification portion, a modifier portion, a prefix portion, a suffix portion, a deviation x-axis portion, a deviation y-axis portion, a deviation z-axis portion, an axial definition portion, an angle portion, an order type portion, an order position portion, a central zone portion, time deviation portion, a synonym portion, or combinations thereof.

[0213] The step 1304 can include determining the anatomic representation based on the anatomic representation identification portion; determining the anatomic site where the marker isdisposed within based on the anatomic site identification portion; determining the laterality modifier that describes the position of the anatomic site relative to the anatomic representation based on the laterality portion; determining the description of the marker based on the description of the marker portion; determining modifiers based on the modifier portion; determining prefixes based on the prefix portion; determining suffixes based on the suffix portion; determining the deviation in the x-axis based on the deviation x-axis portion; determining the deviation in the y- axis based on the deviation y-axis portion; determining the deviation in the y-axis based on deviation z-axis portion; determining the axial definitions based on axial definition portion; determining the angle of interpretation for each axis, a rotation of a path, plane, custom axis, or combinations thereof based on the angle portion; determining the order type based on the order type portion; determining the order type position based on the order type position portion; determining the description of the central zone based on the central zone portion; determining the deviation in time based on the time deviation portion; determining any synonyms based on the synonym portion; or combinations thereof.

[0214] In certain examples, the step 1304 includes presenting the output on the GUI 112 on the display 106. In certain examples, the output is a digital file or a printed physical document. In certain examples, the output is sent to the output device 110 or used as a training data for identification machine learning model. The output can be saved on the medium 104. In certain embodiments, the medical visualization includes a path defined anatomic location, and the path defined anatomic location can be targeted relative to other parts of the medical visualization.

[0215] In certain embodiments, the system 100 can be configured to decode the encoded string into the medical visualization. The input device 108 can be configured to send the encoded string from the user. The generation model 116 can be configured to generate the output having the medical visualization based on the encoded string.

[0216] FIG. 11 illustrates example interfaces 1306 of the GUI 112 showing a visualization encoded into the encoded string. In certain embodiments, the system 100 enables coordinated anatomic site sharing systems and methods. The system 100 generates a code that retrieves a specific, custom coordinated visual asset from a library based on identifiers or characteristics (e.g., such as a numerical id, a language description, a set of coordinates, a detected area), and the directions and deviations and proximities related to self and neighboring or groups sites as determined by code, language, or calculations. In certain embodiments, the coordinated anatomic site is represented by an alphanumeric code that may contain symbols and calculations within it.

[0217] As one non-limiting example, 101 -L_(2)— did!0-dx80dy-17-otl_l would encode very specifically and allow this to be pulled up in a desired language through automatic translation of the named components. Breaking this non-limiting example down further, we know from thecoordinated string the following properties. The anatomic site (101=Sidewall of ala nasi), laterality (Left), the enhanced description of the pin position (2=posterior), the diagram id (10 = left side of nose), the deviation from center in the x axis (80) for the path on this particular diagram, the deviation from center in the y axis for the path on this particular diagram (-17), the order type (1), the order position. Changing properties on this will change the visualization dynamically, for example otA would change this to A as shown in non-limiting embodiments. As other non-limiting examples, otA_2 would change this pin label to be B, and ota_2 would change the pin label to be “b.” In certain embodiments, when lists are dynamically reordered, or order type is changed, these visualizations can maintain their position but have their properties dynamically changed. In certain embodiments, the pin order is in Chinese, Arabic, Roman, or other numerals or other alphabets.

[0218] This is a novel and vast improvement of technology and visual libraries because it specifies in the coordinated sharable string coordinates to a specific visualization, as well as deviations of a specific marker relative to the path on the visualization defined by the language descriptions, as well a pin position, order, and order type. In other embodiments, additional coded properties could be added to this to provide short URL parameters to interact with a plurality of databases to get even more information. In one non-limiting example, 101-R_(2)— didl0-dx80dy- 17-otl_l_D_2c32 would add “2C32” as a diagnosis associated with this pin and visualization as Basal Cell Carcinoma. The application of a plurality of data is possible through shortened strings that pull up precise, accurate, reproducible, and translatable visualizations even in different systems and different languages. In certain embodiments, the pin can be re-created by another input device such as by scanning a QR code, and automatic summaries can be written about them, and pins can be generated and placed automatically on a map, avatar, or image to correspond with the recreated information. In certain embodiments, such as the one shown as one non-limiting example, the recreated pin at a different time point might have a note automatically written about it like “This pin was ordered “B” when shared by Dr. Matt Molenda on shared date 2024-01-10. The shared notes were “biopsy proven BCC.’" The shared diagnosis information was: Basal cell carcinoma (2C32), Basal cell carcinoma, nodular (XH2CR0).”

[0219] Pin sharing has industrial applications, such as in healthcare where sharing the location of a disease, finding, or concern is critically important, and automatic documentation enabled by the system 100 also has similar industrial application. More than just pin order, position, description, and associated health information can be shared. In certain embodiments, sharing can also include reports, pdfs, and other imaging as non-limiting examples. In certain embodiments, the additional attachments can be shared through a unique pin id, wherein the attachments can be stored on a medium 104 accessible through a network as one example. In certain embodiments, when addingspecific information about a standardized map-diagram pair as a reference, the coordinates, deviations, proximities, levels, and / or calculations are extrapolated to other images, visualizations, or spatial data. In other words, the map-diagram pair in certain embodiments acts as a reference for other multimedia to further enhance precision, accuracy, reproducibility, and targeting. In certain embodiments, pin sharing allows for collation and normalization of health data to a dynamic anatomic address, even in different systems such as different electronic health records (EHRs) thus creating longitudinal tracking points for health data. In certain embodiments, the longitudinal tracking points for health data are used to generate, e.g., through the generation module 116, timelines and summaries related to anatomic sites, nearby anatomic regions (e.g., enabled by range categorization), diagnoses, procedures, relationships, or combinations thereof. In certain embodiments, other data related to anatomic site, diagnosis, procedures, images, text, or data in the medical record can be extracted and coordinated, related, and / or regenerated by combining their characteristics, with one practical example being automatically finding, extracting, and outputting an Accession Number, order (e.g. Specimen B), diagnosis, biopsy type, and biopsy date from a pathology report stored in the medium related to an anatomic region of interest. In certain embodiments, anatomic site is similar to a “docket” number at which to attach data over time, except that it can also be improved by being multidimensional and consistent across patients by coordinating to standardized data. In certain embodiments, the input is existing text, image, code, or combination thereof stored on the medium (e.g., existing medical records), and the data processing module 114 extracts, analyzes, categorizes, detects, and coordinates the data to one or more standardized concepts such as anatomic site, diagnosis, or procedure. In certain embodiments, non-anatomic concepts form their own “docket” locations to coordinate data into, such as diagnosis, and procedures; thus generating (e.g., through the generation module 116) longitudinal data that can be further analyzed in the omnidirectional system. Throughout this disclosure, certain embodiments can automatically coordinate data to standards, e.g. with the data processing module 114, such as standardized codes, coordinates, vision, symbols, images, or language, the system 100 which enables generation, e.g. with the generation module 114, of health data that is interoperable across any database, data format, or translated language. Interoperable health data is research-ready enabling further analysis by the system 100.

[0220] With respect to FIG. 16M, a method 1400 for generating a spatial description for a marker on an anatomic representation can include a step 1402 of rendering an anatomic representation on the display 106, wherein the anatomic representation includes a plurality of predefined anatomic sites, a plurality of predefined direction planes, or combinations thereof, wherein each of the direction planes overlap one or more of the predefined anatomic sites; a step 1404 of receiving an input from a user, wherein the input includes a name of anatomic site, adescription of the anatomic site, a procedure for the anatomic site, a diagnosis for the anatomic site, or combinations thereof; a step 1406 of rendering a marker on the anatomic representation based on the anatomic site of the input on the display 106; a step 1408 of determining the spatial description of the marker based on a spatial relationship of the marker with an overlapping direction plane of the predefined direction planes, an adjacent direction plane of the predefined direction planes, or combinations thereof; and a step 1410 of generating an output having the spatial description of the marker.

[0221] The step 1402 can include rendering the anatomic representation on the GUI 112 on the display 106. The anatomic representation includes a plurality of predefined anatomic sites, a plurality of predefined direction planes, or combinations thereof. Each of the predefined anatomic sites relate to a particular location on the anatomic representation. Each of the plurality of predefined direction planes overlap one or more of the predefined anatomic sites. Each of the plurality of predefined direction planes has one or more custom axes. For example, one of the predefined direction planes can have a custom axis oriented from a proximal direction to a distal direction, whereby the proximal direction is towards a head on the anatomic representation and the distal direction is away from the head of the anatomic representation.

[0222] The step 1404 can include receiving the input from the input device 108. The input can include a name of an anatomic site, a description of the anatomic site, a procedure for the anatomic site, a diagnosis for the anatomic site, or combinations thereof. In certain examples, the input is based on an interaction with the anatomic representation by the user, e.g., placing the marker on the anatomic site using the GUI 112. The input can be saved on the medium 104.

[0223] The step 1406 can include rendering on the display 106 the GUI having the marker on the anatomic representation based on the anatomic site of the input. The step 1406 can include processing the input to determine the anatomic site of the input. This can include comparing the input to the visual library. If the name of the anatomic site, the description of the anatomic site, the procedure for the anatomic site, or the diagnosis for the anatomic site match one of the anatomic sites in the visual library, a location of the marker on the anatomic representation is determined based on the matched result.

[0224] In certain examples, the step 1406 comprises training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm. The training data can include the visual library in the data processing module 114. The identification machine learning model can receive the name of the anatomic site, the description of the anatomic site, the procedure for the anatomic site, or the diagnosis for the anatomic site and output the location of the marker on the anatomic representation based on a matched result from the visual library in the data processing module 114. Non-limiting examples for the machine learningalgorithms includes span categorization-based algorithms, range categorization-based algorithms, or other similar algorithms, or combinations thereof.

[0225] The step 1408 can include describing the spatial relationship of the marker with one or more overlapping direction planes of the predefined direction planes, with one or more adjacent direction planes of the predefined direction planes, or combinations thereof.

[0226] The step 1410 can include displaying the spatial description presenting the output on the GUI 112 on the display 106. In certain examples, the output is a digital file or a printed physical document. In certain examples, the output is sent to the output device 110 or used as a training data for identification machine learning model. The output can be saved on the medium 104.

[0227] In certain examples, the anatomic representation includes one or more velocity centers and the input includes temporal data. The temporal data can include the date of analysis / patient data capture, and a change in the position of a condition, such as a disease, across one or more anatomic sites. The method 1400 can include a step 1412 of determining the tempo or velocity of a condition progression based on a direction of the condition relative to one or more the direction planes, one or more velocity centers, the change in the position of a condition, or combinations thereof. The method 1400 can include a step 1414 of generating a prediction matrix to capture, analyze, research, and / or predict progression of health data over time with velocity centers (e.g., also velocity borders, velocity paths, velocity scales) and direction planes. In certain embodiments enabled by the velocity centers and direction planes, the time data is analyzed along with intervention data (such as a medication or treatment as non-limiting examples), to capture, analyze, research, and / or predict how interventions data affects the progression data over time, space (e.g. body surface area), other factors (e.g. morphology, severity, lesion counts), or combinations thereof.

[0228] In certain examples, the system 100 can be configured to generate a spatial description for the marker on the anatomic representation. The display 106 can be configured to render the GUI 112 having the anatomic representation. The input device 108 can be configured to send the input from the user. The display 106 can be configured to render the GUI 112 having the marker on the anatomic representation. The data processing module 114 can be configured to determine the spatial description of the marker based on a spatial relationship of the marker with an overlapping direction plane of the predefined direction planes, an adjacent direction plane of the predefined direction planes, or combinations thereof; determining the tempo or velocity of a condition progression based on a direction of the condition relative to one or more the direction planes, one or more velocity centers, the change in the position of a condition, or combinations thereof; and generating a prediction matrix to capture, analyze, research, and predict progression of health data over time with velocity centers (e.g., also velocity borders, velocity paths, velocityscales) and direction planes. The generation module 116 can be configured to generate the output having the spatial description of the marker.

[0229] FIG. 12 illustrates an example anatomic representation 1416 and example anatomic representation 1418, each having velocity centers and direction planes. The system 100 can be configured to capture, analyze, research, and predict progression of health data over time with velocity centers and direction planes. As shown in FIG. 12 different colors or patterns are used to illustrate direction planes 1420 stored in association with physical maps or maps stored in the medium 104. As illustrated in FIG. 12, some direction planes 1420 on the forearms / hands are outlined to visualize. With the direction planes 1420, the system 100 can describe relationships among points 1422 in a different direction plane 1424 or overlapping planes (not shown in the figure which is a non-limiting example). Also illustrated in the embodiment are non-limiting axial synonyms such as “Medial” and “Ulnar” meaning the same thing in the direction plane 1426. Also shown in the non- limiting embodiment is a rotation of a customized axis and an axial synonym (for clarity, the axis showing Proximal, Cephalad, etc. is a non-limiting example of a rotated axis of interpretation within a direction plane) in the direction plane 1426. In the non-limiting example, if "Cephalad" means toward the head, but also can mean "Anterior" on the extremities, "Proximal" may be the term of choice on extremities because it is less ambiguous in the context. Different areas of the body may have different axial synonyms related to direction planes; like as one example, on the forearms and hands, "Medial" can also be described as "Ulnar." Direction planes may also have different angles of interpretation (e.g., 1420 vs 1424) as illustrated in the nonlimiting embodiments.

[0230] In certain embodiments, directions can be assigned to different anatomic regions by weighting them numerically into matrices and storing or processing in communication with the medium 104. In certain embodiments, a quantum computing type processor 102 within the system 100 can be used to determine the state of different anatomic site segments, group, or subsegments along a spectrum and direction. It is contemplated that quantum computing has more than two state variables at a time, e.g., non-binary data composed of more than just “0” and “1” states. The deviation from center calculation is one such measure of numerous state variables, as one non-limiting example. Deviations in direction planes related to paths, path groups, points within paths, points within path groups are an improvement in the system 100.

[0231] In one non- limiting embodiment, direction planes have weights associated with different directions. When combined with other data enabled by the system 100 and stored in the medium 104, such as non-limiting examples like patient characteristics (like body mass index BMI), height, weight, distance to umbilicus from floor, or temporal data (like date of analysis / patient data capture), the tempo or velocity of disease progression or change can be determined along withdirection. As one non-limiting example, the system 100 can process (e.g. through the data processing module 1 14) and summarize research data (e.g. through the data generation module 116), such as where on the body a skin disease usually starts, what the morphology is at different time points, which direction it spreads in, etc. as non- limiting examples. The system 100 can answer questions like “if the velocity of spread starts to speed up and involves a certain morphology the cephalad direction, is this a sign that more aggressive therapy should be started quickly to minimize the risk of a poor outcome?” Answering questions like this non-limiting example has traditionally relied on human expert experience and opinion, with non- standardized methods of tracking or validating velocity and direction, whereas the system 100 enables coordination to standardized or normalized methods of tracking through communication with its modules (e.g., the data processing module 114 and / or the generation module 116).

[0232] In certain embodiments, including body mass index (BMI) and other data also helps to convert language more precisely to surface area calculation. Additionally, each path or path segment or path group in the system 100 can have a calculation or property associated with it that is shown visibly enabled by the GUI 112. In certain embodiments, a percentage of a path or path segment involved in calculating Body Surface Area (BSA) of involvement can have different weights associated with it, with opacity adjustments of color, or pattern adjustments of dots as nonlimiting examples. Relationships and dynamic boundaries of the paths (e.g., proportional progressive segmentation) can be generated based on their relationships to one another and / or to direction planes, centers, centroids, and other calculable or definable characteristics of paths in the medium 104. In certain embodiments, descriptions of body locations can also be collapsed into, expanded into, combined into, or combinations thereof into normalized or recalculated coordinates to generate processed health data like BSA estimates (e.g., the data processing module 114 and / or the generation module 116). In certain embodiments, BSA estimates are normalized through the data processing module 114 to standardized estimates like Lund Browder estimates thus creating more research-ready data. Predicting metastatic spread patterns for cancer is another non- limiting example that would benefit from the system 100.

[0233] FIG. 13 illustrates example anatomic representations 1428 having velocity planes that can be associated with anatomy data (such as hierarchical terminology) and to visual anatomic sites. When combined with temporal data and change data, such as, changes in morphology or diagnosis, or presence or absence of a finding as non-limiting examples, the velocity and direction of change is able to be determined by the data processing module 114 of the system 100. The vertical numbers 1430 (1 -7 in this grid) are a non-limiting example that can be used to determine directions like Cephalad to Caudad, Superior to Inferior, Inferior to superior, etc. as non-limiting examples. The horizontal numbers 1432 (-4 to 4) can determine midline / central involvement (e.g.at 0) to peripheral involvement, and as one skilled in the art would know the scales do not need to be whole numbers or even numerical, and absolute values can be used to describe deviation from a center if, for example, laterality is not a needed part of the analysis as one non- limiting example. One non-limiting example is offered to better understand this teaching: the system 100 can contemplate a disease that starts as “redness’- and has a symptom of “itching” on the central abdomen (Vertical grid 3, Horizontal scale 0) and moves outward in all directions (moves in a centripetal pattern) with vesicles and redness and itching and crusts appearing at different times within a few days (temporal relationship, the system 100 can generate a diagnosis (e.g. enabled by the generation module 116) of primary varicella or “Chicken pox” as one non- limiting example. Conversely, as another non-limiting example, lesions that are all of similar morphology moving toward the center of the body (in a centrifugal pattern) is more consistent with Smallpox diagnosis. The system 100 is enabled by the data processing module 114 stored on the medium 104 to generate a diagnosis enabled by the data processing module 114 and / or the generation module 116, as one non-limiting example. The deeper black lines of the figures illustrate non-limiting velocity centers stored in the medium 104. The shaded shapes around the anatomic illustrations represent direction planes 1420 as previously described as another possible scale for velocity, spread, and / or progression, (not all direction planes or velocity centers are shown even in this non-limiting embodiment to facilitate understanding). The vertical numbers 1430 (1-7 in this grid) are a nonlimiting example that can be used to determine directions like Cephalad to Caudad, Superior to Inferior, Inferior to superior, etc. as non-limiting examples. The horizontal numbers 1432 (-4 to 4) can determine midline / central involvement (e.g. at 0) to peripheral involvement, and as one skilled in the art would know the scales do not need to be whole numbers or even numerical, and absolute values can be used to describe deviation from a center if, for example, laterality is not a needed part of the analysis as one non-limiting example. The velocity centers do not have to be straight lines as illustrated on the “Right side of body” illustration with the deeper black line 1434 separating the anterior and posterior body, which can capture direction from front to back or vice versa as another non-limiting example. Velocity centers do not necessarily even need to be centered and can also be described in some embodiments as velocity planes, velocity scales, direction scales, direction centers, directional centers, velocity matrices, gridmarks, or data matrix borders. In certain embodiments, capturing this data delivers not only spatial and data-based relationship and data matrices, but also directional measures, temporal measures, and progression / regression measures. In certain embodiments, such data enables the generation of a prediction matrix to capture, analyze, research, and predict progression of health data over time with velocity centers (e.g., also velocity borders, velocity paths, velocity scales) and direction planes 1420. In certain embodiments, data can be input into the medium 104 and become part ofthe data processing module 114, which can include knowledge about individuals or populations or studies.

[0234] In certain embodiments such scales can be more efficiently applied with non-binary processing, such as with a quantum computing processor, as one non-limiting example. In certain embodiments, the processor 102 of the system 100 can be a quantum processor.

[0235] In certain embodiments, the system 100 creates a prediction network of coordinated data to capture, analyze, research, and predict progression of health data over time with components of the system 100 physically stored in the medium 104 velocity centers and direction planes, as nonlimiting examples. In certain embodiments, the prediction network analyzes temporal data, patient data, encounter data, diagnosis data, anatomy data, symptom data, morphology data, images, relationships, and other data as non-limiting examples to generate additional conclusions or suggestions. For example, questions like “if the tempo of disease progression increases to a specific anatomic location and characteristics (e.g. like morphology) as non-limiting examples, does this mean the disease is likely to get better or get worse?’" can be answered through the system 100. Other non-limiting example questions answered by the system 100 can include “If the disease is predicted to get worse, how quickly will it get worse? Where is it likely to spread?What treatment will this patient do best with based on the disease factors? Should we escalate therapy immediately? Etc.” In certain embodiments, the directional centers are not actually in a true center, and centroid or center of mass may be used as alternate centers. In certain embodiments, directional centers are applied to physical objects or spatial objects input into or stored within the system 100, with non-limiting examples being floor plans, cars, boats, microscopic slides, videos, illustrations, images, 3D models, and other data. Such objects can be animated or inanimate. In certain embodiments, the fourth dimension of time is added to show changes over time in relation to the directional centers. In certain embodiments, points of interest can be their own directional centers, and contain directional centers within them. These directional centers can interact with other points of interest or map data, with natural language descriptions or encodings in any language to describe relationships, velocities, directions, movements, positions among them. As some non-limiting examples, two points of interest could be two different people on a floor plan each with their own directional centers and direction planes interacting with the floor plan or field plan. The system 100 can describe, in natural language, to “move left” or “move right” in the correct language as well as velocity such as “move left quickly, run” or “slowly move right” or “look up” based on velocity of different directional centers. In certain non-limiting embodiments, a finding such as a mole I nevus on the body, can have its own directional centers present on a microscopic level, dermatoscopic level, or grossly visible level. Knowing the depth of invasion of a mole that is actually a malignant melanoma at one edge, and which direction themelanoma is invading deepest can help predict metastatic spread patterns or the lymph nodes most likely to be involved. Tn certain non-limiting embodiments, two lesions, rash findings (like morphology or symptoms) can be described relative to one another through spatial relationships, surface areas, and directions enabled by the directional centers and direction planes of the system 100.

[0236] With respect to FIG. 16N, a method 1500 for capturing, analyzing, researching, and predicting progression of health data comprises a step 1502 of receiving an input, from the input device 108, having health data, wherein the input is text-based, visual-based, audio-based, and / or based on an interaction with the anatomic representation; a step 1504 of capturing data related to time / temporal, anatomy, diagnosis, morphology, or other characteristics in relation to directional centers or direction planes; and a step 1506 of processing the captured data into categories and context.

[0237] The processor 102 can be a quantum computing processor. The directional centers can be applied to physical objects and physical objects have one or more directional centers defined in the medium 104 or calculated by the data processing module 114. The categorized and contextual data can create a data matrix. The data matrix can be further processed within the medium 104 to analyze or research the data matrix. The data matrix can enable prediction generation related to anatomic site, diagnosis, surface area, or other health data. The directional centers can be applied to physical objects.

[0238] The system 100 can detect and / or describe and / or highlight and / or target anatomic sites on images, illustrations, or other multimedia like video as non-limiting examples, regardless of multimedia angle. In certain embodiments, LIDAR based cameras can help with this (e.g., by creating a 3D scan that can also have measurements). The system 100 can process (e.g., enabled by the processor 102) health documents including text summaries, scanned records, handwritten records, and images to categorize, capture, summarize, and visualize health data. Anatomic site, diagnosis data, patient data, encounter data, and other health data can be summarized and visualized by the system 100. Span categorization and coordination of health data can detect, organize, analyze, encode, summarize, predict, and otherwise coordinate health data.

[0239] As one non-limiting example, a faxed record of handwritten notes describing a basal cell carcinoma on the right nose can properly encode, translate, visualize, describe, coordinate, and map the data with the correct information and timepoint. The system 100 with different direction planes and directional centers can document origination points and radiation points through language, visual descriptions, and coded or mathematical descriptions. For example, documenting symptoms of heaviness and pain originating around the left chest and radiating in a superior direction (toward the chin) and distally direction down the left arm can point to symptoms of amyocardial infarction or heart attack, as one non-limiting example.

[0240] With respect to FIG. 16P, a method 1700 for estimating a surface area of a region of interest can include a step 1702 of receiving instructions from the user to estimate the surface area of a region of interest; a step 1704 of determining a number of anatomic sites within the region of interest; a step 1706 of determining an estimation of the surface area of the region of interest based on the number of anatomic sites within the region of interest; and a step 1708 of generating an output with the estimation of the surface area of the region of interest.

[0241] The step 1702 can include the user sending the instructions via the input device 108. The region of interest can refer to an anatomic site or a group of anatomic sites. In certain embodiments, selection of anatomic sites, via the input device 108, prompts calculation of surface area relative to a segment of an anatomic visualization or group, and / or relative to the entire body.

[0242] The step 1704 can include comparing the region of interest to the visual library. The visual library includes a plurality of anatomic representations. Each of the anatomic representations has a plurality of predefined anatomic sites correlated with medical information, such as the anatomic site name and an average surface area of said anatomic site. If the region of interest matches one or more of the predefined anatomic sites, the number of anatomic sites within the region of interest can be determined based on the matched predefined anatomic sites.

[0243] In certain examples, the step 1704 comprises training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm. The training data can include the visual library in the data processing module 114. The identification machine learning model can receive the region of interest and output the number of anatomic sites within the region of interest based on a matched result from the visual library in the data processing module 114. Non-limiting examples for the machine learning algorithms includes span categorization-based algorithms, range categorization-based algorithms, or other similar algorithms, or combinations thereof.

[0244] The step 1706 can include adding together the average surface area of each anatomic site within the number of anatomic sites based on the visual library to generate an estimation of the surface area of the region of interest.

[0245] The step 1708 can include displaying the estimation of the surface area of the region of interest on the GUI 112 on the display 106. In certain examples, the output is a physical document or a digital file. In certain examples, the output is sent to the output device 110 or used as a training data for identification machine learning model. The output can be saved on the medium 104. In certain examples, the step 1708 includes displaying the number of anatomic sites within the region of interest with indicia within each anatomic site to represent the average surface area of said anatomic site.

[0246] In certain embodiments, the system 100 can be configured to estimate the surface area of the region of interest. For example, the input device 108 can be configured to send the instructions from the user to estimate the surface area of a region of interest. The data processing module 114 can be configured to determine the number of the anatomic sites within the region of interest and determine the estimation of the surface area of the region based on the number of anatomic sites within the region of interest. The generation module 116 can be configured to generate an output with the estimation of the surface area of the region of interest.

[0247] In certain embodiments, body surface area calculations are simplified for practical industrial utility, so that they may be used on paper diagrams. As one non-limiting example, only an anterior and posterior view of the whole body (front and back) is used to calculate BSA, with the anterior side representing 50% of the body, and the posterior side representing 50% of the body in one non-limiting embodiment. The surface area and intensity of each anatomic site, as shown by opacity or percent coverage in certain embodiments, contributes to the overall percentage score. This represents a significant improvement in accuracy, triage, and calculations when compared to Lund Browder diagrams. Additionally, different body types can be available, or the avatars can be adjust dynamically based on patient BSA, waistline, height, age, and other characteristics in some non-limiting embodiments. Increased accuracy, precision, and ease of use in BSA calculations, severity, and distribution (e.g., weighting certain anatomic regions as more critical, like hands, genitals, face). Hierarchical painting and augmented documentation enabled by the system 100 are non-limiting examples that would be practically useful.

[0248] FIG. 14 illustrates an example anatomic representation 1710 that has been segmented into a plurality of predefined sites 1712. This can enable volumetric and spatial analysis and measurements from language, code, or symbols describing anatomic sites, distributions, and modifiers of anatomic sites. The language, code, symbols, or combinations of these as inputs into the system 100 can describe an anatomic site, collection of anatomic sites, modified anatomic sites (e.g., with components of language such as laterality, prefixes, or suffixes as non- limiting examples), distribution of anatomic sites; relationships between anatomic sites; or other combinations of health findings in an anatomic site. The data processing module 114 processes the components to enable outputs through the generation module 116 with non-limiting output examples including visualizations, descriptions combined to natural language to describe a group, and / or calculations.

[0249] In certain embodiments, each anatomic site can have characteristics such as laterality, prefixes, suffixes, relationships, spatial neighbors, data neighbors, and other characteristics. As shown in FIG. 14, a simple grid can break up the Right Palm of hand, shown in gray shading. The “Right” term represents a laterality modifier and an inherent characteristic of the entire diagram.A+C+E+G in this embodiment illustrates the “Right Lateral Palm of hand”; and B+D+F+H in this embodiment illustrates the “Right Medial Palm of hand” wherein the “Lateral” and “Medial” components are prefix modifiers in certain embodiments. With a language based description of the “Right Proximal Palm of hand” as one example of an input into the system 100, a body surface area estimate for this description can be output by the system 100, by adding together the surface area A+B with the data processing module 114, and knowing that the “palm of the hand” is approximately 1% of the body surface area from the libraries in the data processing module 114. Therefore, the surface area calculation determined by language inputs in this non-limiting example, for the “Right Proximal Palm of hand” (A+B) is 0.25%.

[0250] Processing (e.g. through the data processing module 114) of anatomic maps, diagrams, images, and avatars by the system 100 can also generate a knowledge base through the data processing module 114 to be stored in the medium 104 that includes measurements and calculations, such as body surface area, for different language-based descriptions of anatomy or modified anatomy. For a non-limiting example, the “left forehead” would have a different measurement than the “right forehead”, but the “forehead” would have a measurement equivalent to the “right forehead + left forehead.”

[0251] As shown in FIG. 16Q, a method 1800 for correlating mixed inputs can include a step 1802 of receiving a plurality of inputs from the user, wherein at least one of the inputs includes an audio component and at least another input includes a visual component; a step 1804 of determining context between the audio component and the visual component; and a step 1806 of generating an output having standardized data based on the context between the audio component and the visual component.

[0252] The step 1802 can include receiving the plurality of inputs from the input device 108. At least one of the inputs includes the audio component and at least another input includes the visual component. Non-limiting examples of the audio component includes audio recordings or audio being streamed from the input device 108. Non-limiting examples of the visual component includes images, videos, and other visual-based content. The plurality of inputs can be saved to the medium 104.

[0253] In certain examples, the audio component includes medical information related to a shorthand for an unspecified anatomic site and the visual component includes a visual representation of the shorthand correlated to an anatomic site. For example, the audio component may include the following statement “I’m taking a photo of specimen A (short hand for an anatomic site), which is a 4mm pink shiny papule, rule out basal cell carcinoma and I’m doing a shave biopsy”, while the visual component includes a photograph a patient with a marker labeled A affixed to an anatomic site on the patient (visual representation of the shorthand correlated to ananatomic site). In certain examples, the visual component is a drawing of an anatomic representation with a marker disposed on an anatomic site. In certain examples, the visual component is an anatomic representation with a marker disposed on an anatomic site rendered on the display 106. In certain examples, the visual component includes the shorthand marked on physical paper (that is subsequently digitized), on the GUI 112 with the input device 108, such as a touchscreen with a digital pencil, placed with the input device 108 such as by dropping pins on a digital avatar or map, or combinations thereof.

[0254] The step of 1804 can include identifying shorthand for an unspecified anatomic site in the audio component and identifying the anatomic site correlated with the shorthand in the visual component. The step of identifying shorthand for an unspecified anatomic site in the audio component can include scanning the audio component for shorthand that matches shorthand found within a library of common shorthand terms in the data processing module 114. The library of common shorthand terms can include a list of shorthand terms for anatomic sites correlated with said anatomic sites. In certain examples, identifying shorthand for an unspecified anatomic site in the audio component comprises training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm. The training data can include the library of common shorthand terms in the data processing module 114. The identification machine learning model can receive the audio component and output the identification of the shorthand within the audio component based on a matched result from the library of common shorthand terms in the data processing module 114. Non-limiting examples for the machine learning algorithms includes span categorization-based algorithms, range categorization-based algorithms, or other similar algorithms, or combinations thereof.

[0255] The step of identifying the anatomic site correlated with the shorthand in the visual component can include comparing an anatomic site marked with the shorthand in the visual component with the visual library in the data processing module 114. If the anatomic site correlated with the shorthand matches an anatomic site in the visual library, the anatomic site correlated with the shorthand can be determined based on the matched result from the visual library. In certain examples, identifying the anatomic site correlated with the shorthand in the visual component comprises training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm. The training data can include the visual library in the data processing module 114. The identification machine learning model can receive the visual component and output the identification of the anatomic site correlated with the shorthand based on a matched result from the visual library in the data processing module 114. Non-limiting examples for the machine learning algorithms includes span categorization-based algorithms, range categorization-based algorithms, or other similaralgorithms, or combinations thereof.

[0256] The step 1806 can include generating an output whereby the standardized data includes the medical information from the audio component with the anatomic site correlated with the shorthand. The output can be presented on the GUI 112 on the display 106. In certain examples, the output is a printed physical document or a digital file. In certain examples, the output is sent to the output device 1 10 or used as a training data for identification machine learning model. The output can be saved on the medium 104.

[0257] In certain embodiments, the system 100 can be configured to correlate mixed inputs into standardized data. For example, the input device 108 can be configured to send the plurality of inputs from the user. At least one of the inputs includes an audio component and at least another input includes a visual component. The data processing module 114 can be configured to determine the context between the audio component and the visual component. The generation module 116 can be configured to generate the output having the standardized data based on the context between the audio component and the visual component.

[0258] Various orders or chronologies that can be selected to facilitate data coordination and organization, in multiple languages and character sets. Verbal interaction with the system 100 can be listened to by a transcribing service, and ambient listening Al scribe, or handwritten or typed data can be entered into I onto forms, and correctly categorized with diagnostic, procedural, anatomy, and other data. The service in this non-limiting embodiment enabled by the system 100 could be managed by artificial intelligence. For example, if a verbal discussion or input documentation is relevant to “site A,” and the system 100 is aware of the context and anatomic location for “site A,” the new data can automatically be interpreted, organized, categorized, and processed relevant to “site A” as one non-limiting embodiment. This can mitigate the need for the user to use or for verbalization of highly specific or specialized terminology in their documentation process, and the system 100 practically solves challenges in reproducibility of data coordination in a clinical setting.

[0259] In certain embodiments, tone differences, language differences, and punctuation differences can be detected. For example, if “sitio” “ah” is verbalized in Spanish, the system 100 knows this correlates with “Site A” (verbalized phonetically as “site” “eh”) in the English documentation. Verbalized “One” in English can correlate with documentation for “site 1” just as “Uno” in Spanish can correlated with “site 1.” The order, order type, and language detections in this non-limiting embodiment provides an organization framework for the health data. In other embodiments, empty boxes correlating with “Site A” in an English paper form, as one non-limiting example, can have handwritten details about the health data serve as an input, which is automatically detected, analyzed, processed, organized, and coordinated within the system 100.Different order types can also be used like “alpha” and “beta” for 1 and 2. In certain examples, order types can include color-coding (ROYGBTV), alphabetical, custom, numerical, or combinations thereof. These can also be in different languages. In certain embodiments, verbalization of an action is captured by the input device 108 (e.g. a microphone) and processed by the data processing module 114 to select the correct template or tool from a plurality of templates or tools (e.g. to plot or associate diagnosis, procedures, observations, morphologies, images, forms, order, additional count, measurement, etc.) in the medium 104 to interact with a digital map or avatar with the another input device 108 (e.g. a mouse, camera, sensor, touchscreen, or combination thereof, etc.) in communication with the GUI 112.[00260 J In one non-limiting example, the user can verbalize “shave biopsy” and the template for “shave biopsy” will automatically be selected and the next mouse-click or touchpoint will document, capture, order, organize, coordinate, visualize, encode, translate, and describe “shave biopsies” to the correct list, diagnosis, anatomic site, order, and procedure. When there is already one shave biopsy documented with a list with a capital letter order type, the next two clicks or touches after verbalization would be ordered as “B” and “C” in the biopsy list. The procedures can be automatically associated with the correctly generated or selected diagnosis and codes such as diagnosis codes and billing codes, e.g., by the data processing module 114 and / or the generation module 116.

[0261] In certain embodiments, input can be ambient conversations such as those between a physician and a patient, captured through the input device 108 such as a microphone as one nonlimiting example, and the system 100 can coordinate and organize data to the correct locations in a template, to the correct anatomic site, to the correct diagnosis, and / or to the correct procedure as non-limiting examples. In certain embodiments, the coordinated data becomes visible, mapped, targeted, isolated, selected, plotted, normalized, described, organized, structured, or combinations thereof on a shadow chart or digital chart, selectively organized with the correct selected order type. In certain embodiments, the coordinated data is output to structured data (e.g., JSON, SQL) and can be combined, analyzed, or further coordinated with other health data already present in the record to modify or generate additional processed health data (e.g., the data processing module 114 and / or the generation module 116). In certain embodiments, large language models (LLMs), Domain Language Models (DLMs), or other models, or combinations thereof are employed by the omnidirectional system 100.

[0262] In certain embodiments, input through the input device 108 can be through ambient or recorded conversations that occur simultaneously with a paper or digital chart that contains map data input by hand drawing / markup or by the input device 108 that allow for interaction with the map such as a mouse or stylus as non-limiting examples. As one non-limiting example, aconversation where the physician states, “we’re going to treat the rash on your feet with terbinafine cream” and “the pathology note for site A is ‘present for 2 months, bleeding, rule out BCC.’ this spot is 4mm, pink, and shiny. We are doing a shave removal biopsy” and “the pathology report for B is ‘black lesion, 4mm, rule out melanoma,’ B is a 4mm punch biopsy.”

[0263] The system 100 can have a plurality of defined pathways to visualize, coordinate, encode, organize, and document this data; with certain embodiments using a hybrid of plotting or indicating (e.g., highlighting, encircling as non-limiting examples) of data on maps, images, forms, or combinations thereof and the audio input information. In certain embodiments, multimodal input is processed (e.g., by the processor 102) so that timing, sequence, or other mixed input can be coordinated to the correct order, order type, anatomic site, diagnosis, or other defined finding. As one non-limiting example, a physician can mark biopsy sites A, B, and C on a paper map as input 1 , mark A, B, and C with a marker on the actual patient, take photos with a camera of the input device 108 as input 2, and while taking photos verbalize, for example, “now I’m taking a photo of specimen A, which is a 4mm pink shiny papule, rule out basal cell carcinoma and I’m doing a shave biopsy” as input 3. Based on the timing of the verbalization input and the photo, in this non-limiting example, and the paper map input and processed to coordinated and processed health data (e.g. by data processing module 114), the photo is automatically coordinated to the correct procedure, anatomic site, billing code, list, diagnosis code, and other templates from a plurality of templates. In other certain embodiments, the audio conversation detects anatomic sites and creates visualizations and / or a visual library and / or targeted and refinable map data from the conversations. In other certain embodiments, the audio conversation extracted data are combined with map data, image data, and other health data in the omnidirectional system 100. Continuing the non-limiting example above, the audio did not specify an anatomic site for A or B. This could be specified synchronously with one or more of the input device (e.g. a microphone input plus a mouse input), later in the audio (e.g. an audio recording being processed along with other health data), or combinations thereof, on a map, template, or form, or even extracted by detecting and describing the anatomic site on a photograph of the patient that physically marked the sites as A and B before photographing (such as with a surgical marker or a label as non-limiting examples), or combinations thereof. These non-limiting examples illustrate the omnidirectional nature of the system 100.

[0264] As shown in FIG. 16R, a method 1900 for filtering audio can include a step 1902 of receiving an input from the user, wherein the input includes audio; a step 1904 of determining if the audio includes undesirable noise; if the audio includes undesirable noise, a step 1906 of at least substantially removing the undesirable noise from the audio of the input; a step 1908 of generating an output having filtered audio, wherein the filtered audio is the audio with the undesirable noisesubstantially removed therefrom.

[0265] The step 1902 can include the user sending or streaming the input via the input device 108. The input includes the audio. The audio can be a previously recorded audio sample or audio that is currently streaming from the input device 108. The input can be saved to the medium 104.

[0266] The step 1904 can include comparing the audio with a library of sounds in the data processing module 114. The library of sounds can include audio signatures for undesirable noises. Non-limiting examples of undesirable noises can include common background noises, healthcare intercom announcements, healthcare machine sounds, music, or combinations thereof. If the audio does not match the audio signature from the library of sounds, the audio will not be filtered.

[0267] If the audio does match the audio signature from the library of sounds, the method proceeds to the step 1906. This can be accomplished by digitally subtracting the undesirable noise from the audio of the input. In certain examples the undesirable noise is removed from the audio of the input.

[0268] The step 1908 can include generating an audio recording of the filtered audio or generating a transcript of the filtered audio. In certain examples, the step 1908 includes presenting the output on the GUI 112 on the display 106. In certain examples, the output is a digital file or a printed physical document. In certain examples, the output is sent to the output device 110 or used as a training data for the identification machine learning model. The output can be saved to the medium 104.

[0269] In certain embodiments, the system 100 can be configured to filter audio. For example, the input device 108 can be configured to send the input from the user. The input includes the audio. The data processing module 114 can be configured to determine if the audio includes undesirable noise and, if the audio includes undesirable noise, at least substantially removing the undesirable noise from the audio of the input. The generation module 116 can be configured to generate the output having the filtered audio. The filtered audio is the audio of the input with the undesirable noise at least substantially removed therefrom.

[0270] In certain embodiments, ambient audio filters are enabled by the processor 102 during healthcare encounters. In certain embodiments, music, beeps, machine noise, intercom announcements, and other background noise are common during healthcare encounters and can interfere with coordination of health data in ambient listening workflows. In certain embodiments, when an audio output device, such as a smart speaker, is also the input listening device, such as a microphone on that same device, being able to filter out irrelevant noise and focus on the relevant audio is critical to accuracy and precision of the processed health data. In other certain embodiments, a music speaker or intercom system may be different from the input device 108 with a microphone. It is necessary to be able to filter out audio that is not relevant to the healthcareconversation. The system 100, using the processor 102 and / or the data processing module 114 in some embodiments, filters out the irrelevant audio and focuses on the relevant ambient sounds and language. For example, the system 100 can recognize that music is playing, check the data processing module 114 for the audio signature of the specified music, and digitally subtract audio matching that signature. The patient experience has been shown to be enhanced by music playing, such as in office-based procedures and surgeries. In the current state of the art, ambient listening technology used to coordinate health data to and from forms and other parts of the records are impaired by background music, making music less plausible to have on when using ambient listening technology to coordinate health data. In certain embodiments, the processor 102, input device 108, and audio output device are in the same hardware system and can directly subtract the output audio from the input audio in real time.

[0271] In certain embodiments, the audio inputs correspond with digital or paper forms (that have not yet been input into the system 100, in some non-limiting embodiments), and the system 100 tracks and organizes the processed health data to put into a mapped, coordinated organizational framework. In certain embodiments, the audio corresponding with the form health data, can be synchronous or asynchronous.

[0272] With respect to FIG. 16S, a method 2000 for encoding a skeleton-based diagnosis or procedure into an encoded string can include a step 2002 of receiving an input from the user, wherein the input includes a diagnosis or procedure related to an anatomic region of a skeleton system, a laterality modifier of the anatomic region, whether the diagnosis or procedure involves an open or closed fracture, a fracture subtype, and a specific anatomy of the anatomic region where the diagnosis or procedure occurs; and a step 2004 of generating an output having the encoded string. The encoded string has a diagnosis or procedure portion, a laterality modifier portion, a fracture open or closed portion, a fracture subtype portion, and a specific anatomy portion.

[0273] The step 2002 can include receiving the input from the input device 108. The input includes a diagnosis or procedure related to anatomic region of a skeleton system, a laterality modifier of the anatomic region, whether the diagnosis or procedure involves an open or closed fracture, a fracture subtype, and a specific anatomy of the anatomic region where the diagnosis or procedure occurs. The input can be saved on the medium 104.

[0274] The step of 2004 can include presenting the encoded string on the GUI 112 on the display 106. In certain examples, the output is a physical document or digital file having the encoded string. In certain examples, the output is sent to the output device 110 or used as a training data for identification machine learning model. The output can be saved to the medium 104. The diagnosis or procedure portion of the encoded string correlates to the diagnosis or procedure related to anatomic region of a skeleton system, e.g., fracture of the index finger. The lateralitymodifier portion correlates to a laterality modifier that describes a position of the anatomic region relative to the skeleton system, e.g., the right index finger. The fracture open or closed portion correlates to whether a fracture is a closed fracture or an open fracture. The fracture subtype portion correlates to the fracture subtype of the fracture, e.g., transverse fracture. The specific anatomy portion correlates to specific anatomy of the anatomic region where the diagnosis or procedure occurs, e.g., middle phalanx of the index finger.

[0275] In certain embodiments, the system 100 can be configured to encode a skeleton-based diagnosis or procedure into an encoded string. For example, the input device 108 can be configured to send the input from the user. The generation module 116 can be configured to generate the output having the encoded string.

[0276] FIG. 15 illustrates an example anatomic representation having a marker thereon. The marker represents a closed transverse fracture of the middle phalanx of the ring index finger. The marker can be encoded into the following encoded string: NC53.60&XK9K&XJ44E&XJ5V7&XA3JL6, wherein NC53.60 correlates to the diagnosis or procedure portion (fracture of index finger), XK9K correlates to the laterality modifier portion (right), XJ44E correlates to the fracture open or closed portion (closed fracture), and XJ5V7 correlates to the fracture subtype portion (transverse fracture), and XA3JL6 correlates to the specific anatomy portion (the middle phalanx of the index finger). In certain embodiments, this same exact code is shown with generated coordinates and visualizations to the exact location but from a surface diagram rather than skeletal, e.g., through the generation module 116, without the need for additional human intervention, enabled through a coordinated language model of the system 100. In certain embodiments, code, language, or vision, or combinations thereof is applied progressively, proportionally, or combinations thereof to generate or select new descriptions, new targets, new map points, or combinations thereof on new or alternate images, visual library components (e.g., maps, avatars, etc.) or combinations thereof. As one skilled in the art would know, this can apply to other organ systems as well, where there may be overlap in coordinates but completely different organ or functional relationships.

[0277] As shown in FIG. 16T, a method 2100 for processing an input having health data comprises a step 2102 of receiving an input having a description related to health data; a step 2104 of analyzing the description for anatomic site names, anatomic site name synonyms, laterality, modifiers (e.g. prefixes, suffixes, directional modifiers, central zone modifiers), magnitude modifiers, laterality synonyms, modifier synonyms, magnitude modifier synonyms, directional synonyms, or combinations thereof to generate normalized data; and a step 2106 of generating an output based on the normalized data, wherein the output includes a path that is selected, coordinated, targeted, described, translated, visualized, mapped, normalized, and / or encoded basedon its spatial location or relationship, data-based location or relationship, context (e.g. surface vs. deep, point vs. region), directional location or relationship, or combination thereof.

[0278] The step 2102 can include receiving the input having the description related to health data from a user via the input device 108. The description can include an anatomic site name, anatomic site name synonyms, laterality, modifiers (e.g., prefixes, suffixes, directional modifiers, central zone modifiers), magnitude modifiers, laterality synonyms, modifier synonyms, magnitude modifier synonyms, directional synonyms, or combinations thereof. The input can be saved on the medium 104.

[0279] The step 2104 can include scanning the description for anatomic site names, anatomic site name synonyms, laterality, modifiers (e.g., prefixes, suffixes, directional modifiers), magnitude modifiers, laterality synonyms, modifier synonyms, magnitude modifier synonyms, directional synonyms, or combinations thereof to generate normalized data. This can include comparing the description to the modifier library within the data processing module 114. The modifier library can include anatomic site names, anatomic site name synonyms, laterality, modifiers (e.g., prefixes, suffixes, directional modifiers, central zone modifiers), magnitude modifiers, laterality synonyms, modifier synonyms, magnitude modifier synonyms, directional synonyms correlated to anatomic sites. If the description includes anatomic site names, anatomic site name synonyms, laterality, modifiers (e.g., prefixes, suffixes, directional modifiers, central zone modifiers), magnitude modifiers, laterality synonyms, modifier synonyms, magnitude modifier synonyms, directional synonyms correlated to a matched anatomic site, normalized data can be generated based on said data being coordinated to the matched anatomic site. In certain embodiments, the order of the modifiers does not matter. In certain embodiments, a modifier being included in an anatomic site name also does not affect the ability to coordinate language with multiple modifiers to the correct generated or selected anatomic site.

[0280] In certain examples, the step 2104 comprises training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm. The training data can include the modifier library of the data processing module 114. The identification machine learning model can receive the input with the description and output normalized data based on the analyzed data being coordinated to the matched anatomic site. Nonlimiting examples for the machine learning algorithms includes span categorization-based algorithms, range categorization-based algorithms, or other similar algorithms, or combinations thereof.

[0281] The step 2106 can include presenting the output on the GUI 1 12 on the display 106. In certain examples the output is a digital file or a printed physical document. In certain examples, the output is sent to the output device 110 or used as a training data for identification machinelearning model. The output can include a path that is selected, coordinated, targeted, described, translated, visualized, mapped, normalized, and / or encoded based on its spatial location or relationship, data-based location or relationship, context (e.g., surface vs. deep, point vs. region), directional location or relationship, or combination thereof.

[0282] In certain embodiments, the step 2104 can include analyzing the description for other data such as symptoms (e.g., pain). The other data can be analyzed and processed in communication with modules, e.g. the data processing module 114 on the medium 104 and the step 2106 can include generating diagnostic recommendations or considerations and / or their encodings (e.g. suggest a diagnosis of “acute appendicitis K35.8O”)) and also to generate follow up questions (e.g. by the generation module 116 such as what is the quality and severity of the pain? Is it sharp? Does it radiate or travel anywhere? Is it worse with a deep breath?) for the output. In certain examples, the output includes laterality and other modifiers in any desired order.

[0283] Research Experiment

[0284] A research experiment was conducted using the systems and methods described herein. The systems and methods were able to accurate plot anatomic sites based on a received input having a description of said anatomic site. Three humans were asked to plot the same anatomic sites based on the same received input. One human, who was experienced healthcare provider (PA / NP), got 3 / 3 "correct" in about 2 mins, 45 seconds. Another human, a less trained medical assistant (pre-PA school), got 2 / 3 correct in about 4 minutes. A further human, a doctorate level person with no medical training, got 0 / 3 correct. This demonstrates that described systems and methods can be used by a user to not only plot anatomic sites accurately, but also without the user having to have medical expertise.

[0285] In one embodiment, the system 100 or method for mapping, targeting, organizing, labeling, coordinating, classifying, and organizing data comprises: receiving an input, from the input device 108, having health data, wherein the input is text-based, visual-based, audio-based, and / or based on an interaction with the anatomic representation; processing the input to generate processed health data, the processed health data including a procedure, a diagnosis, a name of an anatomic site, and / or a description of an anatomic site; rendering, on the display 106, a marked anatomic site on the anatomic representation that is based on the processed health data, or an isolated anatomic representation having a marked anatomic site that is based on the processed health data; selectively rendering, on the display 106, a mirror image of the anatomic representation with the marked anatomic site or the isolated anatomic representation with the marked anatomic site based on a user preference or context; selecting one of a plurality of templates, each of the templates having one or more fields; populating one of the fields with the anatomic representation with the marked anatomic site or the isolated anatomic representation withthe marked anatomic site to generate a populated selected template; and generating a health record including the populated selected template.

[0286] In certain embodiments, the anatomic representation includes a plurality of predefined anatomic sites. In certain embodiments, the input is captured, recorded, or live audio (e.g., ambient listening through a microphone) that contains verbal descriptions of an anatomic site, procedure, order, diagnosis, treatment, recommendation, or other data. In certain embodiments, the audio input is processed along with the input from a physical paper form, the input device 108 marking on a physical paper form, or with the input from the input device 108 (e.g., mouse, touchscreen) interaction with a digital form or the GUI 112 rendered on the display 106. In certain embodiments, the audio input is filtered by the processor 102 to ignore background noise, music, beeps, and other distracting sounds to categorize the context, person, place, timing, and data into the system 100 in relation to another input such as a paper map or other form input. The processed audio and form input generate processed health data. As one non-limiting example, verbal interaction with the system 100 can be listened to by a transcribing service, or a handwritten or typed data can be entered into I onto forms, and correctly categorized with diagnostic, procedural, anatomy, and other data. The service in this non-limiting embodiment enabled by the system 100 could be managed by artificial intelligence. In certain embodiments, input can be ambient conversations such as those between a physician and a patient, captured through the input device 108 such as a microphone as one non-limiting example, and the system 100 can coordinate and organize data to the correct locations in a template, to the correct anatomic site, to the correct diagnosis, to the correct patient chart, and / or to the correct procedure as non-limiting examples. In certain embodiments, the coordinated data becomes visible and mapped on a shadow chart or digital chart.

[0287] In certain embodiments, paths, path groups, vertices, vertice groups, planes, plane groups, axes, shapes, bounding boxes, polygons, or coordinate collections (referred to synonymously as “a path” or “paths” throughout this disclosure, except where specified or contrasted to be different in the same sentence) are proportionally and progressively segmented and encoded to generate a coordination system that does not require numbers to describe a position within a path. In certain embodiments, paths are related to maps of anatomy, physical objects, floor plans, geographic maps, or spatial maps. In certain embodiments, each proportional segment or group of segments can have an optionally defined custom axis, direction plane, median, center, centroid, relationship, offset or coordinate system.

[0288] In certain embodiments, paths and planes can be different and can have different coordinates, axial definitions, segmentation boundaries, path rotations, axial rotations, path scales, path rotations, identifiers, modifiers, encodings, directions, relationships, thicknesses, densities,colors, highlights, patterns, fills, opacities, or properties or combinations thereof.

[0289] In certain embodiments, a point or a path is related to deviation from a corner, point, centroid, or a center of a path to generate a direction in relation to other paths, in relation to itself, or combinations thereof. In certain embodiments, the generated direction in relation to other paths is represented as a numerical weight to represent the direction on an axis. In certain embodiments, the generated direction data is processed in relation to other data, such as time points or body surface area as non-limiting examples, to generate new processed data as velocity data. A nonlimiting practical application of the processed data would be to generate a visualization illustrating the velocity and direction of change of a disease. For example, to show visually (e.g., on the display 106) and numerically how a disease progresses over time and what body surface area is affected by different morphologies at different time points. Such analysis and data processing has not been possible in the past due to the multidimensional nature of the data. In certain embodiments, the processor 102 is a quantum processor that is designed to better handle multidimensional data. In certain embodiments, the data is further processed alongside the data processing module 114 to generate data predictions, recommendations, or conclusions. A nonlimiting prediction, recommendation, or conclusion example is described as: “when this diagnosis affects body locations X, Y, and Z with at least 30% body surface area involved with the morphology of erythema, intervention with Drug A should be considered. Intervention with Drug A reduces the probability of progression of the morphology erythema to sclerosis by 80% and reduces the probability of disease spread by 40%. With prior systems, such predictions, recommendations, or conclusions with multidimensional data have not been possible with traditional processors or human analysis. In certain embodiments wherein images are analyzed for properties like morphology or body surface area or intensity as non-limiting examples, human bias and multiple observer bias can lead to more inconsistencies when compared to a single trained model processing the analysis.

[0290] In certain embodiments, a path is related to another path by using translated names for each path and a custom axis. In certain embodiments, the custom axis is the same in the paths being compared; and in certain embodiments the custom axis is different in the paths being compared so an alternate axis, such as a custom axis associated with a direction plane, is used to describe the relationship between the paths or points within the paths. A plurality of axes, directions, vectors, path descriptions, distances, coordinates, weights, and magnitudes are defined and stored in the medium 104 and processed with the processor 102 to generate and / or analyze relationship descriptions.

[0291] In certain embodiments, multimedia inputs automatically receive an embedded label containing a visual description, generated or selected visualization, language description, textdescription, order, pin, path coloring, custom axis, coordinates, proportionally segmented encoding, coded description, other data, or combinations thereof in multimedia. In certain embodiments, the embedded label contains a hyperlink stored within the file on the medium 104, a code such as a QR code, URL, bar code, text code, symbolic code, language based description, alphanumeric code, or proportionally segmented encoding, and a code regenerates an anatomic representation, visualization, map point, highlight, coloring, cross-code, shape, path, pin, order, avatar, map, map segment, path, library, target, translation, description, and / or other associated data such as but not limited to diagnosis, morphology, symptoms, tags, symbols. In certain embodiments, regeneration of the anatomy representation and other data pulls and relates visualizations from a visual library stored on the medium 104, and processes other data to generate instructions to process and manipulate the anatomy representation. In certain embodiments the hyperlink can replot, re-select, regenerate, organize, coordinate, visualize, or combinations thereof information on a map, avatar, or combination thereof. Non-limiting examples of manipulation of the anatomy representation include adding a pin, a pin order, a pin color, a pin description, pin coordinates, and path color shading to the anatomy representation. In certain embodiments, the embedded label has a standardized layout and the system 100 can analyze and manipulate the embedded label, for example, to redact information contained in the embedded label. In certain embodiments, volumetric and spatial analysis and measurements are enabled by the system 100 from language, code, or symbols describing anatomic sites, distributions, modifiers, or combinations thereof of anatomic sites.

[0292] In certain embodiments, systems and methods for three-dimensional (3D) hierarchical model projection to two-dimensional (2D) image assets has three-dimensional mesh objects for each segmented anatomic site, arranged into collections and with hierarchical relationships. In certain embodiments, standardized rotations, views, visibilities, layers, and zoom levels are defined in the medium 104 for the 3D models. In certain embodiments, customized axes are applied to the paths when transforming the paths by projecting from 3D to 2D; or when transforming the paths by projecting from 2D to 3D. As mentioned above, the paths refer to other synonymous matter like planes, path groups, coordinates, shapes, polygons, vertices, etc.

[0293] In certain embodiments, a visual library of language-vision pairs is stored in the medium 104 in communication with the data processing module 114 and is used to coordinate training data for processing through machine learning, neural networks, and artificial intelligence. The processed data generates, via the generation module 116, coordinates, maps, planes, paths, labels, and translations to describe and visualize relationships on new images. In certain embodiments, the visual library is a collection of paths highlighted on anatomy illustrations. In certain embodiments, the visual library is a collection of language-vision pairs describing visual findingsunder a microscope for pathology slides with the correlating digital slide or slide image, with coordination to diagnosis information such as diagnosis codes. In certain embodiments, directional centers are applied to physical objects or spatial objects input into or stored within the system 100, with non-limiting examples being floor plans, cars, boats, microscopic slides, videos, illustrations, images, 3d models, and other data. Such objects can be animated or inanimate. In certain embodiments, the fourth dimension of time is added to show changes over time in relation to the directional centers. In certain embodiments, semantic segmentation can also coordinate spatial information of other relevant physical objects, such as the slide number and slice location and relevant finding location on a pathology slide, thus describing the exact position of the relevant finding for the pathologic diagnosis features. In certain embodiments, progressive semantic segmentation can describe progressive and proportional segmentation with natural language, as input, output, or combinations thereof.

[0294] In certain embodiments, inputs are mixtures of audio like ambient conversations (e.g. detected with the input device 108, e.g., like a microphone, processed with the processor 102, and stored in a medium 104), interactions detected by physical sensors (e.g. eye-tracking, spatial sensors, mouse or keyboard interaction with the GUI 112, sensor interaction of a electronically enabled stylus or pencil with a piece of paper or the display 106, or touchscreen interaction with the display 106), or computer vision detection of markup on paper forms. In certain embodiments, data are extracted from the plurality of inputs, processed by the processing module, and coordinated into a plurality of templates to generate organized, translated, and processed data.

[0295] In certain embodiments, representations of physical objects or anatomy are displayed on a screen and aligned with nearby physical objects through sensors (e.g., camera sensor, Light Detection and Ranging (LIDAR), eye tracking as non-limiting examples) as input in communication with the processor 102 to apply custom axes and proportional progressive segmentation. In certain embodiments, eye tracking on physical objects is an example of an input that can, through communication with the processor 102 and the system 100, coordinate, plot, highlight, or target points or areas of interest on the physical objects with points on 2D or 3D representations of the same or similar objects, such as an anatomic map, anatomic illustration (e.g. from a library of templates), or anatomic avatar as non-limiting examples. In certain embodiments, similar objects mean a point or region of human anatomy on a line art illustration from a library that contains a plurality of templates and maps. In certain embodiments, the coordinated, plotted, highlighted, or targeted points or areas of interest are described in coded, linguistic, symbolic, or mixed components of language. In certain embodiments, for example during a surgery when the user is a physician with gloves on as a non- limiting example, and the camera is a touch screen, a gesture near the touch screen but not touching it is detected by the inputdevice 108 (e.g. a camera sensor) and interacts with the avatar, form, map, record, or other element of the GUT 1 12 without actually touching the touchscreen. Non-limiting example gestures include pinch-to-zoom, 2-finger pan, pointing, pointing plus eye movements, etc. Such example embodiments have a practical application of interacting with the input device 108 without compromising the sterile field of surgery.

[0296] In certain embodiments, the input device 108 is a touch screen that has any combination of embedded sensors, light sources (e.g. laser light, spectral light, ultraviolet light, infrared light, polarized light, etc.), polarizers, filters, lenses, cameras, lasers, rulers, embedded color gradients, Light Detection and Ranging (LIDAR), processor, wireless communication module, internal storage, communication port, battery, graphical processor unit (GPU), microphone, speaker, physical button, contact microscopy, high resolution image sensor, and / or a charging port.

[0297] Certain embodiments of the apparatuses and methods disclosed herein are defined in the above examples. It should be understood that these examples, while indicating particular embodiments of the invention, are given by way of illustration only. From the above discussion and these examples, one skilled in the art can ascertain the essential characteristics of this disclosure, and without departing from the spirit and scope thereof, can make various changes and modifications to adapt the devices and methods described herein to various usages and conditions. Various changes may be made, and equivalents may be substituted for elements thereof without departing from the essential scope of the disclosure. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the disclosure without departing from the essential scope thereof.

Claims

CLAIMSWhat is claimed is:

1. A method for generating a segmented output having a segmented input, the method comprising: receiving an input from a user; identifying a landmark within the input; segmenting the input into a plurality of segments to form the segmented input; generating a path or a path group based on the landmark; encoding the path or the path group based on the plurality of segments; and generating the segmented output having the segmented input with the encoded path or path group.

2. The method of claim 1 , wherein the step of identifying a landmark within the input comprises training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library.

3. The method of claim 1, further comprising coordinating the segmented output with other coordinate systems.

4. A system for generating an output having a segmented input, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, from the input device, an input from a user; identify, using the data processing module, a landmark within the input; segment, using the data processing module, the input into a plurality of segments toform the segmented input; generate, using the data processing module, a path or a path group based on the landmark; encode, using the data processing module, the path or the path group based on the plurality of segments to form an encoded path or encoded path group; and generate, using the generation module, the output having the segmented input with the encoded path or the encoded path group.

5. A method for detecting a reference point or reference area on a physical object, the method comprising: aligning the reference point or reference area to spatial data, custom axis data, database data, or to detected features, wherein the detected features include topology, morphology, diagnosis, color, counts, surface area, or combinations thereof; and calculating and encoding a point or an area in relation to the detected and aligned reference point or reference area with progressive and proportional segmentation.

6. A system for detecting a reference point or reference area on a physical object, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: align, using the data processing module, the reference point or reference area to spatial data, custom axis data, database data, or to detected features, wherein the detected features include topology, morphology, diagnosis, color, counts, surface area, or combinations thereof; and calculate and encode, using the data processing module, the point or area in relation to the detected and aligned reference point or reference area with progressive and proportional segmentation.

7. A method for generating an embedded output, the method comprising: receiving an input from a user; processing the input to form processed input; and applying an embedded label based on the processed input to the input to generate the embedded output.

8. The method of claim 7, wherein the step of processing the input to form processed input comprises identifying and recording medical information in the input; selectively generating a description of the input based on the medical information; and selectively generating visualizations based on the medical information.

9. The method of claim 8, wherein the step of processing the input to form processed input comprises training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library.

10. The method of claim 9, wherein the embedded label includes medical information, including the description of the medical information, the visualizations based on the medical information, or combinations thereof.

11. The method of claim 7, wherein the embedded label includes an encoded portion.

12. The method of claim 7, wherein the step of applying an embedded label based on the processed input to the input to generate the embedded output includes depersonalizing the medical information to generate depersonalized medical information, and wherein the embedded label includes the depersonalized medical information.

13. A system for generating an embedded output, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; andan input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from a user; processing, using the data processing module, the input to form processed input; and applying, using the generation module, an embedded label based on the processed input to the input to generate the embedded output.

14. A method for regenerating decoded data, the method comprising: scanning an embedded output having an embedded label to generate decoded data; and regenerating the decoded data.

15. The method of claim 14, wherein the embedded label includes an encoded portion.

16. The method of claim 14, wherein the step of scanning an embedded output having an embedded label to generate processed data includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library.

17. The method of claim 14, further comprising a step of authenticating a user before the step of regenerating processed data, wherein if the user unauthenticated, the decoded data only includes depersonalized medical information, and if the user is authenticated, the decoded data includes the medical information without being depersonalized.

18. A system for regenerating decoded data, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: scan, using the data processing module, an embedded output having an embeddedlabel to generate decoded data; and regenerating, using the generation module, the decoded data.

19. A method for detecting and reconciling spatial errors within an input, the method comprising: receiving an input from a user, wherein the input includes a marker on an anatomic representation; determining if the marker includes a spatial error; if the marker includes the spatial error, generating an output based on a rectified input; and if the marker does not include the spatial error, generating an output based on the input.

20. The method of claim 19, wherein the step of determining if the marker includes a spatial error includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library.

21. A system for detecting and reconciling spatial errors within an input, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from a user, wherein the input includes a marker on an anatomic representation; determine if the marker includes a spatial error; if the marker includes the spatial error, generate an output based on a rectified input; and if the marker does not include the spatial error, generate an output based on the input.

22. A method for generating an output based on non-semantic similarity, the method comprising: receiving an input from a user to identify paths and at least one diagram in a library of diagrams and paths, wherein the input includes an uncoordinated component, wherein the uncoordinated component is a coded, language-based, symbol-based, or mixed description, and wherein the paths include at least one path, path segment, or path group; calculating the non-semantic similarity between the input and other paths in the library, wherein the non-semantic similarity includes coordinate similarity, positional similarity, or spatial similarity; optionally, calculating the non-semantic similarity on new visualizations by overlaying or underlaying and aligning other paths in the library with anatomic features present in the diagram; and generating maps, avatars, illustrations, or visualizations based on the non-semantic similarity as outputs.

23. A system for generating an output based on non-semantic similarity, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from a user to identify paths and at least one diagram in a library of diagrams and paths, wherein the input includes an uncoordinated component, wherein the uncoordinated component is a coded, language-based, symbolbased or mixed description, and wherein the paths include at least one path, path segment, or path group; calculate, using the data processing module, the non-semantic similarity between the input and other paths in the library, wherein the non-semantic similarity includes coordinate similarity, positional similarity, or spatial similarity; optionally, calculate the non-semantic similarity on new visualizations by overlaying or underlaying and aligning other paths in the library with anatomic features present inthe diagram; and generate maps, avatars, illustrations, or visualizations based on the non-semantic similarity as outputs.

24. A method for improving reproduction and generation of anatomic site visualizations, description, maps, and relationships, the method comprising: receiving at least one coordinate-based path, path segment, or path group linked to at least one anatomic representation identified with the input, and an input serving as a reference to a map-diagram pair; rendering at least the reference map-diagram pair on a display; selectively rendering, additional data in the input related to the map-diagram pair on the display; and selectively generating new maps, images, avatars, relationships, and descriptions based on coordinate similarity, positional similarity, or spatial similarity regardless of semantic similarity.

25. A system for improving reproduction and generation of anatomic site visualizations, description, maps, and relationships, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, at least one coordinate-based path, path segment, or path group linked to at least one anatomic representation identified with the input, and the input serving as a reference to a map-diagram pair; render, using the processor, at least the reference map-diagram pair on the display; selectively render, using the processor, additional data in the input related to the mapdiagram pair on the display; and selectively generate, using the generation module, new maps, images, avatars, relationships, and descriptions based on coordinate similarity, positional similarity, orspatial similarity regardless of semantic similarity.

26. A method for generating a description of a plurality of markers on an anatomic representation, the method comprising: receiving an input from a user, wherein the input includes the plurality of markers on the anatomic representation; determining a spatial relationship between each of the plurality of markers; and generating a description of the input, wherein the description of the input includes a description of the spatial relationship between each of the plurality of markers or a visualization of the plurality of the markers with the description of the spatial relationship.

27. The method of claim 26, wherein the step of determining the spatial relationship between each of the plurality of markers includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library.

28. A system for generating a description of a plurality of markers on an anatomic representation, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from a user, wherein the input includes the plurality of markers on the anatomic representation; determine, using the data processing module, a spatial relationship between each of the plurality of markers; and generate, using the generation module, a description of the input, wherein the description of the input includes a description of the spatial relationship between each of the plurality of markers or a visualization of the plurality of the markers with the description of the spatial relationship.

29. A method for generating a visualization of a global period of a procedure or a diagnosis, the method comprising: receiving an input from a user, wherein the input includes a record of a patient having the procedure or the diagnosis related to the patient; determining one or more anatomic sites associated with the procedure or the diagnosis; determining the global period of the procedure or diagnosis; and generating the visualization of the global period of the procedure or diagnosis.

30. The method of claim 29, wherein the step of determining the one or more anatomic sites associated with the procedure or the diagnosis includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a library of procedures and diagnoses.

31. The method of claim 29, wherein the step of determining the global period of the procedure or diagnosis includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a library of procedures and diagnoses.

32. The method of claim 29, wherein the step of generating the visualization of the global period of the procedure or diagnosis includes generating the visualization which includes an anatomic representation having the anatomic sites affected by the procedure or diagnosis with indicia in each anatomic site showing whether the site is in the global period.

33. A system for generating a visualization of a global period of a procedure or a diagnosis, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to:receive, using the input device, an input from a user, wherein the input includes a record of a patient having the procedure or the diagnosis related to the patient; determine, using the data processing module, one or more anatomic sites associated with the procedure or the diagnosis; determine, using the data processing module, the global period of the procedure or diagnosis; and generate, using the generation module, the visualization of the global period of the procedure or diagnosis.

34. A method for determining a billing code for a procedure or diagnosis, the method comprising: receiving an input from a user, wherein the input includes a procedure or the diagnosis related to a patient; determining one or more anatomic sites associated with the procedure or the diagnosis; determining the billing code based on the procedure or diagnosis and the one or more anatomic sites associated with the procedure or the diagnosis; and generating an output having the billing code for the procedure or diagnosis.

35. The method of claim 34, wherein the step of determining the one or more anatomic sites associated with the procedure or the diagnosis includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a library of procedures and diagnoses.

36. The method of claim 34, wherein the step of determining the billing code based on the procedure or diagnosis and the one or more anatomic sites associated with the procedure or the diagnosis includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a library of billing codes.

37. The method of claim 34, wherein the step of generating an output having the billing code for the procedure or diagnosis includes generating a justification for selecting the higher or lower reimbursing code in natural language based on the billing code matched with the procedure or diagnosis in the input and the anatomic sites affected by the procedure or diagnosis.

38. A system for generating a visualization of a global period of a procedure or adiagnosis, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from a user, wherein the input includes a procedure or the diagnosis related to a patient; determine, using the data processing module, one or more anatomic sites associated with the procedure or the diagnosis; determine, using the data processing module, a billing code based on the procedure or diagnosis and the one or more anatomic sites associated with the procedure or the diagnosis; and generate, using the generation module, an output having the billing code for the procedure or diagnosis.

39. A method for verifying a billing code for a procedure or diagnosis, the method comprising: receiving an input from a user, wherein the input includes a billing code and the one or more anatomic sites affected by the procedure or the diagnosis; determining the one or more anatomic sites covered by the billing code; determining whether the one or more anatomic sites covered by the billing code matches one or more anatomic sites affected by the procedure or the diagnosis; if the one or more anatomic sites covered by the billing code does not match the one or more anatomic sites affected by the procedure or the diagnosis, determining a correct billing code for the one or more anatomic sites affected by the procedure or the diagnosis to generate a verified billing code based on the correct billing code; if the one or more anatomic sites covered by the billing code does match the one or more anatomic sites affected by the procedure or the diagnosis, generate the verified billing code based on the billing code of the input; and generating an output, wherein the output includes the verified billing code.

40. The method of claim 39, wherein the step of determining the one or more anatomic sites covered by the billing code includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a library of billing codes.

41. The method of claim 39, wherein the step of determining a correct billing code for the one or more anatomic sites affected by the procedure or the diagnosis to generate a verified billing code based on the correct billing code includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a library of billing codes.

42. A system for verifying a billing code for a procedure or diagnosis, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from a user, wherein the input includes a billing code and one or more anatomic sites affected by the procedure or the diagnosis; determine, using the data processing module, the one or more anatomic sites covered by the billing code; determine, using the data processing module, whether the one or more anatomic sites covered by the billing code matches the one or more anatomic sites affected by the procedure or the diagnosis; if the one or more anatomic sites covered by the billing code does not match the one or more anatomic sites affected by the procedure or the diagnosis, determine, using the data processing module, a correct billing code for the one or more anatomic sites affected by the procedure or the diagnosis to generate a verified billing code based on the correct billing code;if the one or more anatomic sites covered by the billing code does match the one or more anatomic sites affected by the procedure or the diagnosis, generate, using the data processing module, the verified billing code based on the billing code of the input; and generate, using the generation module, an output, wherein the output includes the verified billing code.

43. A method for encoding a medical visualization into an encoded string, the method comprising: rendering the medical visualization on a display, wherein the medical visualization includes an anatomic representation having a plurality of predefined anatomic sites and at least one of the predefined anatomic sites includes a marker; receiving instructions from a user to encode the medical visualization into the encoded string; and generating an output having the encoded string, wherein the encoded string includes an anatomic site identification portion, a laterality portion, a description of a marker portion, an anatomic representation identification portion, a deviation x-axis portion, a deviation y-axis portion, an order type portion, and an order position portion.

44. The method of claim 43, further comprising a step of the user disposing a marker on at least one of the predefined anatomic sites prior to the step of rendering the medical visualization on the display.

45. A system for encoding a medical visualization into an encoded string, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: render, using the processor, the medical visualization on the display, wherein the medical visualization includes an anatomic representation having a plurality ofpredefined anatomic sites and at least one of the predefined anatomic sites includes a marker; receive, using the input device, instructions from a user to encode the medical visualization into the encoded string; and generate, using the generation module, an output having the encoded string, wherein the encoded string includes an anatomic site identification portion, a laterality portion, a description of a marker portion, an anatomic representation identification portion, a deviation x-axis portion, a deviation y-axis portion, an order type portion, and an order position portion.

46. A method for decoding an encoded string into a medical visualization, the method comprising: receiving an encoded string from a user; and generating an output having the medical visualization based on the encoded string, wherein the encoded string includes an anatomic site identification portion, a laterality portion, a description of a marker portion, an anatomic representation identification portion, a deviation x- axis portion, a deviation y-axis portion, an order type portion, and an order position portion.

47. The method of claim 46, wherein the step of generating an output having the medical visualization based on the encoded string includes determining the anatomic representation based on the anatomic representation identification portion; determining the anatomic site where the marker is disposed within based on the anatomic site identification portion; determining the laterality modifier that describes the position of the anatomic site relative to the anatomic representation based on the laterality portion; determining the description of the marker based on the description of the marker portion; determining modifiers based on the modifier portion; determining prefixes based on the prefix portion; determining suffixes based on the suffix portion; determining the deviation in the x-axis based on the deviation x-axis portion; determining the deviation in the y-axis based on the deviation y-axis portion; determining the deviation in the y-axis based on deviation z-axis portion; determining the axial definitions based on axial definition portion; determining the angle of interpretation for each axis, a rotation of a path, plane, custom axis, or combinations thereof based on the angle portion; determining the order type based on the order type portion; determining the order type position based on the order type position portion; determining the description of the central zone based on the central zone portion; determining the deviation in time based on the time deviation portion; determining any synonyms based on the synonym portion; or combinations thereof.

48. A system for decoding an encoded string into a medical visualization, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an encoded string from a user; and generate, using the generation module, an output having the medical visualization based on the encoded string, wherein the encoded string includes an anatomic site identification portion, a laterality portion, a description of a marker portion, an anatomic representation identification portion, a deviation x-axis portion, a deviation y-axis portion, an order type portion, and an order position portion.

49. A method for generating a spatial description for a marker on an anatomic representation, the method comprising: rendering an anatomic representation on a display, wherein the anatomic representation includes a plurality of predefined anatomic sites, a plurality of predefined direction planes, or combinations thereof, wherein each of the direction planes overlap one or more of the predefined anatomic sites; receiving an input from a user, wherein the input includes a name of anatomic site, a description of the anatomic site, a procedure for the anatomic site, a diagnosis for the anatomic site, or combinations thereof; rendering a marker on the anatomic representation based on the anatomic site of the input on the display; determining the spatial description of the marker based on a spatial relationship of the marker with an overlapping direction plane of the predefined direction planes, an adjacent direction plane of the predefined direction planes, or combinations thereof; and generating an output having the spatial description of the marker.

50. The method of claim 49, wherein the step of rendering a marker on the anatomic representation based on the anatomic site of the input includes a step of processing the input to determine the anatomic site of the input.

51. The method of claim 50, wherein the step of processing the input to determine the anatomic site of the input includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library.

52. The method of claim 49, wherein the anatomic representation includes one or more velocity centers and the input includes temporal data, and wherein the temporal data includes the date of analysis / patient data capture and a change in a position of a condition across one or more anatomic sites.

53. The method of claim 52, further comprising a step of determining the tempo or velocity of a condition progression based on a direction of the condition relative to one or more the direction planes, one or more velocity centers, the change in the position of a condition, or combinations thereof.

54. The method of claim 53, further comprising a step of generating a prediction matrix to capture, analyze, research, and predict progression of health data over time with velocity centers and direction planes.

55. A system for decoding an encoded string into a medical visualization, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: render, using the processor, an anatomic representation on the display, wherein theanatomic representation includes a plurality of predefined anatomic sites, a plurality of predefined direction planes, or combinations thereof, wherein each of the direction planes overlap one or more of the predefined anatomic sites; receive, using the input device, an input from a user, wherein the input includes a name of anatomic site, a description of the anatomic site, a procedure for the anatomic site, a diagnosis for the anatomic site, or combinations thereof; render, using the processor, a marker on the anatomic representation based on the anatomic site of the input on the display; determine, using the data processing module, a spatial description of the marker based on a spatial relationship of the marker with an overlapping direction plane of the predefined direction planes, an adjacent direction plane of the predefined direction planes, or combinations thereof; and generate, using the generation module, an output having the spatial description of the marker.

56. A method for capturing, analyzing, researching, and predicting progression of health data, the method comprising: receiving an input having health data, wherein the input is text-based, visual-based, audio-based, and / or based on an interaction with an anatomic representation; capturing data related to time / temporal, anatomy, diagnosis, morphology, or other characteristics in relation to directional centers or direction planes; and processing the captured data into categories and context.

57. A system for capturing, analyzing, researching, and predicting progression of health data, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input having health data, wherein the input is text-based, visual-based, audio-based, and / or based on an interaction with an anatomic representation; capture, using the data processing module, data related to time / temporal, anatomy, diagnosis, morphology, or other characteristics in relation to directional centers or direction planes; and process, using the data processing module, the captured data into categories and context.

58. A method for estimating a surface area of a region of interest, the method comprising: receiving instructions from a user to estimate the surface area of the region of interest; determining a number of anatomic sites within the region of interest; determining an estimation of the surface area of the region of interest based on the number of anatomic sites within the region of interest; and generating an output with the estimation of the surface area of the region of interest.

59. The method of claim 58, wherein the step of determining a number of anatomic sites within the region of interest includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library.

60. The method of claim 58, wherein the step of determining an estimation of the surface area of the region of interest based on the number of anatomic sites within the region of interest includes adding together an average surface area of each anatomic site within the number of anatomic sites to generate an estimation of the surface area of the region of interest.

61. The method of claim 58, wherein the step of generating an output with the estimation of the surface area of the region of interest includes displaying the number of anatomic sites within the region of interest with indicia within each anatomic site to represent an average surface area of said anatomic site.

62. A system for estimating a surface area of a region of interest, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non-transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, instructions from a user to estimate the surface area of the region of interest; determine, using the data processing module, a number of anatomic sites within the region of interest; determine, using the data processing module, an estimation of the surface area of the region of interest based on the number of anatomic sites within the region of interest; and generate, using the generation module, an output with the estimation of the surface area of the region of interest.

63. A method for correlating mixed inputs, the method comprising: receiving a plurality of inputs from a user, wherein at least one of the inputs includes an audio component and at least another input includes a visual component; determining context between the audio component and the visual component; and generating an output having standardized data based on the context between the audio component and the visual component.

64. The method of claim 63, wherein the audio component includes medical information related to a shorthand for an unspecified anatomic site and the visual component includes a visual representation of the shorthand correlated to an anatomic site.

65. The method of claim 64, wherein the step of determining context between the audio component and the visual component includes a step of identifying the shorthand for the unspecified anatomic site in the audio component and a step of identifying the anatomic site correlated with the shorthand in the visual component.

66. The method of claim 65, wherein the step of identifying the shorthand for the unspecified anatomic site in the audio component includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learningalgorithm, wherein the training data includes a library of common shorthand terms.

67. The method of claim 66, wherein the step of identifying the anatomic site correlated with the shorthand in the visual component includes training, iteratively and / or recursively, the identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a visual library.

68. The method of claim 67, wherein the standardized data includes the medical information from the audio component with the anatomic site correlated with the shorthand.

69. A system for correlating mixed inputs, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, a plurality of inputs from a user, wherein at least one of the inputs includes an audio component and at least another input includes a visual component; determine, using the data processing module, context between the audio component and the visual component; and generate, using the generation module, an output having standardized data based on the context between the audio component and the visual component.

70. A method for filtering audio, the method comprising: receiving an input from a user, wherein the input includes audio; determining if the audio includes undesirable noise; if the audio includes undesirable noise, at least substantially removing the undesirable noise from the audio of the input; and generating an output having filtered audio, wherein the filtered audio is the audio with the undesirable noise substantially removed therefrom.71 . A system for filtering audio, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from a user, wherein the input includes audio; determine, using the data processing module, if the audio includes undesirable noise; if the audio includes undesirable noise, at least substantially remove, using the data processing module, the undesirable noise from the audio of the input; and generate, using the generation module, an output having filtered audio, wherein the filtered audio is the audio with the undesirable noise substantially removed therefrom.

72. A method for encoding a skeleton-based diagnosis or procedure into an encoded string, the method comprising: receiving an input from a user, wherein the input includes a diagnosis or procedure related to an anatomic region of a skeleton system, a laterality modifier of the anatomic region, whether the diagnosis or procedure involves an open or closed fracture, a fracture subtype, and a specific anatomy of the anatomic region where the diagnosis or procedure occurs; and generating an output having the encoded string, wherein the encoded string has a diagnosis or procedure portion, a laterality modifier portion, a fracture open or closed portion, a fracture subtype portion, and a specific anatomy portion.

73. A system for encoding a skeleton-based diagnosis or procedure into an encoded string, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executableinstructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input from a user, wherein the input includes a diagnosis or procedure related to an anatomic region of a skeleton system, a laterality modifier of the anatomic region, whether the diagnosis or procedure involves an open or closed fracture, a fracture subtype, and a specific anatomy of the anatomic region where the diagnosis or procedure occurs; and generate, using the generation module, an output having the encoded string, wherein the encoded string has a diagnosis or procedure portion, a laterality modifier portion, a fracture open or closed portion, a fracture subtype portion, and a specific anatomy portion.

74. A method for processing an input having health data, the method comprising: receiving an input having a description related to health data; analyzing the description for anatomic site names, anatomic site name synonyms, laterality, modifiers, magnitude modifiers, laterality synonyms, modifier synonyms, magnitude modifier synonyms, directional synonyms, or combinations thereof to generate normalized data; and generating an output based on the normalized data, wherein the output includes a path that is selected, coordinated, targeted, described, translated, visualized, mapped, normalized, and / or encoded based on its spatial location or relationship, data-based location or relationship, context, directional location or relationship, or combination thereof.

75. The method of claim 74, wherein the step of analyzing the description for anatomic site names, anatomic site name synonyms, laterality, modifiers, magnitude modifiers, laterality synonyms, modifier synonyms, magnitude modifier synonyms, directional synonyms, or combinations thereof to generate normalized data includes training, iteratively and / or recursively, an identification machine learning model using training data and a machine learning algorithm, wherein the training data includes a modifier library.

76. The method of claim 74, wherein the step of analyzing the description for anatomic site names, anatomic site name synonyms, laterality, modifiers, magnitude modifiers,laterality synonyms, modifier synonyms, magnitude modifier synonyms, directional synonyms, or combinations thereof to generate normalized data includes analyzing the description for other data, wherein the other data includes symptoms, and wherein the step of generating an output based on the normalized data includes generating diagnostic recommendations, considerations, encodings, and follow up questions, or combinations thereof.

77. A system for processing an input having health data, the system comprising: a processor; a medium in communication with the processor, wherein the medium is tangible, non- transitory, and computer readable; processor-executable instructions stored on the medium, the processor-executable instructions defining a mapping platform including a data processing module and a generation module; a display in communication with the medium; and an input device in communication with medium and display; wherein the mapping platform is configured to: receive, using the input device, an input having a description related to health data; analyze, using the data processing module, the description for anatomic site names, anatomic site name synonyms, laterality, modifiers, magnitude modifiers, laterality synonyms, modifier synonyms, magnitude modifier synonyms, directional synonyms, or combinations thereof to generate normalized data; and generate, using the generation module, an output based on the normalized data, wherein the output includes a path that is selected, coordinated, targeted, described, translated, visualized, mapped, normalized, and / or encoded based on its spatial location or relationship, data-based location or relationship, context, directional location or relationship, or combination thereof.

Images