System and method for adaptive generation of graphic data for predictive diagnosis

Abstract

A method for generating a user interface of predicted disease progression includes receiving medical data corresponding to a patient visit to a healthcare provider, generating a diagnosis for the patient based on the medical data, and generating a predictive diagnosis regarding the patient's future symptoms based on the diagnosis and a prediction model. The method further includes generating a timeline view of the diagnosis and the predictive diagnosis in the current patient visit. Each of the graphic elements of the diagnosis and the predictive diagnosis includes a graphic indicator of the diagnosis and at least one graphic sub-element of a physiological parameter related to the diagnosis. The method further includes generating a graphic connector between the graphic elements to indicate the progression of time between a first time and a second time of the current patient visit.

Description

Technical Field

[0001] Priority Claim and Cross - Reference to Related Applications This application claims priority to U.S. Provisional Patent Application No. 63 / 364,518, filed on May 11, 2022, entitled "SYSTEM AND METHOD FOR ADAPTIVE GENERATION OF GRAPHICAL DATA OF PREDICTED DIAGNOSES", the entire content of which is incorporated herein by reference. This application cross - references U.S. Provisional Patent Application No. 63 / 364,517, filed on May 11, 2022, entitled "SYSTEM AND METHOD FOR ADAPTIVE GENERATION OF GRAPHICAL DATA OF A TREATMENT HISTORY", which is co - pending and the entire content of which is incorporated herein by reference.

Background Art

[0002] Patients with diabetes (PwD), especially those with type 2 diabetes (T2D), generally receive treatment from a primary care provider (PCP) such as a general practitioner (GP) or a family doctor (FM). Since PCPs diagnose not only patients with T2DM but also patients with many other chronic conditions, they are often overwhelmed due to the large number of patients. With a typical appointment time of less than 15 minutes, there is a significant cognitive load on the PCP regarding disease management and optimal treatment recommendations. These factors lead to the phenomenon of clinical inertia, which is a delay caused in the appropriate intensification of treatment for better disease management. Clinical inertia, in turn, leads to an increase in health - economic costs and a decrease in the quality of life in PwD.

[0003] Therefore, there is a need for clinical decision support (CDS) tools that assist primary care physicians (PCPs) and other healthcare providers (HCPs) in making appropriate treatment selections for patients with type 2 diabetes. When incorporated into the clinical workflow, CDS tools that take into account patient characteristics can assist HCPs in making better individualized treatment decisions that improve clinical outcomes, patient-reported outcomes, and economic outcomes. In the medical field, clinical guidelines for diabetes management are recognized by organizations such as the American Diabetes Association (ADA) and the European Association for the Study of Diabetes (EASD). However, even these clinical guidelines for treatment transitions in type 2 diabetes (T2D) can be cumbersome for PCPs to follow or apply given the volume of patient data. Considering the chronic nature of diabetes and the many comorbidities, healthcare providers also need to reexamine and share potential prognoses with people with diabetes (PwD) to evaluate various treatment options and help educate PwD about disease progression. Although there are statistical models that can help predict the trajectory of the disease, HCPs, who have limited patient time at each visit, may not have the opportunity to examine such models to provide different prognoses to PwD in a rigorous manner. As a result, improvements in systems and methods for efficiently providing clinical information and CDS to PCPs and other HCPs, reducing cognitive load, and enabling HCPs to easily consider different predictions of disease progression would be beneficial.

Summary of the Invention

[0004] An adaptive clinical decision support user interface (UI) identifies and generates graphic data for a user interface with one or more predicted disease progressions for a patient based on a current patient diagnosis, optionally one or more treatment options, and a prediction model. The model-based predictive approach not only displays potential disease progression in different prescribed treatment options but also adds other contextual elements such as the expected duration at each stage and the possible outcomes in both health and economic terms and the likelihood of success in each of these trajectories, enabling healthcare providers (HCPs) in the medical field to quickly visualize and discuss treatment options with the patient.

[0005] In one embodiment, a method for generating a user interface for a patient's treatment history has been developed. The method includes receiving, using a processor, medical data about a patient, where the medical data corresponds to at least one patient visit to a healthcare provider; generating, using the processor, a first diagnosis about the patient during the current patient visit based on the medical data; generating, using the processor, a first predictive diagnosis regarding the patient's future symptoms based at least in part on the first diagnosis and a predictive model stored in a memory operably connected to the processor; and generating, using the processor, graphic data corresponding to a timeline view of the current patient visit and the first predictive diagnosis. Generating the graphic data includes generating a first graphic element corresponding to the first diagnosis, where the first graphic element further comprises a graphic indicator of the first diagnosis and at least one graphic sub - element, where at least one graphic sub - element is related to a physiological parameter selected from the medical data and the physiological parameter is related to the first diagnosis; generating a second graphic element corresponding to the first predictive diagnosis, where the second graphic element further comprises a graphic indicator of the first predictive diagnosis and at least one graphic sub - element, where at least one graphic sub - element is related to a physiological parameter related to the first predictive diagnosis; and further including generating a first graphic connector between the first graphic element and the second graphic element, where the first graphic connector indicates the progression of time between a first time and a second time of the current patient visit in the timeline view.

[0006] In other embodiments, a computing system configured to generate a user interface for a patient's treatment history includes a memory and a processor operably connected to the memory. The memory is configured to store medical data regarding the patient, a prediction model, and stored program instructions corresponding to at least one patient visit to a healthcare provider. The processor executes the stored program instructions to generate a first diagnosis for the patient during a current patient visit based on the medical data, generate a first predictive diagnosis regarding the patient's future symptoms based at least in part on the first diagnosis and the prediction model, and generate graphic data corresponding to a timeline view of the current patient visit and the first predictive diagnosis. The processor is further configured to generate a first graphic element corresponding to the first diagnosis, the first graphic element further comprising a graphic indicator of the first diagnosis and at least one graphic sub-element, the at least one graphic sub-element being related to a physiological parameter selected from the medical data, the physiological parameter being related to the first diagnosis; generate a second graphic element corresponding to the first predictive diagnosis, the second graphic element further comprising a graphic indicator of the first predictive diagnosis and at least one graphic sub-element, the at least one graphic sub-element being related to a physiological parameter related to the first predictive diagnosis; and generate a first graphic connector between the first graphic element and the second graphic element, the first graphic connector being further configured to indicate the passage of time between a first time and a second time of the current patient visit in the timeline view.

[0007] To facilitate identification of any particular element or act of description, the most significant digit of a reference number refers to the figure number in which the element is first introduced.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

[0009] These and other advantages, effects, features, and objectives will be better understood from the following description. In the description, reference is made to the accompanying drawings which form a part hereof and in which are shown, by way of illustration and not limitation, embodiments of the concepts of the invention. Corresponding reference numerals indicate corresponding parts throughout several views of the drawings.

[0010] The concept of the present invention is susceptible to various modifications and alternative forms, and illustrative embodiments thereof are shown by way of example in the drawings and described in detail herein. However, the following description of the illustrative embodiments does not limit the concept of the present invention to the specific forms disclosed, but rather, the intention is to cover all advantages, effects, and features that fall within the spirit and scope defined by the embodiments described herein and the following embodiments. Therefore, reference should be made to the embodiments described herein and the following embodiments to interpret the scope of the concept of the present invention. It should be noted that the embodiments described herein may also have useful advantages, effects, and features when solving other problems.

[0011] Here, with reference to the accompanying drawings showing some, but not all, embodiments of the concept of the present invention, devices, systems, and methods are described more fully below. In fact, the devices, systems, and methods may be embodied in many different forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will satisfy applicable legal requirements.

[0012] Similarly, many modifications and other embodiments of the devices, systems, and methods described herein will come to mind to those skilled in the art to which this disclosure pertains, having the benefit of the teachings presented in the foregoing description and the associated drawings. Therefore, it is to be understood that the devices, systems, and methods are not limited to the specific embodiments disclosed, and that modifications and other embodiments are intended to be included within the scope of the embodiments. Specific terms are used herein, but they are used only in a general and descriptive sense and not for purposes of limitation.

[0013] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains. Although any methods and materials similar or equivalent to those described herein can be used in the practice or testing of the methods, the preferred methods and materials are described herein.

[0014] Furthermore, references to an element by the indefinite article "a" or "an" do not exclude the possibility of there being more than one element, unless the context clearly requires that there be one and only one element. Thus, the indefinite article "a" or "an" typically means "at least one." Similarly, the terms "having," "comprising," or "including," or any grammatical variations thereof, are used in a non-exclusive manner. Thus, these terms can refer to both situations where no additional features exist in the entity described in this context other than the features introduced by these terms, and situations where one or more additional features exist. For example, the expressions "A has B," "A comprises B," and "A includes B" can all refer to situations where no other elements exist in A other than B (i.e., situations where A consists solely and exclusively of B), or situations where one or more additional elements such as element C, elements C and D, or additional elements exist in A in addition to B.

[0015] As used herein, the term "person with diabetes" (PwD) refers to a patient diagnosed with or at risk of being diagnosed with one or more forms of diabetes, including prediabetes, type 1 diabetes, type 2 diabetes, gestational diabetes, and one or more co-morbidities associated with diabetes. In certain embodiments described herein, the PwD is a patient of a healthcare provider (HCP), and references to the PwD and the patient are used interchangeably herein. Certain embodiments described herein are directed to improving the user interface for a patient treatment history of a PwD for an HCP, but the systems and methods described herein are not limited to the treatment of PwDs and can be used to implement an improved user interface for the treatment of other diseases and conditions, particularly chronic conditions that require long-term treatment.

[0016] As used herein, the term "physiological parameter" refers to any quantifiable aspect of the physiological function of a PwD that is measured as part of providing medical data for diagnosing a new condition or tracking the status of a previously diagnosed condition. A non-limiting list of physiological parameters of interest for the treatment of diabetes and diabetes co-morbidities includes body mass index (BMI), blood pressure (BP), blood glucose, glycosylated hemoglobin (HbA1c), blood ketones, and estimated glomerular filtration rate (eGFR).

[0017] As used herein, the term "medical data" refers to including both medical diagnostic data and medical treatment data. Medical diagnostic data includes the identification of previous diagnoses, diagnostic test results, and records of previous and current physiological parameter values for a PwD. Medical diagnostic data optionally includes related genetic data, phenotypic data, demographic data, and socioeconomic data for a PwD. Medical treatment data includes records of previously prescribed medications or other medical treatments prescribed to a PwD during a previous patient visit. During a current patient visit, a clinical decision support system is configured to generate one or more prescribed treatments for a PwD based on the medical data, and the HCP can adopt the prescribed treatment or manually select a different course of action for the PwD.

[0018] As used herein, the term "prescribed treatment" refers to the course of any medical diagnostic test, medical diagnosis or prognostic algorithm, medical procedure, medical treatment, medication, diet and lifestyle modification, or other recommended action that is issued by or has the option of being issued by an HCP in the treatment history of a PwD. In particular, with respect to medications, the term "prescribed" is herein inclusive of both over-the-counter and prescription medications.

[0019] As used herein, the term "graphic data" refers to any form of encoded data that a computing device uses to generate a visually perceivable output, including text, geometry, photographs, icons, textures, etc., using a display device, printer, or other output device. Different forms of graphic data include both still image data and moving images such as animations and videos. Examples of graphic data include rasterized image data, vector graphic data, procedural graphic data, and combinations thereof. Examples of rasterized image data include graphic data that encodes an array of pixel values within an image, and the display device generates an output image formed from the array of pixel values. Rasterized image data may be compressed using JPEG, PNG, WEBP, or other compression formats suitable for static images, and may also be compressed using video compression codecs such as h.264, h.265, VP9, AV1, or other compression formats suitable for videos or animations. Examples of vector graphics include graphic data that encodes declarative parameters that describe the shape, color, placement, and other details of an image that a computing device processes to reproduce the image. Also, examples of vector graphics include Scalable Vector Graphics (SVG), graphics generated from Cascading Style Sheet (CSS) documents, Portable Document Format (PDF), and other suitable vector graphics formats. Procedural graphic data includes data encoded as instruction command data that a processor executes to dynamically generate graphic data. Examples of procedural graphic data include JavaScript, WebAssembly, WebGL, or HTML used in publicly available web browsers <canvas>Coded command parameters for controlling other scripting languages for rendering graphics as part of an element, or data encoded in a PostScript language that a computing device renders using a PostScript rendering engine. Further, markup language formats such as Hypertext Markup Language (HTML), Extensible Markup Language (XML), or a suitable markup language may be used to format the placement of one or more sets of graphic data that form graphic elements for generating a timeline view and other graphics described herein. In some configurations, a single computing system generates graphic data and executes a process to render the graphic data on a display device for a human user to view the graphics. As described in more detail below, in other configurations, a first computing system generates graphic data and transmits the graphic data to one or more computing systems that execute the task of rendering the graphics on one or more display devices so that one or more human users can view the graphics.

[0020] FIG. 1 shows a system 100 for providing clinical decision support information to an HCP using the adaptive user interface described herein. System 100 includes a clinical decision support (CDS) system 102, an electronic health record (EHR) service 120, an HCP terminal 128, and an optional PwD device 138. The CDS system 102, the EHR service 120, the HCP terminal 128, and the PWD device 138 are communicatively connected via a network 148.

[0021] The CDS system 102 of FIG. 1 utilizes one or more computing devices including one or more central processing units (CPUs), graphics processing units (GPUs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), other digital logic devices, or combinations thereof, depicted as the CDS processor 104 of FIG. 1, to perform the functions described herein. The CDS processor 104 is operably connected to a CDS memory 106 and a network transceiver 118. The CDS memory 106 includes one or more volatile data storage devices such as static and dynamic random access memories (RAM), and one or more non-volatile data storage devices such as magnetic storage drives, solid state storage drives, and optical storage drives. During operation, the CDS processor 104 reads and writes data to the CDS memory 106 to execute stored program instructions and to store data including medical data received from the HCP terminal 128 and the EHR service 120 and generated graphic data. The CDS processor 104 operates the network transceiver 118, which is a wired or wireless network interface controller that transmits and receives data over the network 148, to receive medical data and other commands from the HCP terminal 128, transmit and receive EHR data with the EHR service 120, and transmit graphic data of the timeline view user interface of the treatment history regarding the PwD to the HCP terminal 128. In some configurations, the CDS processor 104 also operates the network transceiver 118 to directly receive medical data from the PWD device 138 and transmit graphic data of the treatment history regarding the PwD to the PWD device 138.

[0022] In the CDS system 102, the CDS memory 106 stores CDS software 108, a diagnostic database 110, PwD medical data 112, graphic data 114, and a prediction model 116. The CDS software 108 includes stored program instructions that are executed so that the CDS processor 104 performs clinical support functions and generates graphic data corresponding to a timeline view of one or more prescribed treatments for treating the PwD over one or more diagnoses and a series of patient visits in the PwD. The CDS software 108 also implements one or more network interfaces, such as a web server or other network server, to enable the HCP terminal 128 to access the CDS system 102 and send commands, and to enable the CDS system 102 to send the generated graphic data described herein to the HCP terminal 128.

[0023] In the CDS memory 106, the diagnostic database 110 includes a stored set of logical rules used by the CDS system 102 to generate a diagnosis regarding the PwD based on the PwD's medical data. In one particular configuration, the diagnostic database 110 encodes guidelines from the medical standards of the American Diabetes Association (ADA) in diabetes. Alternative configurations use different medical guidelines or other algorithms to generate diagnoses and prescribed treatments. The CDS system 102 uses the diagnostic database 110 to generate graphic elements that display diagnoses and prescribed treatments in an automated manner during operation of the system 100, although the HCP may optionally use the HCP terminal 128 to override the proposed diagnosis or course of action recommendations.

[0024] In the CDS memory 106, the PwD medical data 112 includes both any relevant medical data in the PwD during the current patient visit and historical medical record data including medical data in one or more previous patient visits. The PwD medical data 112 optionally includes the PwD medical data received by the CDS system 102 from the EHR service 120, historical medical data stored in the electronic health record for the PwD, and data received from external laboratory tests, home diagnostics such as spot and continuous glucose meter devices, and medical data provided by the HCP to the CDS system 102 via the HCP terminal 128 during the patient visit. Further, during operation, the CDS system 102 optionally transmits updated medical data in the PwD to the EHR service 120 to reflect updated measurements in physiological parameters, diagnoses, or to record prescribed medications or other medical treatments received by the PwD during the course of treatment.

[0025] In the CDS memory 106, the graphic data 114 includes a graphic display of a timeline view of the treatment history in the PwD over a series of one or more patient visits based on the PwD medical data 112. For example, the graphic data 114 forms a timeline view that includes graphic elements and sub-elements to show one or more diagnoses and associated physiological parameters, prescribed treatments, prescribed medications, diagnostic tests, and graphic connectors linking the graphic elements within the timeline view. In some configurations, the graphic data 114 further includes stored text, icons, geometric templates, and other visually perceivable data used by the CDS system 102 to adaptively generate a timeline view in the PwD based on the PwD medical data 112.

[0026] In the CDS memory 106, the prediction model 116 is embodied as, for example, a probabilistic model or a machine learning model. Examples of probabilistic models include Markov chains, Markov decision processes, semi-Markov chains, or semi-Markov decision processes. Further details of these probabilistic models implemented in the CDS system 102 are given in more detail below. These prediction models are described in more detail herein as non-limiting examples for illustrative purposes, but another configuration of the CDS system 102 can utilize prediction models that incorporate different probabilistic models or rely on machine learning models to generate predictions of disease progression. For example, recurrent neural networks such as general artificial neural networks (ANNs), particularly long short-term memory (LSTM) neural networks, may be used to generate disease progression predictions. Generally, any prediction model known in the art and suitable for generating predictive diagnoses may be utilized in the CDS system 102.

[0027] As is known in the art, a Markov chain models the probability of transitions between states, where each state corresponds to a stage in the progression of a disease based on the current state, the current state being the currently diagnosed symptoms of the PwD and optionally other known information about the PwD associated with the state of the PwD in the Markov chain. The Markov chain provides probability values for transitioning to different states based on discrete time increments, where the discrete time increments correspond to the time intervals between patient visits in the exemplary example of FIG. 1. Further, transitions that result in remaining in the current state, corresponding to the PwD remaining in a stable symptom through the next patient visit, are typically one potential outcome of state transitions in the Markov chain. A Markov decision process is a modified form of the Markov chain, in which the probability values of transitions to different states are determined based on the current state as in the Markov chain and further determined based on a decision or "action", where an action in the context of the CDS system 102 refers to a prescribed treatment that potentially affects the disease progression and as a result changes the probabilities of transitions to different states in the Markov decision model. In contrast, a Markov chain encodes information about different prescribed treatment options into the current state of the PwD, such that in addition to the diagnosed symptoms and other medical data, each prescribed treatment option corresponds to one of the current states in the set of current states of the PwD in the Markov chain, and the selection of a different prescribed treatment changes the current state of the PwD and the corresponding state transition probabilities in the Markov chain.

[0028] The semi-Markov chain and semi-Markov decision process prediction models refer to the above-mentioned deformations of the Markov chain and Markov decision process models, where the transition probabilities are further determined using the "sojourn time" parameter corresponding to the length of time a PwD has spent in the current state, which is determined based on the medical history data in PwD. For example, the semi-Markov chain and semi-Markov decision process prediction models treat a newly diagnosed patient with an elevated Hba1c level (sojourn time zero) differently from a patient who has experienced an elevated Hba1c level for one year, which in turn affects the probability values of the future progression of HbA1c levels or other diagnosed symptoms in the prediction model.

[0029] During the generation of the prediction model 116 for use in the CDS system 102, the exact probability values for each state transition are derived from empirical data such as epidemiological study data, actuarial tables, insurance claim data, and other sources of clinical data that provide statistical data related to the disease progression of diabetes and diabetic complications. The prediction model 116 is generated prior to the operation of the CDS system 102 and the system 100, as further described herein.

[0030] The EHR service 120 in FIG. 1 provides medical data about PwD to the CDS system 102 in the form of an EHR. In the exemplary embodiment of FIG. 1, the EHR service is a network computing service that includes a digital processor 122 and a memory 124 that stores EHR data 126 in PwD. The EHR data 126 is a digital record encoded in a standard format such as the Fast Healthcare Interoperability Resource (FHIR) format, a version of the Health Level Seven International (HL7) format, or other suitable electronic health record formats. In the embodiment of FIG. 1, the EHR service 120 operates independently of the CDS system 102, but in another configuration, the EHR service 120 and the CDS system 102 may be implemented as an integrated system. In an actual embodiment, the EHR data 126 about PwD may include data received from a plurality of data sources including an external diagnostic test service, an HCP operating the HCP terminal 128, the CDS system 102, and EHR data from other HCPs such as medical specialists who treat PwD for other medical conditions and co-morbidities.

[0031] The HCP terminal 128 of FIG. 1 is a desktop or laptop personal computer (PC), tablet, smartphone, or other suitable client computing device of the HCP that includes a terminal processor 130, a memory 132, and a display device 136. The HCP uses the HCP terminal 128 to provide medical data to the CDS system 102 and optionally the EHR service 120, and to receive and display graphic data corresponding to a timeline view of at least one patient visit in the PwD when the PwD is being treated over a series of visits by the HCP. In some configurations, the HCP also communicates with the PWD device 138 between patient visits using the HCP terminal 128, or performs remote patient visits in situations where the HCP provides telemedicine services to the PwD. In the embodiment of FIG. 1, the HCP terminal 128 executes stored program instructions within terminal software 134 stored in the HCP terminal memory 132 to enable the HCP terminal 128 to communicate with the CDS service 102. In one configuration, the terminal software 134 includes an operating system and web browser software that functions as a client for one or more web services provided by the CDS system 102, but in another configuration, the terminal software 134 is another client software program. During operation, the terminal processor 130 executes the terminal software 134 and operates the display device 136 to generate a visual output of the graphic data 114 generated by the CDS system 102 and transmitted to the HCP terminal 128. The display device 136 is, for example, a flat panel display screen or other electronic display device, but in some configurations, a printer may reproduce a graphic display of the timeline view on paper or other print media. In some configurations, the display device 136 incorporates a touch screen interface to enable the HCP to input data and modify the timeline view as described in more detail below, but in other configurations, the HCP terminal 128 incorporates a combination of a mouse, keyboard, voice input device, or other input device (not shown) to receive HCP input.

[0032] The PWD device 138 of FIG. 1 is another desktop or laptop PC, tablet, smartphone, or other suitable client computing device of the PwD that includes a device processor 140, a device memory 142 that stores PwD device software 144, and a display device 146. In some configurations, the PWD device 138 receives physiological parameter data from a monitoring device such as a spot or continuous blood glucose meter, a health tracking device such as a smartwatch, or other medical devices. The PWD device 138 is optionally configured to enable the PwD to perform telemedicine patient visits with an HCP via the HCP terminal 128 using video conferencing software and other telemedicine software known in the art and not described in further detail herein. In some configurations, the CDS system 102 transmits generated graphic data for a timeline view user interface of the treatment history in the PwD to the PWD device 138 for display using the display device 146 via the network 148. In other configurations, the HCP terminal 128 retransmits graphic data for a timeline view of the treatment history in the PwD to the PWD device 138 during a telemedicine patient visit.

[0033] FIG. 2 is a block diagram of a process 200 for the operation of a CDS system to generate a graphical timeline view user interface of current diagnosed symptoms, potential prescribed treatment options, and predictions in future disease progression over one or more future patient visits in PwD. Process 200 can be executed at any time, but for illustrative purposes, process 200 is described as occurring during a patient visit to generate a graphical timeline view of the current patient visit and one or more predictions for disease prediction. Process 200 is described in relation to system 100 of FIG. 1, and a reference to process 200 executing a function or operation refers to the operation of a processor, such as CDS processor 104 within CDS system 102, to execute stored program instructions, such as CDS software 108, to execute the function or operation.

[0034] Process 200 begins when CDS system 102 receives PwD medical data in at least one patient visit (block 204). In system 100, the processor 104 of CDS system 102 receives medical data from one or more sources including, but not limited to, EHR service 120, HCP terminal 128, and optionally PWD device 138. In particular, EHR service 120 provides medical data from previous patient visits, including previous diagnoses, prescribed medications and medical procedures, historical records of physiological parameter data measurements in the PwD, and optionally socioeconomic and demographic data regarding the PwD. During a patient visit, HCP terminal 128 optionally transmits physiological parameters and other medical data to CDS system 102 from automatically uploaded physiological parameters generated by a medical test device such as a blood glucose meter, based on manual input from the HCP, or both. Additionally, CDS system 102 may receive medical data regarding blood tests or other diagnostic tests that the PwD undergoes at an external diagnostic laboratory prior to a patient visit, directly from the diagnostic laboratory's computing system, via EHR service 120, or from HCP terminal 128. As described above, CDS system 102 stores the received PwD medical data 112 in CDS memory 106.

[0035] Process 200 continues (block 208) as CDS system 102 identifies the physiological parameters most relevant to the diagnosis during each patient visit. In the embodiment of FIG. 1, CDS processor 104 uses diagnostic database 110 to identify the physiological parameters within PwD medical data 112 that are most relevant to each diagnosis in a series of one or more patient visits. For example, if a patient visit includes a diagnosis that the PwD is not only obese but also has an uncontrolled HbA1c indicating the onset of type 2 diabetes, CDS processor 104 uses diagnostic database 110 to identify the physiological parameters most highly correlated with these diagnoses, such as the body mass index (BMI) related to obesity and the HbA1c level measured for the PwD. In many cases, PwD medical data 112 includes physiological parameters and other information not directly relevant to the diagnosis, and CDS processor 104 filters this data from the timeline view, although the HCP can, of course, access the complete PwD medical data 112 via the conventional user interface as needed.

[0036] Process 200 continues (block 212) with the CDS system 102 generating graphic elements of the diagnosed symptoms in the PwD during the current patient visit and one or more graphic elements of potential prescribed treatment options. The graphic elements of the diagnosed symptoms further include at least one graphic sub - element in one or more identified physiological parameters related to the diagnosis of the PwD. The graphic elements and graphic sub - elements provide a graphic indicator of the physiological parameter data that led to the diagnosis and the described treatment process. The graphic indicator refers to any type of graphic data within a timeline view that conveys specific information about the medical data in the PwD, the treatment prescribed for the PwD, or the recommendations for treatment prescribed for the PwD. The graphic sub - elements are a type of graphic element that is subordinate to other graphic elements within the timeline view, and the CDS system 102 either generates the graphic data in the graphic sub - elements within the boundaries of the parent graphic element or otherwise associates each graphic sub - element with the parent graphic element. The graphic elements and sub - elements provide a clear display of the relationship between the graphic elements in the patient visit and one or more graphic sub - elements related to the patient visit. The CDS system 102 uses the diagnostic database 110 to identify potential prescribed treatments related to the diagnosed symptoms and generates a graphic element for each potential prescribed treatment option, such as the type of medication, diagnostic test, or other medical treatment, and optionally includes additional useful information regarding the prescribed treatment in the HCP.

[0037] Figure 3 shows an example of a timeline view 300 that includes a graphic element 302 indicating the diagnosis for the PwD during the current patient visit and a graphic element 306 indicating treatment options for the PwD. In a specific example of the timeline view 300, the diagnosis in the current visit includes a diagnosis of chronic kidney disease (CKD) in a person with type 2 diabetes. CKD is a known comorbidity in the PwD, which is also known to be a progressive condition.

[0038] In the timeline view 300, the graphic element 302 is shown as a rectangular graphic element that includes a graphic indicator of a first diagnosis, which is a text label indicating the diagnosis of type 2 diabetes and stage 2 CKD in the example of FIG. 3. The graphic element 302 further includes graphic sub-elements 304a and 304b located inside the graphic element 302. The graphic sub-element 304a is shown as a circle that includes a graphic indicator of a physiological parameter, HbA1c within the upper semi-circle, and a measured value of HbA1c for PwD within the lower semi-circle. The HbA1c physiological parameter is related to the diagnosis of type 2 diabetes. Similarly, the graphic sub-element 304b is shown as another circle that includes a graphic indicator of another physiological parameter, estimated glomerular filtration rate (eGFR) within the upper semi-circle, and a numerical value of eGFR within the lower semi-circle. The eGFR physiological parameter is related to the diagnosis of stage 2 CKD. In some configurations, the graphic data of the graphic sub-elements of each physiological parameter provides additional information to the HCP that exceeds the quantitative value of the physiological parameter. For example, in some configurations, the physiological parameter data is displayed using color-coded text or color-coded graphics within the graphic sub-element to indicate whether the physiological parameter is within or outside the range for a particular PwD. Using the HbA1c physiological parameter 302a as an example, green can indicate an HbA1c value considered normal for a healthy individual, yellow can indicate an elevated HbA1c for non-insulin-dependent diabetes, and red can indicate an even more elevated HbA1c indicating the need for insulin treatment. In some configurations, the graphic sub-elements of the physiological parameters also include arrows or other graphic indicators that display the trend of the physiological parameters over time from previous patient visits, such as upward or downward arrows indicating an increasing or decreasing trend of the HbA1c level or a change in other related physiological parameters. In some configurations, the graphic indicators of the physiological parameters include graphs, icons, or other non-text graphic indicators that can be easily interpreted by the HCP to evaluate the symptoms of the PwD.

[0039] In the timeline view 300, the graphic element 306 is shown as a rectangular graphic element that includes graphic indicators of the prescribed treatment options for the diagnosed CKD conditions. In the example of FIG. 3, the graphic element 306 includes a graphic depiction of a list of CKD treatment options that includes medications related to blood pressure and cholesterol known to affect the progression of CKD, along with options to stop smoking and changes to diet and exercise for PwD. During operation, the CDS processor 104 identifies the treatment options prescribed based on the diagnosed conditions in the PwD along with other relevant PwD medical data 112, and identifies the options for the prescribed treatment from the diagnostic database 110. For example, in FIG. 3, the prescribed treatment to stop smoking for the PwD is generated only for PwDs who have a smoking history as recorded in the PwD medical data 112. The graphic element 306 is also referred to as a trigger graphic element for the prescribed treatment because the HCP can optionally select the graphic element 306 to trigger one or more of the recommended treatment options. In one embodiment, one or more of the prescribed treatment options are displayed using clickable hyperlinks or using associated graphic control buttons to enable the HCP to select the prescribed treatment options. The CDS system 102 then generates a pop-up window or user interface screen (not shown) to enable the HCP to implement the selected prescribed treatment options such as prescribing medications or enrolling the PwD in a smoking cessation or diet and exercise program.

[0040] Referring again to FIG. 2, process 200 continues (block 216) with the CDS processor 104 generating one or more predictive diagnoses in the patient's future symptoms, at least in part based on the first diagnosis in the current patient visit and the predictive model 116 stored in the CDS memory 106. As described above, in a Markov chain, a Markov decision process, or a variation thereof, the CDS processor 102 uses the diagnosis to identify the current state in the predictive model corresponding to the diagnosis of the PwD. The CDS processor 102 identifies any state linked to the current state in the model as a predictive diagnosis, in a state where the transition probabilities in the predictive model correspond to the likelihood of each predictive diagnosis. For some predictive diagnoses, the CDS processor 102 also uses the prescribed treatment options, in addition to the first diagnosed symptoms in the PwD from the current patient visit, to identify the predictive diagnosis in the predictive model and the associated probability values in the predictive diagnosis. For example, in the example of FIG. 3, the CDS processor 102 generates a predictive diagnosis in the PwD if no further prescribed treatment is given to the PwD to establish a baseline prediction regarding disease progression such as CKD progression in the PwD. Also, the CDS processor 102 uses the recommended prescribed treatment from the diagnostic database 110 to identify, in addition to the current state of the PwD in the Markov decision process, different current states regarding the PwD in the Markov chain or as action inputs. In at least some examples, the treatment prescribed for the PwD affects the probability values in the future predictive diagnoses, and the predictive model 116 returns a set of one or more predictive diagnoses with different corresponding probability values compared to the baseline prediction in disease progression without treatment. In some cases, the predictive model generates multiple sets of predictive diagnoses regarding multiple different prescribed treatment options. Further, in some embodiments, the CDS processor 104 provides additional medical data from the PwD medical data 112 as input to the predictive model 116 to improve the predictive diagnosis results. For example, demographic and other relevant medical risk factor data in PwDs beyond the currently diagnosed symptoms (e.g., if the PwD smokes) can be provided to the predictive model 116 to generate a predictive diagnosis.Furthermore, in an embodiment of the predictive model 116 that uses a semi-Markov chain or a semi-Markov decision process, the CDS processor 102 also provides data corresponding to the period during which the PwD remained stable in the diagnosis of the current patient visit to the predictive model 116 as the "sojourn time".

[0041] Process 200 continues (block 220) with the CDS processor 104 generating graphic elements in one or more of the predictive diagnoses based on the ranking of probabilities in the predictive diagnoses returned from the prediction model 116. In the exemplary embodiment of FIG. 2, the CDS processor 104 identifies the predictive diagnosis with the highest probability as the top-ranked predictive diagnosis for each potential prescribed treatment option, such as the aforementioned CKD treatment options and the no additional treatment baseline option. As described below, during operation, the HCP may provide user input to view additional predictive diagnoses with lower probability values to consider different potential disease progression outcomes for the PwD. Another configuration may use other ranking processes, such as a predetermined probability threshold for the predictive diagnoses, and select any predictive diagnosis that exceeds the predetermined probability threshold. The CDS processor 104 generates the graphic elements for each selected predictive diagnosis, along with a graphic indicator of the predictive diagnosis and at least one graphic sub-element related to the physiological parameters associated with the predictive diagnosis. In particular, the at least one graphic sub-element includes a graphic indicator of the range of values of the physiological parameters corresponding to the predictive diagnosis. The CDS processor 104 generates the graphic elements for each predictive diagnosis using at least one of a shape, color, or label different from the corresponding shape, color, or label of the graphic elements of the initially diagnosed symptoms, indicating that the graphic elements correspond to future predictive diagnoses. The distinction between the graphic elements in the current or past diagnoses and the graphic elements in the predictive diagnoses assists the HCP in quickly evaluating the information in the timeline view and reduces the likelihood that the HCP will misinterpret the predictive diagnoses as the PwD's existing diagnoses. In the embodiments described herein, the graphic elements of the predictive diagnoses include rectangles with rounded corners compared to the right-angled corners of the graphic elements in the initial diagnosis in the current patient visit, although in another embodiment, the predictive diagnoses can be distinguished by using different colors, text within the label or graphic icons, or combinations of different shapes, colors, and labels.

[0042] Referring to FIG. 3, the timeline view 300 includes graphic elements 312 and 320 for predictive diagnosis. In the timeline view 300, the graphic elements 312 and 320 in predictive diagnosis show a predictive diagnosis regarding the symptoms of the PwD at a future patient visit, which is a six-month time span in the example of FIG. 3. The graphic element 312 is a predictive diagnosis having the highest probability value in the prediction model 116 in response to the execution of the prescribed treatment regarding CKD shown in the graphic element 306. The graphic element 312 includes a graphic indicator in a predictive diagnosis which, in this case, is "type 2 diabetes / stage 2 CKD" and a text label "prediction: stable" indicating the prediction that the PwD remains with the same general symptoms as diagnosed in the current patient visit. The graphic element 312 also includes graphic sub-elements 314a and 314b of the estimated ranges of relevant physiological parameters related to the predictive diagnosis. The graphic sub-element 314a includes a graphical depiction of the estimated range of HbA1c, and the graphic sub-element 314b includes a graphical depiction of the estimated range of eGFR. In FIG. 3, the graphic element 320 is a predictive diagnosis having the highest probability value in the prediction model 116 in response to no further treatment being performed. The graphic element 320 includes a graphic indicator in a predictive diagnosis which, in this case, is "type 2 diabetes / stage 3 CKD" and a text label "prediction: progression" indicating the prediction that the PwD experiences progression from the symptoms diagnosed in the current patient visit to disease symptoms. The graphic element 320 also includes graphic sub-elements 322a and 322b of the estimated ranges of the values of relevant physiological parameters related to the predictive diagnosis. The graphic sub-element 322a includes a graphical depiction of the estimated range of HbA1c, and the graphic sub-element 322b includes a graphical depiction of the estimated range of eGFR, which is a different range from the predicted value in the graphic sub-element 314a due to the prediction of the progression of CKD symptoms regarding the PwD. In the examples disclosed herein, the graphic sub-elements of the predicted physiological parameters include ranges of multiple estimated values in the relevant physiological parameters, but in another configuration, the range is instead a single predicted physiological parameter value.As described above, graphic elements 312 and 320 include rectangles having rounded corners, which are different from the right-angled shape of graphic element 302 regarding the diagnosis in the current patient visit. Further, the text labels within graphic elements 312 and 320 indicated that the diagnosis was a prediction.

[0043] Referring again to FIG. 2, process 200 continues (block 224) by the CDS processor 104 generating graphic data corresponding to a timeline view that includes the graphic elements described above in connection with the processing of blocks 212-220, as well as graphic connectors connecting these graphic elements, and a timeline slider that enables dynamic adjustment of the timeline view. In addition to including the placement of previously generated graphic elements, the timeline view generates one or more graphic elements indicating the time range during which the treatment visited and prescribed by the patient is to be performed. The timeline view further includes a timeline slider that enables the HCP to adjust the size of the time range shown in the timeline view and move the time range shown in the timeline view forward and backward in time.

[0044] When generating graphic data corresponding to the timeline view at block 224 of process 200, the CDS system 102 uses the CDS processor 104 and the network transceiver 118 to transmit the generated graphic data for the timeline view user interface to the client HCP terminal 128 via the network 148. The HCP terminal 128 receives the graphic data, and the terminal processor 130 executes terminal software 134 such as a web browser or other client software, and uses the display device 136 provided on the HCP terminal 128 to generate a rendered user interface with a visual depiction of the timeline view. The HCP interacts with the user interface using the HCP terminal 128, and as described below, the HCP optionally provides input to the HCP terminal to update the timeline user interface, and the CDS system 102 receives this input via the network 148 and processes it to provide an updated set of graphic data in the updated timeline view to the HCP terminal 128. Further, in some configurations, the CDS system 102 optionally transmits the generated graphic data in the timeline view user interface to the PWD device 138 for direct display on the PwD using the display device 146. The system 100 is embodied as a network system in which the CDS system 102 is connected to the HCP terminal 128 via the network 148 for illustrative purposes, but in other configurations, a single computing system executes the operations of both the CDS system 102 and the HCP terminal 128. In this configuration, a processor within the single computing system generates graphic data corresponding to the timeline view of the patient visit and operates a display device provided within the single computing system to display the graphic data corresponding to the timeline view of the patient visit.In one configuration, a single computing system is the HCP terminal 128 that is further reconfigured to host CDS software 108, diagnostic database 110, PwD data 112, graphic data 114, and prediction model 116 in addition to the terminal software 134.

[0045] Referring back to FIG. 3, the timeline view 300 includes the aforementioned graphic elements 302, 306, 312, 320 arranged linearly along a timeline indicated by a timeline graphic element 324. The timeline graphic element 324 includes date information (September 2021) regarding the time of the current patient visit and the scheduled time of a future patient visit (March 2022) corresponding to the time range of the predicted diagnosis. A timeline slider graphic element 326 within the timeline view graphic element 324 enables an HCP to adjust the time range shown in the timeline view 300. Although not described in further detail herein, the timeline slider 326 enables an HCP to view previous patient visits and old medical histories in the PwD based on the PwD medical data 112, and as will be described in further detail below, the timeline slider 326 enables an HCP to view predicted diagnoses in further future patient visits. The graphic connectors show the relationships between the current patient visit graphic element 302, the prescribed treatment trigger graphic element 306, and the predicted diagnosis graphic elements 312 and 320. In FIG. 3, the graphic connectors are formed as straight or curved connectors having arrows indicating the flow of time in the timeline view 300. In particular, the graphic connector formed from graphic sub-connectors 308a and 308b connects the current patient visit diagnosis graphic element 302 to the predicted diagnosis graphic element 312 via the prescribed treatment graphic element 306. The graphic sub-connectors 308a and 308b link the current diagnosis, the prescribed treatment, and the predicted future diagnosis in a structure that is easily understandable to an HCP. Another graphic connector 316 links the current patient visit diagnosis graphic element 302 to the predicted diagnosis graphic element 320, which shows the most probable predicted diagnosis in the PwD if the PwD does not receive further treatment. The timeline view 300 also includes a graphic display of the probabilities in each of the predicted diagnoses associated with the corresponding graphic connectors within the timeline view.For example, an expected probability value 310 is positioned in relation to the graphic sub - connector 308a or 308b (308b in the example of FIG. 3), and another expected probability value 318 is associated with the graphic connector 316. The expected probability value is the expected probability for reaching the corresponding predicted diagnosis generated from the prediction model 116. In the example of FIG. 3, the expected probability value is a graphic indicator displayed as a numerical value in the range from 0.0 to 1.0. However, in other embodiments, the expected probability value may be a ranked value (e.g., the first, second, and third with the highest probabilities), or qualitatively as a percentage, such as by adjusting the thickness or color of the graphic connector line to indicate the likelihood of a particular predicted diagnosis. FIG. 3 also shows a ranking selector widget 330 embodied as a dropdown selector input in the timeline view 300. The ranking selector widget enables an HCP or other user to adjust the ranking threshold in the predicted diagnoses displayed in the timeline view. In the exemplary example of FIG. 3, the default rank is set to display only the predicted diagnosis with the highest rank (1) in the timeline view 300.

[0046] As will be appreciated by those skilled in the art, the processing of steps 212 - 220 may be performed in a different order than that described above, or simultaneously. Further, the timeline view shown herein is arranged in a left - to - right format representing the current time to future time of patient visits for predicted diagnoses. However, another configuration can orient the timeline in a right - to - left format or vertically in an up - to - down or down - to - up format. Additionally, another configuration of the process 200 can include different visual formats and arrangements of the graphic elements, graphic sub - elements, and graphic connectors shown herein.

[0047] Referring again to FIG. 2, during process 200, the HCP has the option to modify the timeline view to adjust the timeline range (block 228), adjust the ranking threshold (block 240), or adjust both the timeline range and the ranking threshold. In particular, the time range in the predictive diagnosis is extended to the next patient visit in the default timeline view of FIG. 3, and the HCP has the option to extend the time range to cover one or more future patient visits. To adjust the timeline range, the HCP operates the HCP terminal 128 to select the timeline slider 326 and drags the timeline slider to the right with a click-and-drag operation or other appropriate user input. The CDS processor 104 uses the prediction model 116 and uses the existing predictive diagnosis and other estimated data as inputs to the prediction model to identify further predictive diagnoses in the future time range in a manner similar to that described in the processing of block 216 (block 232). The CDS processor 104 generates updated graphic data including additional graphic elements for further predictive diagnoses in future patient visits in the timeline view (block 236), and the HCP terminal 128 or other client computing device displays the updated timeline view.

[0048] Figure 4 shows an example of an extended timeline view 400 generated by the CDS system 102 in response to an input for displaying a predictive diagnosis in two future patient visits. The timeline view 400 includes elements of the timeline view 300 with a timeline graphic element 324 that here displays a larger time range including the second future patient visit in September 2022. In the example of FIG. 4, the graphic element 412 represents a second predictive diagnosis for the stable symptoms of the PwD if the PwD continues to receive the prescribed treatment for the CKD shown in the graphic element 306. The graphic sub-elements 414a and 414b respectively show the estimated HbA1c and eGFR physiological parameter range values. The graphic connector 406 shows the progression from the predictive diagnoses in the graphic elements 312 and 412, and the expected probability indicator 404 shows the likelihood of the predictive diagnosis 412 along a given treatment path. Similarly, the graphic element 420 shows a second predictive diagnosis of the continuation of the progression of diabetes with stage 3 CKD if the PwD does not receive further treatment. The graphic element 420 includes predictions of a further elevated HbA1c level range in the graphic sub-element 422a and a further decreased eGFR level range in the graphic sub-element 422b. The graphic connector 418 connects the previous predictive diagnosis of the graphic element 320 to the graphic element 420, and the expected probability indicator 416 shows the likelihood of the predictive diagnosis 420 along a given treatment path.

[0049] Referring again to FIG. 2, to adjust the ranking threshold (block 240), the HCP terminal 128 receives input from the HCP via the ranking selector widget 330, adjusts the ranking threshold in the number of predictive diagnoses, and displays it in the timeline view. The ranking selector widget 330 shown herein selects based on a numerical rank, but in another configuration, the ranking threshold is the minimum probability value corresponding to the likelihood of a given predictive diagnosis in the prediction model 116. The CDS system 102 receives the updated ranking threshold data, and the CDS processor 104 uses the prediction model 116 to identify all predictive diagnoses that meet the updated ranking threshold. The CDS processor 104 generates updated graphic data for the timeline view that includes graphic elements for newly added predictive diagnoses or, potentially, removes graphic elements for predictive diagnoses with expected probability values less than the new ranking threshold if the ranking threshold is increased. The CDS processor 104 generates graphic data for the updated timeline view for predictive diagnoses having an expected probability exceeding the ranking threshold (block 244), and the HCP terminal 128 or other client computing device displays the updated timeline view.

[0050] FIG. 5 shows an example of a timeline view 500 generated by the CDS system 102 in response to an input for adjusting a ranking threshold so as to show a predictive diagnosis having both the highest probability and the second highest probability in the prediction model 116. The timeline view 500 includes the graphic elements of FIG. 3, along with additional graphic elements 520 for newly generated predictive diagnoses, and additional connector graphic elements 508 and 516 having corresponding expected probability graphic indicators 504 and 512. Further, the ranking selector widget 330 displays a "2" indicating that the predictive diagnoses having the highest and second highest (ranked first and second) expected probabilities within the prediction model 116 are included in the timeline view 500. More specifically, the graphic element 520 shows other predictive diagnoses that, if the PwD does not receive treatment for a CKD diagnosis, the PwD will experience an acceleration in the progression of diabetes with a further increase in HbA1c level and an acceleration in the progression to stage 4 CKD with a further decrease in eGFR level by the time of the next scheduled patient visit. The graphic element 520 includes graphic sub-elements 522a and 522b showing the estimated ranges of HbA1c and eGFR, respectively. FIG. 5 also includes a new graphic sub-connector 508 that connects the graphic element 306 to the graphic element 320, indicating that there is some probability that the PwD will progress to stage 3 CKD even if the PwD receives the recommended CKD treatment. The timeline view 300 displays both the predicted branch having the graphic sub-connector 308b and the associated graphic indicator of the expected probability value 310, along with the sub-connector 508 having the graphic indicator of the lower expected probability value 504. Similarly, the graphic connector 516 connects the graphic element 302 for the diagnosis in the current patient visit to the graphic element 520 of the third predictive diagnosis. The graphic indicator 512 of the expected probability displays the expected probability value that the PwD will reach an advanced CKD stage, which is a lower probability value than the graphic indicator of the expected probability 318 of the branched graphic connector 316.In this way, the process 200 illustrated in the timeline view 500 enables an HCP to view a greater or lesser number of predictive diagnoses and generates a display of how different treatment paths diverge or converge with predicted symptoms.

[0051] The embodiments described herein enable the generation of a timeline view user interface that presents relevant diagnoses, predictive diagnoses, physiological parameters, and recommended prescribed treatment options to an HCP. The user interface reduces the cognitive burden on the HCP and enables more efficient and effective treatment of PwDs and other patients. When integrated into the clinical workflow, the embodiments described herein can assist an HCP in making improved individualized treatment decisions that improve clinical, patient-reported, and economic outcomes. In particular, the embodiments described herein enable an HCP to collaborate with existing clinical guidelines for treatment transitions in diabetes in an efficient manner, which can be cumbersome to follow or apply considering the amount of patient data in prior art systems. Further, the embodiments described herein enable an HCP to consider one or more potential future diagnoses that are likely to result from various prescribed treatment options, thereby enabling the HCP to analyze and discuss various treatment options with PwDs in an efficient and effective manner.

[0052] This disclosure is described in relation to what is considered to be the most practical and preferred embodiments. However, these descriptions are presented by way of example and are not intended to be limiting of the disclosed embodiments. Accordingly, as will be understood by those skilled in the art, this disclosure encompasses all modifications and alternative configurations within the spirit and scope of this disclosure and as set forth in the following claims.< / canvas>

Claims

1. A method for generating a user interface of a predicted disease progression for a patient, the method comprising: receiving, using a processor, medical data for the patient, the medical data being medical data of the patient corresponding to at least one patient visit to a healthcare provider; generating, using the processor, a first diagnosis for the patient based on the medical data during a current patient visit; generating, using the processor, a first predictive diagnosis regarding future symptoms of the patient based at least in part on the first diagnosis and a prediction model stored in a memory operably connected to the processor; generating, using the processor, graphic data corresponding to a timeline view of the current patient visit and the first predictive diagnosis; comprising; generating the graphic data comprises: generating a first graphic element corresponding to the first diagnosis, the first graphic element comprising: a graphic indicator of the first diagnosis; at least one graphic sub-element, the at least one graphic sub-element being related to a physiological parameter selected from the medical data, the physiological parameter being related to the first diagnosis; generating a first graphic element further comprising; generating a second graphic element corresponding to the first predictive diagnosis, the second graphic element comprising: a graphic indicator of the first predictive diagnosis; at least one graphic sub-element, the at least one graphic sub-element being related to a physiological parameter related to the first predictive diagnosis; generating a second graphic element further comprising; generating a first graphic connector between the first graphic element and the second graphic element, the first graphic connector indicating the progression of time between a first time and a second time of the current patient visit in the timeline view; a method further comprising.

2. Further comprising generating, using the processor, a second predictive diagnosis regarding the future symptoms of the patient, at least partially based on the first diagnosis, the recommended prescribed treatment, and the prediction model, Generating, using the processor, the graphic data corresponding to the timeline view, Generating a third graphic element including a graphic indicator of the recommended prescribed treatment, Generating a fourth graphic element corresponding to the second predictive diagnosis, the fourth graphic element comprising A graphic indicator of the second predictive diagnosis, and At least one graphic sub - element related to a physiological parameter related to the second predictive diagnosis, Generating a fourth graphic element further comprising the at least one graphic sub - element, Generating a second graphic connector between the first graphic element and the fourth graphic element, the second graphic connector indicating the progression of time between the first time and the third time of the current patient visit in the timeline view, The method according to claim 1, further comprising.

3. The second connector Comprises a first sub - connector connecting the first graphic element to the third graphic element and a second sub - connector connecting the third graphic element to the fourth graphic element, The method according to claim 2, further comprising.

4. Generating the second graphic connector Further comprises generating, using the processor, a graphic indicator of the expected probability for the second predictive diagnosis associated with the second graphic connector The method according to claim 2, further comprising.

5. The method according to claim 1, wherein the processor generates the second graphic element having at least one of a shape, color, or label different from the corresponding shape, color, or label of the first graphic element to indicate that the second graphic element corresponds to a future predictive diagnosis.

6. Generating the first graphic connector Using the processor, generating a graphic indicator of the expected probability for the first predictive diagnosis associated with the first graphic connector The method according to claim 1, further comprising:

7. Using the processor, further comprising generating a second predictive diagnosis regarding the future symptoms of the patient, at least partially based on the first predictive diagnosis and the prediction model, Using the processor, generating the graphic data corresponding to the timeline view Generating graphic data corresponding to a timeline slider in the timeline view In response to user input to the timeline slider moving to the third time in the timeline view during a third time occurring after the second time, generating a third graphic element related to the second predictive diagnosis in the medical data, the third graphic element being A graphic indicator of the second predictive diagnosis At least one graphic sub-element, the at least one graphic sub-element being related to a physiological parameter related to the second predictive diagnosis, generating a third graphic element further comprising the at least one graphic sub-element Generating a second graphic connector between the second graphic element and the third graphic element, the second graphic connector indicating the progression of time between the second time of the first predictive diagnosis and the third time of the second predictive diagnosis in the timeline view, generating the second graphic connector The method according to claim 1, further comprising:

8. The method according to claim 7, further comprising using the processor to generate a graphic indicator of the expected probability for the second predictive diagnosis associated with the second graphic connector

9. Using the processor, generating the first predictive diagnosis regarding the future symptoms of the patient, at least partially based on the first diagnosis and the prediction model, the first predictive diagnosis having the highest probability in the prediction model, generating the first predictive diagnosis ​ Using the processor, generating a second predictive diagnosis regarding the future symptoms of the patient, at least partially based on the first diagnosis and the prediction model, wherein the second predictive diagnosis has the second highest probability in the prediction model. Further comprising Using the processor, generating the graphic data corresponding to the timeline view comprises Generating a third graphic element corresponding to the second predictive diagnosis, wherein the second graphic element Is a graphic indicator of the second predictive diagnosis; and At least one graphic sub-element, wherein the at least one graphic sub-element is related to a physiological parameter related to the second predictive diagnosis. Generating a third graphic element further comprising Generating a second graphic connector between the first graphic element and the third graphic element, wherein the second graphic connector indicates the progression of time between a first time and a second time of the current patient visit in the timeline view. Generating a second graphic connector. The method according to claim 1, further comprising **Claim 10** A computing system configured to generate a user interface for a treatment history of a patient, the computing system comprising: Medical data regarding the patient corresponding to at least one patient visit to a healthcare provider; A prediction model; Stored program instructions; A memory configured to store; A processor operably connected to the memory Comprising The processor is Generating a first diagnosis regarding the patient during the current patient visit based on the medical data; Generating a first predictive diagnosis regarding the future symptoms of the patient, at least partially based on the first diagnosis and the prediction model; Generating graphic data corresponding to a timeline view of the current patient visit and the first predictive diagnosis; Configured to execute the stored program instructions as described above, and the processor is Generating a first graphic element corresponding to the first diagnosis, wherein the first graphic element Is a graphic indicator of the first diagnosis; At least one graphic sub - element, wherein the at least one graphic sub - element is related to a physiological parameter selected from the medical data, and the physiological parameter is related to the first diagnosis, and at least one graphic sub - element; Generating a first graphic element, further comprising; Generating a second graphic element corresponding to the first predicted diagnosis, wherein the second graphic element; A graphic indicator of the first predicted diagnosis; At least one graphic sub - element, wherein the at least one graphic sub - element is related to a physiological parameter related to the first predicted diagnosis, and at least one graphic sub - element; Generating a second graphic element, further comprising; Generating a first graphic connector between the first graphic element and the second graphic element, wherein the first graphic connector indicates the progression of time between a first time and a second time of the current patient visit in the timeline view, and generating a first graphic connector; Further configured to perform; A computing system.

11. The processor; Generates a second predicted diagnosis regarding the future symptoms of the patient, at least partially based on the first diagnosis, the recommended prescribed treatment, and the prediction model; Generates the graphic data corresponding to the timeline view; Further configured as such, wherein the timeline view; A third graphic element including a graphic indicator of the recommended prescribed treatment; A fourth graphic element corresponding to the second predicted diagnosis, wherein; A graphic indicator of the second predicted diagnosis; At least one graphic sub - element, wherein the at least one graphic sub - element is related to a physiological parameter related to the second predicted diagnosis, and at least one graphic sub - element; Generating a fourth graphic element, further comprising; A second graphic connector between the first graphic element and the fourth graphic element, wherein the second graphic connector indicates the progression of time between the first time and a third time of the current patient visit in the timeline view, and a second graphic connector; The computing system according to claim 10, further comprising

12. The processor is further configured to generate the second graphic connector further comprising a first sub-connector connecting the first graphic element to the third graphic element and a second sub-connector connecting the third graphic element to the fourth graphic element The computing system according to claim 11

13. The processor is further configured to generate a graphic indicator of the expected probability for the second predictive diagnosis associated with the second graphic connector, of the computing system according to claim 11

14. The processor is configured to generate the second graphic element having at least one of a shape, color, or label different from the corresponding shape, color, or label of the first graphic element, to indicate that the second graphic element corresponds to a future predictive diagnosis, of the computing system according to claim 10

15. The processor is further configured to generate a graphic indicator of the expected probability for the first predictive diagnosis associated with the first graphic connector, of the computing system according to claim 10

16. The processor generates a second predictive diagnosis regarding the future symptoms of the patient, based at least in part on the first predictive diagnosis and the prediction model, generates the graphic data corresponding to the timeline view, and is further configured such that the timeline view includes graphic data corresponding to a timeline slider in the timeline view, and in response to user input to the timeline slider in the timeline view to move to the third time in the timeline view between the second time and a third time occurring after the second time, a third graphic element related to the second predictive diagnosis in the medical data, the graphic indicator of the second predictive diagnosis, and at least one graphic sub-element, wherein the at least one graphic sub-element is related to a physiological parameter associated with the second predictive diagnosis, and further comprises a third graphic element A second graphic connector between the second graphic element and the third graphic element, the second graphic connector indicating the progression of time between the second time of the first predictive diagnosis and the third time of the second predictive diagnosis in the timeline view; The computing system according to claim 10, further comprising.

17. The processor is The computing system according to claim 16, further configured to generate a graphic indicator of the expected probability for the second predictive diagnosis associated with the second graphic connector.

18. The processor is Generating a first predictive diagnosis regarding the future symptoms of the patient, at least partially based on the first diagnosis and the prediction model, wherein the first predictive diagnosis has the highest probability in the prediction model; Generating a second predictive diagnosis regarding the future symptoms of the patient, at least partially based on the first diagnosis and the prediction model, wherein the second predictive diagnosis has the second highest probability in the prediction model; Generating the graphic data corresponding to the timeline view; Further configured to perform, wherein the timeline view is A third graphic element corresponding to the second predictive diagnosis, wherein the second graphic element is A graphic indicator of the second predictive diagnosis; At least one graphic sub-element, wherein the at least one graphic sub-element is related to a physiological parameter associated with the second predictive diagnosis; A third graphic element further comprising; A second graphic connector between the first graphic element and the third graphic element, the second graphic connector indicating the progression of time between the first time and the second time of the current patient visit in the timeline view; The computing system according to claim 10, further comprising.

19. The computing system further comprises a network transceiver, The processor is operably connected to the network transceiver, and the processor further With the processor provided in the server computing system, generate the graphic data corresponding to the timeline view. Using the network transceiver, transmit the graphic data corresponding to the timeline view to the client computing system for display by a display device provided in the client computing system. It is configured as follows. The computing system according to claim 10.

20. The computing system further includes a display device. The processor is operably connected to the display device, and the processor further Displays the graphic data corresponding to the timeline view on the display device. It is configured as follows. The computing system according to claim 10.

Images