System and method of facilitating improved patient recovery

Abstract

A surgical site infection (SSI) detection and evaluation system is disclosed that includes a denoising diffusion generative network (DDGN) configured to generate a plurality of surgical site images with a plurality of surgical site infection (SSI) classifications; and a surgeon digital twin neural network (SDTNN) trained using at least the plurality of surgical site images, patient data, and a source surgical site image database, the SDTNN being configured to determine a predicted clinician evaluation using at least the plurality of surgical site images, and a captured surgical site image with an SSI classification.

Description

Atty Ref. 94421.00216SYSTEM AND METHOD OF FACILITATING IMPROVED PATIENT RECOVERYCROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims the benefit of priority to U.S. Provisional Patent Application No. 63 / 693,655, filed on September 11 , 2024, the entire contents of which are incorporated herein by reference in their entirety.FIELD

[0002] This disclosure generally relates to computerized systems and methods to facilitate communication between different user types and improved patient recovery.BACKGROUND

[0003] A substantial portion of patients experience a post-discharge complication. Such complications can result in patient readmission as well as substantially increase near-term and long-term patient care costs. For example, average readmission costs to providers can be approximately $15,000 per patient with annual total costs of readmission estimated at approximately $41.3B. Further, surgical site infection (SSIs) are the leading cause of hospital readmissions, affecting about 4% of surgical patients and increasing hospitalization costs by over $20,000 per readmission. Such costs can include aspects such as provider visits after a procedure, follow-up procedures not previously planned, hospitalization, as well as additional and avoidable correspondence between care providers and patients.

[0004] Although SSIs significantly impact patient outcomes and healthcare costs, SSIs are among the most common preventable post-discharge (PD) complications and can be remedied often with early intervention. Consequently, there is increased financial pressure to prevent SSIs, with care providers often denying reimbursements for SSIs in recent years. Therefore, there is an urgent need for improved prevention through early detection.

[0005] The solution of this disclosure resolves these and other issues of the art.SUMMARY

[0006] In some examples, a computer-implemented method is disclosed that includes generating, using at least a denoising diffusion generative network (DDGN), a plurality of surgical site images with a plurality of classifications; and determining,Atty Ref. 94421.00216 using at least a surgeon digital twin neural network (SDTNN), the plurality of surgical site images, a captured surgical site image, and a surgical site infection (SSI) classification, a predicted clinician evaluation, the SDTNN trained using at least the plurality of surgical site images, patient data, and labeled surgical wound images.

[0007] In some examples, the computer-implemented method includes determining, using at least an SSI classifier trained on a source surgical site image database and the generated surgical site images, the SSI classification.

[0008] In some examples, the plurality of classifications includes SSI classifications.

[0009] In some examples, the computer-implemented method includes generating, using at least the DDGN, a plurality of surgical site images labeled with an SSI classification.

[0010] In some examples, the DDGN is trained using at least a source surgical site image database and labeled surgical wound images.

[0011] In some examples, the SDTNN is trained to predict a clinician evaluation, using at least the generated plurality of surgical site images, a source surgical site image database, and patient information and without clinician input.

[0012] In some examples, the SDTNN is trained continuously using at least the generated plurality of surgical site images, a source surgical site image database, and patient information.

[0013] In some examples, the computer-implemented method includes transmitting image capturing guidance to an image capturing system, prior to or during capturing of the captured surgical site image, in compliance with an image standard.

[0014] In some examples, a user computing device includes the image capturing system.

[0015] In some examples, the image standard is determined by an image capturing guidance network (ICGN) using at least a source surgical site image database and the generated plurality of surgical site images.

[0016] In some examples, the ICGN is trained using at least the source surgical site image database and the generated plurality of surgical site images.

[0017] In some examples, the image standard includes the captured surgical site image including a predetermined percent of the surgical site image.

[0018] In some examples, the image standard is based at least on focus, contrast, and depth of field.Atty Ref. 94421.00216

[0019] In some examples, the image capturing guidance is determined by applying random brightness, contrast, and affine transforms to an image that initially conforms with the image standard; outputting, using at least an image capturing system, an inverse transform at each deviation; filling in a background of the image, using at least an image generative model and as the inverse transform is output at each deviation; mapping the image back to the captured surgical site image; and analyzing an error between a prediction of the inverse transform generated by the image capturing system and an actual inverse transform.

[0020] In some examples, the computer-implemented method includes extracting data from the captured surgical site image prior to or during the determining the predicted clinician evaluation.

[0021] In some examples, the computer-implemented method includes determining, using at least the SDTNN and a determined SSI classification, a surgical site treatment protocol; and displaying information related to the surgical site treatment protocol in a visualization dashboard of a patient computer system and / or a healthcare provider computer system.

[0022] In some examples, the computer-implemented method includes upon determining a SSI classification, generating, using at least the SDTNN, one or more message recommendations; and displaying the one or more message recommendations in a visualization dashboard of a patient computer system and / or a provider computer system.

[0023] In some examples, a surgical site infection (SSI) detection and evaluation system is disclosed that includes a denoising diffusion generative network (DDGN) configured to generate a plurality of surgical site images with a plurality of surgical site infection (SSI) classifications; and a surgeon digital twin neural network (SDTNN) trained using at least the plurality of surgical site images, patient data, and a source surgical site image database, the SDTNN being configured to determine a predicted clinician evaluation using at least the plurality of surgical site images, and a captured surgical site image with an SSI classification.

[0024] In some examples, the SSI detection and evaluation system includes an SSI classifier trained on the plurality of surgical site images and labeled source surgical site image database, the SSI classifier configured to determine the SSI classification.

[0025] In some examples, the labels of the plurality of images define a latent space of the DDGN, and wherein the latent space of an infection label is traversed during theAtty Ref. 94421.00216 generating of surgical wound images to generate images with features corresponding to the labels.

[0026] In some examples, the SSI detection and evaluation system includes an image capturing guidance network (ICGN) configured to determine an image capturing guidance using at least source images and the generated plurality of surgical site images, prior to or during capturing of the captured surgical site image, in compliance with an image standard.

[0027] In some examples, the ICGN is trained using at least the plurality of surgical site images and the source surgical site image database.

[0028] In some examples, the ICGN is configured to guide a user using a user computing device to capture an image of a surgical site.

[0029] In some examples, the ICGN is configured to guide a user to capture the image based on image capturing guidance determined by applying brightness, contrast, and affine transforms to an image that initially conforms with an image standard; outputting, using at least an image capturing system, an inverse transform at each deviation; and mapping the image back to the captured SSI image.

[0030] In some examples, a clinician evaluation prediction system is disclosed that includes a computer system configured to implement an artificial neural network adapted to generate, using captured imaging data of a surgical site and a plurality of surgical wound images generated by a denoising diffusion generative network (DDGN) from a source surgical site image database, a surgeon digital twin neural network (SDTNN) trained to predict a clinician SSI evaluation using at least the plurality of surgical wound images, a captured surgical site image, and an SSI classification.

[0031] In some examples, the SSI classification is determined by an SSI classifier trained on the plurality of surgical site images and the source surgical site image database.

[0032] In some examples, the SDTNN is trained to predict the clinician SSI evaluation without clinician input.

[0033] In some examples, the DDGN is configured to generate the plurality of surgical wound images labeled with an SSI severity.

[0034] In some examples, labels of the plurality of surgical wound images define a latent space of the DDGN, and wherein the latent space of an infection label is traversed during the generating of the system generated surgical wound images to generate images with features corresponding to the labels.Atty Ref. 94421.00216

[0035] In some examples, the DDGN is configured to generate the surgical wound images with features corresponding to a plurality of risk labels.

[0036] In some examples, the DDGN is configured to vary the plurality of risk labels for the same input.

[0037] In some examples, a number of input images to the SDTNN is configured to accommodate any number of previously captured images to predict a risk label of the plurality of risk labels.

[0038] In some examples, the plurality of risk labels at least include a no infection risk label, a further remote monitoring required label, an in-person consultation required label, and a readmission required label.

[0039] In some examples, a system is disclosed that includes at least one memory storing instructions; and at least one processor executing the instructions to perform operations including generating, using at least a denoising diffusion generative network (DDGN), a plurality of surgical site images with a plurality of classifications; and determining, using at least a surgeon digital twin neural network (SDTNN), the plurality of surgical site images, a captured surgical site image, and an SSI classification, a predicted clinician evaluation, the SDTNN trained using at least the plurality of SSI images, patient data, and labeled surgical wound images.

[0040] In some examples, the operations include determining, using at least an SSI classifier trained on the plurality of surgical site images and labeled surgical wound images, the SSI classification.

[0041] In some examples, the operations include transmitting image capturing guidance to an image capturing system, prior to or during capturing of the captured surgical site image, in compliance with an image standard, wherein the image standard is determined by an image capturing guidance network (ICGN) using at least source images and the generated plurality of surgical site images, wherein the image capturing guidance is determined by applying random brightness, contrast, and affine transforms to an image that initially conforms with the image standard; outputting, using at least the image capturing system, an inverse transform at each deviation; filling in a background of the image, using at least an image generative model and as the inverse transform is output at each deviation; mapping the image back to the captured surgical site image; and analyzing an error between a prediction of the inverse transform generated by the image capturing system and an actual inverse transform.Atty Ref. 94421.00216

[0042] In some examples, the operations include determining, using at least the SDTNN and an SSI severity, a surgical site treatment protocol; and displaying information related to the surgical site treatment protocol in a visualization dashboard of a patient computer system and / or a healthcare provider computer system.

[0043] In some examples, the operations include upon determining the SSI classification is elevated, generating, using at least the SDTNN, one or more message recommendations; and displaying the one or more message recommendations in a visualization dashboard of a patient computer system and / or a provider computer system.

[0044] T o the accomplishment of the foregoing and related ends, certain illustrative aspects are described herein in connection with the following description and the appended drawings. These aspects are indicative, however, of but a few of the various ways in which the principles of the claimed subject matter may be employed and the claimed subject matter is intended to include all such aspects and their equivalents. Other advantages and novel features may become apparent from the following detailed description when considered in conjunction with the drawings.BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and further aspects of this invention are further discussed with reference to the following description in conjunction with the accompanying drawings, in which like numerals indicate like structural elements and features in various figures. The drawings are not necessarily to scale, emphasis instead being placed upon illustrating principles of the invention. The figures depict one or more implementations of the inventive devices, by way of example only, not by way of limitation.

[0046] FIG. 1 shows a workflow detailing the system and method of an example embodiment of this disclosure.

[0047] FIG. 2 shows a workflow detailing the system and method of an example embodiment of this disclosure according to an example of this disclosure.

[0048] FIG. 3 shows an example workflow for generating an image set by specifying corresponding severities according to an example of this disclosure.

[0049] FIG. 4 shows an example workflow for predicting severity from input images labeled with time stamps according to an example of this disclosure.Atty Ref. 94421.00216

[0050] FIG. 5 shows an example workflow according to an example of this disclosure.

[0051] FIG. 6 shows an example workflow according to an example of this disclosure.

[0052] FIG. 7 shows an example workflow for training aspects of systems and methods according to an example of this disclosure.

[0053] FIG. 8 shows an example workflow for generating one or more predictive outputs according to an example of this disclosure.

[0054] FIG. 9 is a computer architecture diagram showing a general computing system for implementing aspects of the present disclosure in accordance with one or more embodiments described herein.

[0055] FIG. 10 depicts a schematic overview of an example method of this disclosure.DETAILED DESCRIPTION

[0056] Although example embodiments of the disclosed technology are explained in detail herein, it is to be understood that other embodiments are contemplated. Accordingly, it is not intended that the disclosed technology be limited in its scope to the details of construction and arrangement of components set forth in the following description or illustrated in the drawings. The disclosed technology is capable of other embodiments and of being practiced or carried out in various ways.

[0057] It must also be noted that, the term “exemplary” is used in the sense of “example,” rather than “ideal.”

[0058] It must also be noted that, as used in the specification and the appended claims, the singular forms “a,” “an” and “the” include plural referents unless the context clearly dictates otherwise.

[0059] By “comprising” or “containing” or “including” it is meant that at least the named compound, element, particle, or method step is present in the composition or article or method, but does not exclude the presence of other compounds, materials, particles, method steps, even if the other such compounds, material, particles, method steps have the same function as what is named.

[0060] Relative terms, such as “about,” “substantially,” or “approximately” are used to include small variations with specific numerical values (e.g., + / - x%,), as well asAtty Ref. 94421.00216 including the situation of no variation (+ / -0%). In various embodiments, the numerical value x is less than or equal to 10 - e.g., less than or equal to 5, to 2, to 1 , or smaller.

[0061] In describing example embodiments, terminology will be resorted to for the sake of clarity. It is intended that each term contemplates its broadest meaning as understood by those skilled in the art and includes all technical equivalents that operate in a similar manner to accomplish a similar purpose. It is also to be understood that the mention of one or more steps of a method does not preclude the presence of additional method steps or intervening method steps between those steps expressly identified. Steps of a method may be performed in a different order than those described herein without departing from the scope of the disclosed technology. Similarly, it is also to be understood that the mention of one or more components in a device or system does not preclude the presence of additional components or intervening components between those components expressly identified.

[0062] As used herein, the term “computing system” is intended to include standalone machines or devices and / or a combination of machines, components, modules, systems, servers, processors, memory, detectors, user interfaces, computing device interfaces, network interfaces, hardware elements, software elements, firmware elements, and other computer-related units. By way of example, but not limitation, a computing system can include one or more of a general-purpose computer, a specialpurpose computer, a processor, a portable electronic device, a portable electronic medical instrument, a stationary or semi-stationary electronic medical instrument, or other electronic data processing apparatus.

[0063] As used herein, the term “database” is intended to include a collection of indexed data stored on a computer readable medium. The term “data store” as referred to herein is intended to include the computer readable medium on which the databases are stored. By way of example and not limitation, data in the database can include numerical values, textual values, computational representation of physical objects. Various data can be linked together or otherwise indexed. By way of example and not limitation, data in the database can be represented as an indexed matrix.

[0064] As used herein, the term “dataset” is intended to include information that can be provided to a computing system in a computer readable format.

[0065] As used herein, the terms “component,” “module,” “system,” “server,” “processor,” “memory,” and the like are intended to include one or more computer- related units, such as but not limited to hardware, firmware, a combination of hardwareAtty Ref. 94421.00216 and software, software, or software in execution. For example, a component may be, but is not limited to being, a process running on a processor, an object, an executable, a thread of execution, a program, and / or a computer. By way of illustration, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and / or thread of execution and a component may be localized on one computer and / or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures stored thereon. The components may communicate by way of local and / or remote processes such as in accordance with a signal having one or more data packets, such as data from one component interacting with another component in a local system, distributed system, and / or across a network such as the Internet with other systems by way of the signal.

[0066] As used herein, the term “non-transitory computer-readable media” includes, but is not limited to, random access memory (RAM), read-only memory (ROM), electronically erasable programmable ROM (EEPROM), flash memory or other memory technology, compact disc ROM (CD-ROM), digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other tangible, physical medium which can be used to store computer readable information.

[0067] As discussed herein, “provider” or “healthcare provider” may include a doctor, surgeon, nurse, nurse practitioner, or any other individual associated with a healthcare action (e.g., a procedure, surgery, or clinical encounter).

[0068] In some aspects, the herein disclosed solution can be configured to address the critical need for surgical site infection (SSIs) prevention and early SSI detection. As there are no transitional care platforms with automated surgical wound monitoring capability, and the market size of readmissions due to SSIs is significant, the solution of this disclosure solves these and other needs of the space.

[0069] Early SSI detection is often hindered by a number of factors, including patients and their caregivers often do not recognize early symptoms of complications, and post-discharge (PD) surgical wound surveillance depends on clinical evaluation at follow-up visits, which may be infrequent, untimely, and even miss otherwise observable infection detection. In some aspects, the methods and systems of this disclosure resolve these and other needs by being configured to direct a user (e.g., a patient) to capture standardized SSI images and provide the user automated surgicalAtty Ref. 94421.00216 wound monitoring and guidance. In some aspects, the solution of this disclosure can utilize a feedback system which guides one or more users to use an image capturing system to capture one or more images that comply with image standards. In some aspects, the solution of this disclosure can utilize a surgeon digital twin neural network (SDTNN) that is trained to predict a clinician SSI evaluation (e.g., a surgeon, a doctor, or any similarly situated care provider). In some aspects, the training aspects can include a denoising diffusion generative network (DDGN) to generate surgical wound images from a small initial SSI dataset.

[0070] In some aspects, the SSI images captured by the user can be HIPAA compliant and can be labeled by a third party different from the user (e.g., a surgeon or any other clinician), with guidance provided in a plurality of risk categories (e.g., no infection risk; further remote monitoring required, in-person consultation with clinician required, readmission required, etc.).

[0071] In some aspects, the labels can define the latent space of the DDGN trained on the image set. In some aspects, the DDGN inference can generate a plurality of images with features corresponding to the labels. By varying labels for the same input, images of the same surgical site can be generated with the DDGN depicting increasing severity.

[0072] In some aspects, SDTNN addresses effectively predicts a clinician’s evaluation without requiring clinical intervention by training the SDTNN to predict guidance the clinician would make based on the generated set of images. The number of input images to the SDTNN is dynamic to accommodate any number of images previously taken by the user to predict the risk category of the plurality of risk categories. SDTNN has the unique ML architecture informed by the surgeon’s domain knowledge which allows the ML model to mimic the decision of the surgeon with high accuracy, yielding a digital twin. In some aspects, the resulting digital twin requires both domain knowledge and overcoming significant technical challenges to effectively predict the clinician’s evaluation and provide user feedback without requiring clinical intervention.

[0073] Turning to the drawings, FIG. 1 shows a workflow detailing the system 100 and method of an example embodiment of this disclosure. In some aspects, system 100 can be surgical site infection (SSI) detection and evaluation system configured to generate a plurality of surgical site images with a plurality of SSI classifications. System 100 can also include a surgeon digital twin neural network (SDTNN) 130Atty Ref. 94421.00216 trained using at least the surgical site images, patient data (e.g., previous user images 133), and / or a source surgical site image database 133. SDTNN 130 can be configured classify a captured image of a surgical site and provide related guidance. SDTNN 130 can be configured to determine a predicted clinician evaluation using at least the plurality of surgical site images, and a captured surgical site image with an SSI classification. System 100 can also include an SSI classifier 160 trained on the source surgical site image database 133 and the generated surgical site images, wherein the SSI classifier 160 can be used to determine an SSI classification.

[0074] In some aspects, system 100 can include an image capturing guidance network (ICGN) 110 to configured to guide image capturing of a surgical site. In some aspects, ICGN 110 can determine guidance based on an image 114 as well as positional feedback (e.g., based on image analysis and / or positional feedback from the device that captured image 114). In some aspects, using image compliance logic ICGN 110 can determine whether a captured image is in compliance with an image standard. In some aspects, ICGN 110 can transmit image capturing guidance to an image capturing system (e.g., a camera on a user computing device, such as a tablet or smart phone), prior to or during capturing of a surgical site image (e.g., image 1 14), in compliance with the image standard.

[0075] In some aspects, the image standard is determined by ICGN 110 using at least a source surgical site image database and the generated plurality of surgical site images. In some aspects, ICGN 110 can be configured to guide users to take an image that complies with image standards using a small dataset and a machine learning model developed utilizing only images that comply with the standards. ICGN 110 can be trained using at least a source surgical site image database and generated plurality of surgical site images. In some aspects, the image standard can include a predetermined percent of the surgical site image and / or be based in part on focus, contrast, and / or depth of field. In one example, ICGN 110 can determine image capturing guidance by applying random brightness, contrast, and affine transforms to an image that initially conforms with the image standard; outputting, using at least the image capturing system, an inverse transform at each deviation; filling in a background of the image, using at least an image generative model and as the inverse transform is output at each deviation; mapping the image back to the captured surgical site image; and analyzing an error between a prediction of the inverse transform generated by the image capturing system and an actual inverse transform.Atty Ref. 94421.00216

[0076] In some aspects of system 100, upon determining an SSI classification, SDTNN 130 can generate one or more message recommendations to a user (e.g., ICGN 110) that can include aspects related to the SSI classification (e.g., high-risk readmittance, low risk, no risk, etc.). In some aspects, a performance evaluation module can be included and include an accuracy submodule and F1-score submodule. Upon the performance evaluation module, based on outputs of the F1 - score submodule and accuracy submodule, determining that a performance score is above a predetermined threshold, a patient risk level can be determined as “high-risk” (e.g., high-risk readmittance) based on a patient risk level metric and / or patient risk level prediction metric. In some aspects, high-risk can be further provided with elevated patient monitoring or depending on the circumstances, the patient may receive standard patient monitoring by the system. If the performance score is below the predetermined threshold, then the system may similarly still provide standard patient monitoring. In some aspects of system 100, upon determining an SSI classification, SDTNN 130 can generate a clinical evaluation 140 to a user, that can include aspects related to the SSI classification. The clinical evaluation 140 for a user can be displayed in a visualization dashboard of a patient computer system and / or a provider computer system (e.g., including within a user interface of an app on the patient computer system, such as a tablet, a smartphone, etc.). Aspects of such a system and method can be understood as including features more clearly described in U.S. Provisional application 63 / 631 ,933 filed April 9, 2024, also by applicant and which is incorporated by reference in its entirety as if set forth verbatim herein. The one or more message recommendations for a user (e.g., a clinician) can be displayed in a visualization dashboard of a patient computer system and / or a provider computer system.

[0077] Turning to FIG. 2, an example workflow 200 is shown for training that a denoising diffusion generative network (DDGN) that is contemplated for use in system 100. In FIG. 2, DDGN can be trained with inputs such as an input image, noise iteration steps, noisy image(s), and denoising diffusion step(s) with severity and / or time stamp labels as inputs. In some aspects, a time stamp can be a duration after a clinical event (e.g., surgery). In some aspects, the DDGN can be trained using a source surgical site image database and labeled surgical wound images. In some aspects, the DDGN trained in FIG. 2 can generate a plurality of surgical site images labeled with an SSI classification, including those referenced in FIG. 1.Atty Ref. 94421.00216

[0078] FIG. 3 shows an example workflow 300 for generating an image set by specifying corresponding severities according to an example of this disclosure. In some examples, during image generation from the DDGN, latent space of infection label(s) can then be traversed to generate images with features corresponding to the labels as shown in FIG. 3.

[0079] FIG. 4 shows an example workflow 400 for predicting severity from input images labeled with time stamps according to an example of this disclosure. As shown in FIG. 4, sequential images can be generated for non-sequential inputs by utilizing image labels, and surgical site severity classification from a dynamic number of input images. In some examples, SDTNN 130 can be trained to classify the surgical site severity based on the generated set of images as shown of FIG. 4.

[0080] FIG. 5 shows an example workflow 500 for an example image transformer, such as image transformer 180 discussed and described below in FIG. 7. Workflow 500 can include generating training data according to one example of this disclosure. In workflow 500, an example is shown of affine transforms deviating from image compliance for generating training data. Workflow 500 can be by applying random brightness, contrast, and affine transforms to an image that initially conforms with the standard. In FIG. 5, since the transform is known, the network is trained to output the inverse transform at each deviation. As transforms are performed, a large image generative model (such as stable diffusion) is used to fill in the background. Note that borders are included in FIG. 5 for process demonstration only. Advantageously, workflow 500 of FIG. 5 can be used to train ICGN 110, as shown in the example of FIG. 7.

[0081] In some aspects, since the transformations are all linear, each step can be mapped back to the original image in one step. However, it is anticipated that the inverse transform communicated to the user will not yield the starting image on first attempt. Therefore, multiple steps are used to account for different user responses but each maps back to the original image. The network is trained by selecting any of the transformed images and predicting the inverse transform. The error between the prediction and actual transform informs the network loss during training, as shown in workflow 600 of FIG. 6.

[0082] FIG. 7 shows an example workflow 700 for one example of training aspects of systems and methods according to an example of this disclosure. In some aspects, workflow 700 can include ICGN 110 receiving training input from image transformerAtty Ref. 94421.00216180. Transformer 180 in turn can be communicatively coupled to at least a source surgical site image database and the generated plurality of surgical site images and receive image data therefrom, transform, then transmit training input to ICGN 110. Training input for DDGN 150 can be at least the source surgical site image database. In some aspects, DDGN 150 can generate a plurality of surgical site images labeled with an SSI classification. Workflow 700 can also include SDTNN 130 arranged in communication with DDGN 150. In some aspects, STDNN 130 can be trained (e g., continuously) where training input can include at least the generated plurality of surgical site images, source surgical site image database, and patient information. Workflow 700 can also include SSI classifier 160 trained on the source surgical site image database and the generated surgical site images, wherein the SSI classifier 160 can be used to determine an SSI classification.

[0083] In some aspects, each of ICGN 110, DDGN 150, SSI classifier 160, and SDTNN 130 can be machine learning models. In some aspects, the machine learning model of this example can be generated based on applying respective training input with, optionally, the associated information paired with the output information as applied by a machine learning algorithm(s). The machine learning algorithm(s) may accept the foregoing aspects as training input, the output information and implement training using one or more techniques. For example, the machine learning models may be trained in one or more Convolutional Neural Networks (CNN), CNN with multipleinstance learning or multi-label multiple instance learning, Recurrent Neural Networks (RNN), Long-short term memory RNN (LSTM), Gated Recurrent Unit RNN (GRU), graph convolution networks, transformer networks, and / or the like or a combination thereof.

[0084] FIG. 8 shows an example workflow 800 for generating one or more predictive outputs according to an example of this disclosure. In some aspects, workflow 800 can include ICGN 110 iteratively communicating with a user surgical wound image database to facilitate image capture of a wound site image according to an image standard. In some aspects, the user surgical wound image database is based in part on user input from a computing device (e.g., a user computing device). Workflow 800 can also include SSI classifier 160 to receive input from the user surgical wound image database as input for image classification to determine an SSI type (e.g., an image classification result). Workflow 800 can also include SDTNN 130 arranged in communication with SSI classifier 160 and ICGN 110. In some aspects, SDTNNAtty Ref. 94421.00216130 can receive input from user data and the SSI type and generate a clinical confidence score and a predicted clinician evaluation. In some aspects, the clinical confidence score can be an output from a layer of SDTNN 130 and can be before a classification layer. In some aspects, the clinical confidence score can be an independent probability of each class, wherein some or all probabilities can be low, but a highest probability can be selected for guidance. To avoid this, SDTNN 130 can sample the layer output and if the maximum value is below a predetermined threshold, then the layer output can be flagged. In some aspects, the predetermined threshold can be determined by statistical analysis of the training / validation data. In some aspects, one or more clusters of each class can be defined and SDTNN 13 can determine if any predictions outside of one or more standard deviations (e.g., 2) of all clusters should be flagged.

[0085] In some aspects, the clinical confidence score can be analyzed according to confidence threshold logic so that a clinical confidence score that passes the threshold logic results in not requiring clinical review. In some aspects, a clinical confidence score that fails the threshold logic results in requiring clinical review and can be used to update the source surgical site image database and / ortrain the SDTNN 130.

[0086] In some aspects, convolutional neural networks can directly learn the features, such as image feature representations necessary for discriminating among characteristics, which can work extremely well when there are large amounts of data to train on, whereas the other methods can be used with either traditional computer vision features, e.g., SURF or SIFT, or with learned embeddings (e.g., descriptors) produced by a trained convolutional neural network, which can yield advantages when there are only small amounts of data to train on. The trained machine learning models of this disclosure may be configured to provide quality designations for the captured patient images.

[0087] Computerized methods of this disclosure that use machine learning models can include, but are not limited to, statistical analysis, autonomous or machine learning, and Al. Al may include, but is not limited to, deep learning, neural networks, classifications, clustering, and regression algorithms. By using machine-learning assisted computational methods, patients and healthcare providers alike can save countless resources by improving system efficiencies, such as diagnostic speed and accuracy, reliability, as well as patient-provider messaging efficiency, and the like. ForAtty Ref. 94421.00216 example, computing systems of this disclosure may be used to assist with image capture, detecting and / or predicting SSI, SSI classification, predicted clinician evaluation, and / or identify or classify patients at higher risk of infection or further avoidable post-operative costs, thereby improving patient outcomes and conserving resources for all involved.

[0088] Prior approaches were time consuming and error-prone in image capture, detecting SSI, classifying SSI, providing clinician evaluation, and identifying certain patients (e g., those prone to reinfection), particularly since certain infection abnormalities are difficult to detect. For example, Al may be used to predict markers from salient regions captured images of surgical sites. Using Al to infer these markers from digital images of surgical sites, or other sites of healthcare actions, has the potential to improve patient care, while also being faster and less expensive.

[0089] According to implementations of the disclosed subject matter, a diagnosis analysis may be implemented at one or a plurality of points during the workflow. As shown, a picture (e.g., a picture of a surgical site) may be captured at the beginning of the workflow. Patient data may also be extracted, including age, gender, and healthcare action (e.g., here that is the surgery related to the picture of the surgical site). In turn, the system can generate a physical or digital patient file that includes or receives patient identification information, patient medical information, and / or other patient related information.

[0090] The captured image can undergo pre-processing using a machine learning model, including analyzed with respect to training data and processed by an augmentation module that may implement one or more augmentation methods to split the image layer from the image preprocessing module into multiple sections, including a training split and validation split. Augmentation techniques can include, but are not limited to, horizontal and vertical flips of images, orthogonal rotation, translation, gaussian noise, contrast variation, and the like. The training split and validation split can be fed into a CNN with novel CNN architecture and a machine learning model (e.g., deep learning model) using training labels from the image training data set and extracted patient data (e.g., patient age, gender, surgical procedure, etc.) to system components, such as ICGN 110, DDGN 150, SSI classifier 160, SDTNN 130, etc. In some aspects, the respective machine learning model can generate outputs using a variety of methods, e.g., identifying an ambiguous range of the probability values such as those close to a threshold, using out-of-distribution techniques (Out-of-DistributionAtty Ref. 94421.00216 detector for Neural Networks (ODIN), tempered mix-up, Mahalanobis distance on the embedding space), etc.

[0091] In some aspects, one practical application of herein disclosed systems and methods is a healthcare provider user can login to the system and a corresponding dashboard of a user interface can present the one or more message recommendations in a visualization dashboard. In some aspects, the one or more message recommendations are generated upon determining an SSI classification using at least the SDTNN. In some aspects, within an exemplary healthcare provider user visualization dashboard, the system can present an inbox messaging module with the one or more message recommendations.

[0092] This disclosure is more clearly understood with an example study evidencing clear system benefits. It is understood that data is presented herein for purposes of illustration and should not be construed as limiting the scope of the disclosed technology in any way or excluding any alternative or additional embodiments. The examples of this disclosure are particularly advantageous for saving considerable time and resources for all parties involved in a typical clinicianpatient surgery. For example, orthopedic surgeons perform on average approximately 32 procedures / month. To handle all of the related pre-operative and post-operative messaging between healthcare providers and patients, on average 4 staff members can be involved in forwarding the messages between patient and healthcare provider. Moreover, each patient can have on average about 8 questions throughout their pre- and post-op process, and an average of 7 minutes is spent answering or forwarding the question. With these baselines, conventional healthcare providers spend on average 7,168 min / month simply responding and handling client inquiries. In some examples, the herein disclosed systems may need no more than 2 staff members to forward or answer the question with an assumed average of 2 minutes spent answering or forwarding the question so that health care providers spend on average 1 ,024 min / month responding and handling client inquiries. Stated differently, the system and method of this disclosure can save at least approximately 85.7% of time compared against current systems used by healthcare providers.

[0093] According to certain embodiments, systems and methods of this disclosure can be included in user-facing front-end including software, firmware, and / or hardware for monitoring aspects of this disclosure pre-operative, post-operative, and after a health action is performed. In some embodiments, this interface to a patient userAtty Ref. 94421.00216 and / or a provider user may include a mobile application (“app”) or other software executable on a mobile computing device (e.g. a smart phone). It is understood that any mobile computing device of this disclosure can be configured to communicate with one or more servers. In another embodiment, the interface may include a web-based application accessible through a browser or other software, or a desktop application. The app can be configured to provide or support functionality for managing patient portal or provider portal of this disclosure. According to certain examples, the app may present information about associated pre-operative protocols, post-operative protocols, patient health states, learning modules, patient data, healthcare provider data, and / or the like, in a dashboard view.

[0094] According to certain embodiments, the system can include a web server, a database server, each connected directly or wirelessly (e.g., 3G / 4G / 5G, RF, a local wireless network, and / or the like). The database server can be operatively connected to one or more web servers across one or more networks, each server operable to permanently store and / or continuously update a database of master data (e.g., data of the patient, historical provider data, historical patient data, pre-operative protocol data, post-operative protocol data, messaging records data, etc.).

[0095] Servers of this disclosure can include back-end architecture with, or be in communication with, one or more of database server(s), whereby functionality of the system may be split between multiple servers, which may be provided by one or more discrete providers. In an example embodiment, the database server may store master data as well as logging and trace information. Software of the database server may be based on the object-relational database system PostgresSQL the database server is not so limited other approaches may be used as needed or required. This database server is not limited to only organizing and storing data and instead, it may be also used to eliminate a need of having an application server (e.g., 2nd Layer). In some embodiments, almost every functional requirement may be realized by using the database’s programming language, PL / pgSQL. The database may also provide an API to the web server for data interchange based on JSON specifications. In some embodiments, the database server may also directly interact with the described functionality of respective patient computing device and / or healthcare provider computing device.

[0096] FIG. 9 is a computer architecture diagram showing a general computing system capable of implementing aspects of the present disclosure in accordance withAtty Ref. 94421.00216 one or more embodiments described herein. In any of these example implementations, computer 900 of the aforementioned may be configured to perform one or more functions associated with embodiments of this disclosure. For example, the computer 900 may be configured to perform operations in accordance with those examples shown in FIGS. 1-8. It should be appreciated that the computer 900 may be implemented within a single computing device or a computing system formed with multiple connected computing devices. The computer 900 may be configured to perform various distributed computing tasks, in which processing and / or storage resources may be distributed among the multiple devices. The data acquisition and display computer 950 and / or operator console 910 of the system shown in FIG. 9 may include one or more systems and components of the computer 900.

[0097] As shown, the computer 900 includes a processing unit 902 (“CPU”), a system memory 904, and a system bus 906 that couples the memory 904 to the CPU 902. The computer 900 further includes a mass storage device 912 for storing program modules 914. The program modules 914 may be operable to analyze data from any herein disclosed data feeds, databases, classify user states based on the data feeds, determine responsive actions, and / or control any related operations. The program modules 914 may include an application 918 for performing data acquisition and / or processing functions as described herein, for example to acquire and / or process any of the herein discussed data feeds. The computer 900 can include a data store 920 for storing data that may include data 922 of data feeds (e.g., pre-operative data, post-operative data, health action data, detected changes in patient states, patient severity states, message prompts, etc.).

[0098] The mass storage device 912 is connected to the CPU 902 through a mass storage controller (not shown) connected to the bus 906. The mass storage device 912 and its associated computer-storage media provide non-volatile storage for the computer 900. Although the description of computer-storage media contained herein refers to a mass storage device, such as a hard disk or CD-ROM drive, it should be appreciated by those skilled in the art that computer-storage media can be any available computer storage media that can be accessed by the computer 900.

[0099] By way of example and not limitation, computer storage media (also referred to herein as “computer-readable storage medium” or “computer-readable storage media”) may include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such asAtty Ref. 94421.00216 computer-storage instructions, data structures, program modules, or other data. For example, computer storage media includes, but is not limited to, RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, CD-ROM, digital versatile disks (“DVD”), HD-DVD, BLU-RAY, or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by the computer 900. “Computer storage media”, “computer- readable storage medium” or “computer-readable storage media” as described herein do not include transitory signals.

[0100] According to various embodiments, the computer 900 may operate in a networked environment using connections to other local or remote computers through a network 916 (e.g., previous network 908) via a network interface unit 910 connected to the bus 906. The network interface unit 910 may facilitate connection of the computing device inputs and outputs to one or more suitable networks and / or connections such as a local area network (LAN), a wide area network (WAN), the Internet, a cellular network, a radio frequency (RF) network, a Bluetooth-enabled network, a Wi-Fi enabled network, a satellite-based network, or other wired and / or wireless networks for communication with external devices and / or systems.

[0101] The computer 900 may also include an input / output controller 908 for receiving and processing input from any of a number of input devices. Input devices may include one or more of keyboards, mice, stylus, touchscreens, microphones, audio capturing devices, and image / video capturing devices. An end user may utilize the input devices to interact with a user interface, for example a graphical user interface, for managing various functions performed by the computer 900. The bus 906 may enable the processing unit 902 to read code and / or data to / from the mass storage device 912 or other computer-storage media.

[0102] The computer-storage media may represent apparatus in the form of storage elements that are implemented using any suitable technology, including but not limited to semiconductors, magnetic materials, optics, or the like. The computerstorage media may represent memory components, whether characterized as RAM, ROM, flash, or other types of technology. The computer storage media may also represent secondary storage, whether implemented as hard drives or otherwise. Hard drive implementations may be characterized as solid state or may include rotating media storing magnetically-encoded information. The program modules 914, whichAtty Ref. 94421.00216 include the data feed application 918, may include instructions that, when loaded into the processing unit 902 and executed, cause the computer 900 to provide functions associated with one or more embodiments illustrated in the figures of this disclosure. The program modules 914 may also provide various tools or techniques by which the computer 900 may participate within the overall systems or operating environments using the components, flows, and data structures discussed throughout this description.

[0103] In general, the program modules 914 may, when loaded into the processing unit 902 and executed, transform the processing unit 902 and the overall computer 900 from a general-purpose computing system into a special-purpose computing system. The processing unit 902 may be constructed from any number of transistors or other discrete circuit elements, which may individually or collectively assume any number of states. More specifically, the processing unit 902 may operate as a finite- state machine, in response to executable instructions contained within the program modules 914. These computer-executable instructions may transform the processing unit 902 by specifying how the processing unit 902 transitions between states, thereby transforming the transistors or other discrete hardware elements constituting the processing unit 902.

[0104] Encoding the program modules 914 may also transform the physical structure of the computer-storage media. The specific transformation of physical structure may depend on various factors, in different implementations of this description. Examples of such factors may include but are not limited to the technology used to implement the computer-storage media, whether the computer storage media are characterized as primary or secondary storage, and the like. For example, if the computer storage media are implemented as semiconductor-based memory, the program modules 914 may transform the physical state of the semiconductor memory, when the software is encoded therein. For example, the program modules 914 may transform the state of transistors, capacitors, or other discrete circuit elements constituting the semiconductor memory.

[0105] As another example, the computer storage media may be implemented using magnetic or optical technology. In such implementations, the program modules 914 may transform the physical state of magnetic or optical media, when the software is encoded therein. These transformations may include altering the magnetic characteristics of particular locations within given magnetic media. TheseAtty Ref. 94421.00216 transformations may also include altering the physical features or characteristics of particular locations within given optical media, to change the optical characteristics of those locations. Other transformations of physical media are possible without departing from the scope of the present description, with the foregoing examples provided only to facilitate this discussion.

[0106] FIG. 10 is a computer-implemented method 1000. Step 1010 of method 1000 can include generating, using at least a denoising diffusion generative network (DDGN), a plurality of surgical site images with a plurality of classifications. Step 1020 of method 1000 can include determining, using at least a surgeon digital twin neural network (SDTNN), the plurality of surgical site images, a captured surgical site image, and a surgical site infection (SSI) classification, a predicted clinician evaluation, the SDTNN trained using at least the plurality of surgical site images, patient data, and labeled surgical wound images.

[0107] Certain embodiments and implementations of the disclosed technology are described above with reference to a block diagram of systems and / or computer program products according to example embodiments or implementations of the disclosed technology. It will be understood that one or more blocks of the block diagram, and combinations of blocks in the block diagrams can be implemented by computer-executable program instructions. Likewise, some blocks of the block diagrams may not necessarily need to be performed all of the functions described herein and may perform additional functions according to some embodiments or implementations of the disclosed technology.

[0108] As will be appreciated by one of ordinary skill in the art, the system may be embodied as a customization of an existing system, an add-on product, a processing apparatus executing upgraded software, a stand-alone system, a distributed system, a method, a data processing system, a device for data processing, and / or a computer program product. Accordingly, any portion of the system or a module may take the form of a processing apparatus executing code, an internet-based embodiment, an entirely hardware embodiment, or an embodiment combining aspects of the internet, software, and hardware. Furthermore, the system may take the form of a computer program product on a computer-readable storage medium having computer-readable program code means embodied in the storage medium.

[0109] The present system or any part(s) or function(s) thereof may be implemented using hardware, software, or a combination thereof and may beAtty Ref. 94421.00216 implemented in one or more computer systems or other processing systems. However, the manipulations performed by embodiments may be referred to in terms, such as matching or selecting, which are commonly associated with mental operations performed by a human operator. No such capability of a human operator is necessary, or desirable, in most cases, in any of the operations described herein. Rather, the operations may be machine operations or any of the operations may be conducted or enhanced by artificial intelligence (Al) or machine learning. Al may refer generally to the study of agents (e.g., machines, computer-based systems, etc.) that perceive the world around them, form plans, and make decisions to achieve their goals. Foundations of Al include mathematics, logic, philosophy, probability, linguistics, neuroscience, and decision theory. Many fields fall under the umbrella of Al, such as computer vision, robotics, machine learning, and natural language processing. Useful machines for performing the various embodiments include general purpose digital computers or similar devices. The Al or ML may store data in a decision tree in a novel way.

[0110] In various embodiments, the system and various components may integrate with one or more smart digital assistant technologies. For example, exemplary smart digital assistant technologies may include the ALEXA® system developed by the AMAZON® company, the GOOGLE HOME® system developed by Alphabet, Inc., the HOMEPOD® system of the APPLE® company, and / or similar digital assistant technologies.

[0111] The system contemplates uses in association with web services, utility computing, pervasive and individualized computing, security and identity solutions, autonomic computing, cloud computing, commodity computing, mobility and wireless solutions, open source, biometrics, grid computing, and / or mesh computing.

[0112] Any databases discussed herein may include relational, hierarchical, graphical, blockchain, object-oriented structure, and / or any other database configurations. Any database may also include a flat file structure wherein data may be stored in a single file in the form of rows and columns, with no structure for indexing and no structural relationships between records. For example, a flat file structure may include a delimited text file, a CSV (comma-separated values) file, and / or any other suitable flat file structure. Common database products that may be used to implement the databases include DB2® by IBM® (Armonk, NY), various database products available from ORACLE® Corporation (Redwood Shores, CA), MICROSOFTAtty Ref. 94421.00216ACCESS® or MICROSOFT SQL SERVER® by MICROSOFT® Corporation (Redmond, Washington), MYSQL® by MySQL AB (Uppsala, Sweden), MONGODB®, Redis, Apache Cassandra®, HBASE® by APACHE®, MapR-DB by the MAPR® corporation, or any other suitable database product. Moreover, any database may be organized in any suitable manner, for example, as data tables or lookup tables. Each record may be a single file, a series of files, a linked series of data fields, or any other data structure.

[0113] As used herein, big data may refer to partially or fully structured, semistructured, or unstructured data sets including millions of rows and hundreds of thousands of columns. A big data set may be compiled, for example, from a history of purchase transactions over time, from web registrations, from social media, from records of charge (ROC), from summaries of charges (SOC), from internal data, or from other suitable sources. Big data sets may be compiled without descriptive metadata such as column types, counts, percentiles, or other interpretive-aid data points.

[0114] Association of certain data may be accomplished through any desired data association technique such as those known or practiced in the art. For example, the association may be accomplished either manually or automatically. Automatic association techniques may include, for example, a database search, a database merge, GREP, AGREP, SQL, using a key field in the tables to speed searches, sequential searches through all the tables and files, sorting records in the file according to a known order to simplify lookup, and / or the like. The association step may be accomplished by a database merge function, for example, using a “key field” in pre-selected databases or data sectors. Various database tuning steps are contemplated to optimize database performance. For example, frequently used files such as indexes may be placed on separate file systems to reduce In / Out (“I / O”) bottlenecks.

[0115] More particularly, a “key field” partitions the database according to the high- level class of objects defined by the key field. For example, certain types of data may be designated as a key field in a plurality of related data tables and the data tables may then be linked on the basis of the type of data in the key field. The data corresponding to the key field in each of the linked data tables is preferably the same or of the same type. However, data tables having similar, though not identical, data in the key fields may also be linked by using AGREP, for example. In accordance withAtty Ref. 94421.00216 one embodiment, any suitable data storage technique may be utilized to store data without a standard format. Data sets may be stored using any suitable technique, including, for example, storing individual files using an ISO / IEC 7816-4 file structure; implementing a domain whereby a dedicated file is selected that exposes one or more elementary files containing one or more data sets; using data sets stored in individual files using a hierarchical filing system; data sets stored as records in a single file (including compression, SQL accessible, hashed via one or more keys, numeric, alphabetical by first tuple, etc.); data stored as Binary Large Object (BLOB); data stored as ungrouped data elements encoded using ISO / IEC 7816-6 data elements; data stored as ungrouped data elements encoded using ISO / IEC Abstract Syntax Notation (ASN.1 ) as in ISO / IEC 8824 and 8825; other proprietary techniques that may include fractal compression methods, image compression methods, etc.

[0116] In various embodiments, the ability to store a wide variety of information in different formats is facilitated by storing the information as a BLOB. Thus, any binary information can be stored in a storage space associated with a data set. As discussed above, the binary information may be stored in association with the system or external to but affiliated with the system. The BLOB method may store data sets as ungrouped data elements formatted as a block of binary via a fixed memory offset using either fixed storage allocation, circular queue techniques, or best practices with respect to memory management (e.g., paged memory, least recently used, etc.). By using BLOB methods, the ability to store various data sets that have different formats facilitates the storage of data, in the database or associated with the system, by multiple and unrelated owners of the data sets. For example, a first data set which may be stored may be provided by a first party, a second data set which may be stored may be provided by an unrelated second party, and yet a third data set which may be stored may be provided by a third party unrelated to the first and second party. Each of these three exemplary data sets may contain different information that is stored using different data storage formats and / or techniques. Further, each data set may contain subsets of data that also may be distinct from other subsets.

[0117] As stated above, in various embodiments, the data can be stored without regard to a common format. However, the data set (e.g., BLOB) may be annotated in a standard manner when provided for manipulating the data in the database or system. The annotation may comprise a short header, trailer, or other appropriate indicator related to each data set that is configured to convey information useful in managingAtty Ref. 94421.00216 the various data sets. For example, the annotation may be called a “condition header,” “header,” “trailer,” or “status,” herein, and may comprise an indication of the status of the data set or may include an identifier correlated to a specific issuer or owner of the data. In one example, the first three bytes of each data set BLOB may be configured or configurable to indicate the status of that particular data set; e.g., LOADED, INITIALIZED, READY, BLOCKED, REMOVABLE, or DELETED. Subsequent bytes of data may be used to indicate for example, the identity of the issuer, user, transaction / membership account identifier or the like. Each of these condition annotations are further discussed herein.

[0118] The data set annotation may also be used for other types of status information as well as various other purposes. For example, the data set annotation may include security information establishing access levels. The access levels may, for example, be configured to permit only certain individuals, levels of employees, companies, or other entities to access data sets, or to permit access to specific data sets based on the transaction, merchant, issuer, user, or the like. Furthermore, the security information may restrict / permit only certain actions, such as accessing, modifying, and / or deleting data sets. In one example, the data set annotation indicates that only the data set owner or the user are permitted to delete a data set, various identified users may be permitted to access the data set for reading, and others are altogether excluded from accessing the data set. However, other access restriction parameters may also be used allowing various entities to access a data set with various permission levels as appropriate.

[0119] The data, including the header or trailer, may be received by a standalone interaction device configured to add, delete, modify, or augment the data in accordance with the header or trailer. As such, in one embodiment, the header or trailer is not stored on the transaction device along with the associated issuer-owned data, but instead the appropriate action may be taken by providing to the user, at the standalone device, the appropriate option for the action to be taken. The system may contemplate a data storage arrangement wherein the header or trailer, or header or trailer history, of the data is stored on the system, device or transaction instrument in relation to the appropriate data.

[0120] One skilled in the art will also appreciate that, for security reasons, any databases, systems, devices, servers, or other components of the system may consist of any combination thereof at a single location or at multiple locations, wherein eachAtty Ref. 94421.00216 database or system includes any of various suitable security features, such as firewalls, access codes, encryption, decryption, compression, decompression, and / or the like.

[0121] Practitioners will also appreciate that there are a number of methods for displaying data within a browser-based document. Data may be represented as standard text or within a fixed list, scrollable list, drop-down list, editable text field, fixed text field, pop-up window, and the like. Likewise, there are a number of methods available for modifying data in a web page such as, for example, free text entry using a keyboard, selection of menu items, check boxes, option boxes, and the like.

[0122] The data may be big data that is processed by a distributed computing cluster. The distributed computing cluster may be, for example, a HADOOP® software cluster configured to process and store big data sets with some of nodes comprising a distributed storage system and some of nodes comprising a distributed processing system. In that regard, distributed computing cluster may be configured to support a HADOOP® software distributed file system (HDFS) as specified by the Apache Software Foundation at ww hg ogg. £ac e ..org / dpcs.

[0123] As used herein, the term “network” includes any cloud, cloud computing system, or electronic communications system or method which incorporates hardware and / or software components. Communication among the parties may be accomplished through any suitable communication channels, such as, for example, a telephone network, an extranet, an intranet, internet, point of interaction device (point of sale device, personal digital assistant (e.g., an IPHONE® device, a BLACKBERRY® device), cellular phone, kiosk, etc.), online communications, satellite communications, off-line communications, wireless communications, transponder communications, local area network (LAN), wide area network (WAN), virtual private network (VPN), networked or linked devices, keyboard, mouse, and / or any suitable communication or data input modality. Moreover, although the system is frequently described herein as being implemented with TCP / IP communications protocols, the system may also be implemented using IPX, APPLETALK® program, IP-6, NetBIOS, OSI, any tunneling protocol (e.g., IPsec, SSH, etc.), or any number of existing or future protocols. If the network is in the nature of a public network, such as the internet, it may be advantageous to presume the network to be insecure and open to eavesdroppers. Specific information related to the protocols, standards, and application softwareAtty Ref. 94421.00216 utilized in connection with the internet is generally known to those skilled in the art and, as such, need not be detailed herein.

[0124] “Cloud” or “Cloud computing” includes a model for enabling convenient, on- demand network access to a shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services) that can be rapidly provisioned and released with minimal management effort or service provider interaction. Cloud computing may include location-independent computing, whereby shared servers provide resources, software, and data to computers and other devices on demand.

[0125] As used herein, “transmit” may include sending electronic data from one system component to another over a network connection. Additionally, as used herein, “data” may include encompassing information such as commands, queries, files, data for storage, and the like in digital or any other form.

[0126] While certain embodiments of the present disclosure have been described in connection with what is presently considered to be the most practical and various embodiments, it is to be understood that the present disclosure is not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.

[0127] This written description uses examples to disclose certain embodiments of the present disclosure, including the best mode, and also to enable any person skilled in the art to practice certain embodiments of the present disclosure, including making and using any devices or systems and performing any incorporated methods. The patentable scope of certain embodiments of the present disclosure is defined in the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they have structural elements that do not differ from the literal language of the claims, or if they include equivalent structural elements with insubstantial differences from the literal language of the claims.

[0128] The specific configurations, choice of components and size and shape of various elements can be varied according to particular design specifications or constraints requiring a system or method constructed according to the principles of the disclosed technology. Such changes are intended to be embraced within the scope of the disclosed technology. The presently disclosed embodiments, therefore, areAtty Ref. 94421.00216 considered in all respects to be illustrative and not restrictive. It will therefore be apparent from the foregoing that while particular forms of the disclosure have been illustrated and described, various modifications can be made without departing from the spirit and scope of the disclosure and all changes that come within the meaning and range of equivalents thereof are intended to be embraced therein.

[0129] The following clauses list non-limiting embodiments of the disclosure:1. A computer-implemented method, comprising: generating, using at least a denoising diffusion generative network (DDGN), a plurality of surgical site images with a plurality of classifications; and determining, using at least a surgeon digital twin neural network (SDTNN), the plurality of surgical site images, a captured surgical site image, and a surgical site infection (SSI) classification, a predicted clinician evaluation, the SDTNN trained using at least the plurality of surgical site images, patient data, and labeled surgical wound images.2. The computer-implemented method of Clause 1 , further comprising: determining, using at least an SSI classifier trained on a source surgical site image database and the generated surgical site images, the SSI classification.3. The computer-implemented method of Clause 1 , wherein the plurality of classifications comprises SSI classifications.4. The computer-implemented method of Clause 1 , further comprising: generating, using at least the DDGN, a plurality of surgical site images labeled with an SSI classification.5. The computer-implemented method of Clause 1 , wherein the DDGN is trained using at least a source surgical site image database and labeled surgical wound images.6. The computer-implemented method of Clause 1 , wherein the SDTNN is trained to predict a clinician evaluation, using at least the generated plurality of surgical site images, a source surgical site image database, and patient information and without clinician input.Atty Ref. 94421.002167. The computer-implemented method of Clause 1 , wherein the SDTNN is trained continuously using at least the generated plurality of surgical site images, a source surgical site image database, and patient information.8. The computer-implemented method of Clause 1 , further comprising: transmitting image capturing guidance to an image capturing system, prior to or during capturing of the captured surgical site image, in compliance with an image standard.9. The computer-implemented method of Clause 8, wherein a user computing device comprises the image capturing system.10. The computer-implemented method of Clause 8, wherein the image standard is determined by an image capturing guidance network (ICGN) using at least a source surgical site image database and the generated plurality of surgical site images.11. The computer-implemented method of Clause 10, wherein the ICGN is trained using at least the source surgical site image database and the generated plurality of surgical site images.12. The computer-implemented method of Clause 8, wherein the image standard comprises the captured surgical site image comprising a predetermined percent of the surgical site image.13. The computer-implemented method of Clause 8, wherein the image standard is based at least on focus, contrast, and depth of field.14. The computer-implemented method of Clause 8, wherein the image capturing guidance is determined by: applying random brightness, contrast, and affine transforms to an image that initially conforms with the image standard;Atty Ref. 94421.00216 outputting, using at least an image capturing system, an inverse transform at each deviation; filling in a background of the image, using at least an image generative model and as the inverse transform is output at each deviation; mapping the image back to the captured surgical site image; and analyzing an error between a prediction of the inverse transform generated by the image capturing system and an actual inverse transform.15. The computer-implemented method of Clause 1 , further comprising: extracting data from the captured surgical site image prior to or during the determining the predicted clinician evaluation.16. The computer-implemented method of Clause 1 , further comprising: determining, using at least the SDTNN and a determined SSI classification, a surgical site treatment protocol; and displaying information related to the surgical site treatment protocol in a visualization dashboard of a patient computer system and / or a healthcare provider computer system.17. The computer-implemented method of Clause 1 , further comprising: upon determining an SSI classification, generating, using at least the SDTNN, one or more message recommendations; and displaying the one or more message recommendations in a visualization dashboard of a patient computer system and / or a provider computer system.18. A surgical site infection (SSI) detection and evaluation system, comprising: a denoising diffusion generative network (DDGN) configured to generate a plurality of surgical site images with a plurality of surgical site infection (SSI) classifications; and a surgeon digital twin neural network (SDTNN) trained using at least the plurality of surgical site images, patient data, and a source surgical site image database, the SDTNN being configured to determine a predicted clinician evaluationAtty Ref. 94421.00216 using at least the plurality of surgical site images, and a captured surgical site image with an SSI classification.19. The SSI detection and evaluation system of Clause 18, further comprising: an SSI classifier trained on the plurality of surgical site images and labeled source surgical site image database, the SSI classifier configured to determine the SSI classification.20. The SSI detection and evaluation system of Clause 18, wherein labels of the plurality of images define a latent space of the DDGN, and wherein the latent space of an infection label is traversed during the generating of surgical wound images to generate images with features corresponding to the labels.21. The SSI detection and evaluation system of Clause 18, further comprising: an image capturing guidance network (ICGN) configured to determine an image capturing guidance using at least source images and the generated plurality of surgical site images, prior to or during capturing of the captured surgical site image, in compliance with an image standard.22. The SSI detection and evaluation system of Clause 21 , wherein the ICGN is trained using at least the plurality of surgical site images and the source surgical site image database.23. The SSI detection and evaluation system of Clause 21 , wherein the ICGN is configured to guide a user using a user computing device to capture an image of a surgical site.24. The SSI detection and evaluation system of Clause 23, wherein the ICGN is configured to guide a user to capture the image based on image capturing guidance determined by: applying brightness, contrast, and affine transforms to an image that initially conforms with an image standard;Atty Ref. 94421.00216 outputting, using at least an image capturing system, an inverse transform at each deviation; and mapping the image back to the captured SSI image.25. A clinician evaluation prediction system, comprising: a computer system configured to implement an artificial neural network adapted to generate, using captured imaging data of a surgical site and a plurality of surgical wound images generated by a denoising diffusion generative network (DDGN) from a source surgical site image database, a surgeon digital twin neural network (SDTNN) trained to predict a clinician SSI evaluation using at least the plurality of surgical wound images, a captured surgical site image, and an SSI classification.26. The clinician prediction system of Clause 25, wherein the SSI classification is determined by an SSI classifier trained on the plurality of surgical site images and the source surgical site image database.27. The clinician prediction system of Clause 25, wherein the SDTNN is trained to predict the clinician SSI evaluation without clinician input.28. The clinician prediction system of Clause 25, wherein the DDGN is configured to generate the plurality of surgical wound images labeled with an SSI severity.29. The clinician prediction system of Clause 28, wherein labels of the plurality of surgical wound images define a latent space of the DDGN, and wherein the latent space of an infection label is traversed during the generating of the system generated surgical wound images to generate images with features corresponding to the labels.30. The clinician prediction system of Clause 25, wherein the DDGN is configured to generate the surgical wound images with features corresponding to a plurality of risk labels.Atty Ref. 94421.0021631. The clinician prediction system of Clause 30, wherein the DDGN is configured to vary the plurality of risk labels for the same input.32. The clinician prediction system of Clause 30, wherein a number of input images to the SDTNN is configured to accommodate any number of previously captured images to predict a risk label of the plurality of risk labels.33. The clinician prediction system of Clause 30, wherein the plurality of risk labels at least comprise a no infection risk label, a further remote monitoring required label, an in-person consultation required label, and a readmission required label.34. A system comprising: at least one memory storing instructions; and at least one processor executing the instructions to perform operations comprising: generating, using at least a denoising diffusion generative network (DDGN), a plurality of surgical site images with a plurality of classifications; and determining, using at least a surgeon digital twin neural network (SDTNN), the plurality of surgical site images, a captured surgical site image, and an SSI classification, a predicted clinician evaluation, the SDTNN trained using at least the plurality of SSI images, patient data, and labeled surgical wound images.35. The system of Clause 34, the operations comprising: determining, using at least an SSI classifier trained on the plurality of surgical site images and labeled surgical wound images, the SSI classification.36. The system of Clause 34, the operations comprising: transmitting image capturing guidance to an image capturing system, prior to or during capturing of the captured surgical site image, in compliance with an image standard, wherein the image standard is determined by an image capturing guidance network (ICGN) using at least source images and the generated plurality of surgical site images, wherein the image capturing guidance is determined by applying random brightness, contrast, and affine transforms to an image that initially conforms with the image standard;Atty Ref. 94421.00216 outputting, using at least the image capturing system, an inverse transform at each deviation; filling in a background of the image, using at least an image generative model and as the inverse transform is output at each deviation; mapping the image back to the captured surgical site image; and analyzing an error between a prediction of the inverse transform generated by the image capturing system and an actual inverse transform.37. The system of Clause 34, the operations comprising: determining, using at least the SDTNN and an SSI severity, a surgical site treatment protocol; and displaying information related to the surgical site treatment protocol in a visualization dashboard of a patient computer system and / or a healthcare provider computer system.38. The system of Clause 34, the operations comprising: upon determining the SSI classification is elevated, generating, using at least the SDTNN, one or more message recommendations; and displaying the one or more message recommendations in a visualization dashboard of a patient computer system and / or a provider computer system.

Claims

Atty Ref. 94421.00216CLAIMSWhat is claimed is:

1. A computer-implemented method, comprising: generating, using at least a denoising diffusion generative network (DDGN), a plurality of surgical site images with a plurality of classifications; and determining, using at least a surgeon digital twin neural network (SDTNN), the plurality of surgical site images, a captured surgical site image, and a surgical site infection (SSI) classification, a predicted clinician evaluation, the SDTNN trained using at least the plurality of surgical site images, patient data, and labeled surgical wound images.

2. The computer-implemented method of Claim 1 , further comprising: determining, using at least an SSI classifier trained on a source surgical site image database and the generated surgical site images, the SSI classification.

3. The computer-implemented method of Claim 1 , further comprising: generating, using at least the DDGN, a plurality of surgical site images labeled with an SSI classification.

4. The computer-implemented method of Claim 1 , wherein the SDTNN is trained to predict a clinician evaluation, using at least the generated plurality of surgical site images, a source surgical site image database, and patient information and without clinician input.

5. The computer-implemented method of Claim 1 , further comprising: transmitting image capturing guidance to an image capturing system, prior to or during capturing of the captured surgical site image, in compliance with an image standard, wherein the image standard is determined by an image capturing guidance network (ICGN) using at least a source surgical site image database and the generated plurality of surgical site images.Atty Ref. 94421.002166. The computer-implemented method of Claim 5, wherein the ICGN is trained using at least the source surgical site image database and the generated plurality of surgical site images.

7. The computer-implemented method of Claim 5, wherein the image standard is based at least on focus, contrast, and depth of field.

8. The computer-implemented method of Claim 5, wherein the image capturing guidance is determined by: applying random brightness, contrast, and affine transforms to an image that initially conforms with the image standard; outputting, using at least an image capturing system, an inverse transform at each deviation; filling in a background of the image, using at least an image generative model and as the inverse transform is output at each deviation; mapping the image back to the captured surgical site image; and analyzing an error between a prediction of the inverse transform generated by the image capturing system and an actual inverse transform.

9. The computer-implemented method of Claim 1 , further comprising: determining, using at least the SDTNN and a determined SSI classification, a surgical site treatment protocol; and displaying information related to the surgical site treatment protocol in a visualization dashboard of a patient computer system and / or a healthcare provider computer system.

10. A surgical site infection (SSI) detection and evaluation system, comprising: a denoising diffusion generative network (DDGN) configured to generate a plurality of surgical site images with a plurality of surgical site infection (SSI) classifications; and a surgeon digital twin neural network (SDTNN) trained using at least the plurality of surgical site images, patient data, and a source surgical site image database, the SDTNN being configured to determine a predicted clinician evaluationAtty Ref. 94421.00216 using at least the plurality of surgical site images, and a captured surgical site image with an SSI classification.

11. The SSI detection and evaluation system of Claim 10, further comprising: an SSI classifier trained on the plurality of surgical site images and labeled source surgical site image database, the SSI classifier configured to determine the SSI classification.

12. The SSI detection and evaluation system of Claim 10, wherein labels of the plurality of images define a latent space of the DDGN, and wherein the latent space of an infection label is traversed during the generating of surgical wound images to generate images with features corresponding to the labels.

13. The SSI detection and evaluation system of Claim 10, further comprising: an image capturing guidance network (ICGN) configured to determine an image capturing guidance using at least source images and the generated plurality of surgical site images, prior to or during capturing of the captured surgical site image, in compliance with an image standard.

14. The SSI detection and evaluation system of Claim 13, wherein the ICGN is configured to guide a user using a user computing device to capture an image of a surgical site, wherein the ICGN is configured to guide a user to capture the image based on image capturing guidance determined by: applying brightness, contrast, and affine transforms to an image that initially conforms with an image standard; outputting, using at least an image capturing system, an inverse transform at each deviation; and mapping the image back to the captured SSI image.

15. A clinician evaluation prediction system, comprising: a computer system configured to implement an artificial neural network adapted to generate, using captured imaging data of a surgical site and a plurality of surgicalAtty Ref. 94421.00216 wound images generated by a denoising diffusion generative network (DDGN) from a source surgical site image database, a surgeon digital twin neural network (SDTNN) trained to predict a clinician SSI evaluation using at least the plurality of surgical wound images, a captured surgical site image, and an SSI classification.

16. The clinician prediction system of Claim 15, wherein the SSI classification is determined by an SSI classifier trained on the plurality of surgical site images and the source surgical site image database.

17. The clinician prediction system of Claim 15, wherein the SDTNN is trained to predict the clinician SSI evaluation without clinician input.

18. A system comprising: at least one memory storing instructions; and at least one processor executing the instructions to perform operations comprising: generating, using at least a denoising diffusion generative network (DDGN), a plurality of surgical site images with a plurality of classifications; and determining, using at least a surgeon digital twin neural network (SDTNN), the plurality of surgical site images, a captured surgical site image, and an SSI classification, a predicted clinician evaluation, the SDTNN trained using at least the plurality of SSI images, patient data, and labeled surgical wound images.

19. The system of Claim 18, the operations comprising: transmitting image capturing guidance to an image capturing system, prior to or during capturing of the captured surgical site image, in compliance with an image standard, wherein the image standard is determined by an image capturing guidance network (ICGN) using at least source images and the generated plurality of surgical site images, wherein the image capturing guidance is determined by applying random brightness, contrast, and affine transforms to an image that initially conforms with the image standard;Atty Ref. 94421.00216 outputting, using at least the image capturing system, an inverse transform at each deviation; filling in a background of the image, using at least an image generative model and as the inverse transform is output at each deviation; mapping the image back to the captured surgical site image; and analyzing an error between a prediction of the inverse transform generated by the image capturing system and an actual inverse transform.

20. The system of Claim 18, the operations comprising: determining, using at least the SDTNN and an SSI severity, a surgical site treatment protocol; and displaying information related to the surgical site treatment protocol in a visualization dashboard of a patient computer system and / or a healthcare provider computer system.

Images