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

Abstract

A method for generating a user interface that predicts disease progression includes receiving medical data corresponding to a patient seeing a doctor to a healthcare provider, generating a diagnosis for the patient based on the medical data, and generating a predictive diagnosis for a future condition of the patient based on the diagnostic and predictive model. The method further includes generating a timeline view of a diagnosis in a current patient visit and the predicted diagnosis. Both the graphical element of the diagnosis and the graphical element of the predictive diagnosis include a graphical indicator of the diagnosis and at least one graphical sub-element of a physiological parameter associated with the diagnosis. The method further includes generating a graphical connector between the graphical elements to indicate a temporal progression between a first time and a second time at which the current patient sees a doctor.

Description

[0001] Priority Claim and Cross-Reference to Related Applications

[0002] This application claims priority to U.S. Provisional Application No. 63 / 364,518, entitled “SYSTEM AND METHOD FOR ADAPTIVE GENERATION OF GRAPHICAL DATA OF PREDICTED DIAGNOSES” and filed on May 11, 2022, the entire contents of which are hereby incorporated herein by reference. This application cross-references co-pending U.S. Provisional Patent Application No. 63 / 364,517, entitled “SYSTEM AND METHOD FOR ADAPTIVE GENERATION OF GRAPHICAL DATA OF A TREATMENT HISTORY” and filed on May 11, 2022, the entire contents of which are hereby incorporated herein by reference. Background Art

[0003] People with diabetes (PwD), and particularly those with type 2 diabetes (T2D), are most often treated by a primary care physician (PCP), such as a general practitioner (GP) or family physician (FM) healthcare provider. PCPs are often overwhelmed by the volume of patients they see, not only for T2DM, but also for many other chronic conditions. With a typical appointment lasting less than 15 minutes, PCPs face a significant cognitive burden in terms of disease management and optimal therapy recommendations. These factors contribute to the phenomenon of clinical inertia, which is the delay in appropriately intensifying therapy to better manage the disease. In turn, clinical inertia leads to high health economic costs and negatively impacts the quality of life of PwDs.

[0004] Therefore, clinical decision support (CDS) tools are needed to help PCPs and other healthcare providers (HCPs) select appropriate therapies for people with type 2 diabetes. When integrated into clinical workflows, CDS tools that take into account patient characteristics can help HCPs make better personalized therapy decisions, thereby improving clinical, patient-reported, and economic outcomes. Although the medical community has endorsed clinical guidelines for diabetes treatment from organizations such as the American Diabetes Association (ADA) and the European Association for the Study of Diabetes (EASD), even these clinical guidelines on T2D therapy transitions are difficult for PCPs to follow or apply given the volume of patient data. Given the chronic nature of diabetes and its many comorbidities, healthcare providers also need to review and share potential prognoses with PwDs to assess different treatment options and help educate PwDs about disease progression. While there are statistical models that can provide assistance in predicting disease trajectories, HCPs with limited patient time per visit may not have the opportunity to review such models to provide PwDs with different prognoses in a rigorous manner. Therefore, improvements in systems and methods for providing clinical information and CDS to PCPs and other HCPs in an efficient manner would be beneficial, reducing cognitive load and enabling HCPs to easily review different predictions of disease progression. Summary of the invention

[0005] An adaptive clinical decision support user interface (UI) identifies and generates graphical data for a user interface with one or more predicted disease progressions for a patient based on a current patient diagnosis, optional one or more treatment options, and a predictive model. The model-based predictive approach enables healthcare providers (HCPs) to quickly visualize and discuss therapy options with patients at the point of care by not only displaying the potential disease progression for different prescribed treatment options, but also adding other contextual elements, such as the expected duration for each stage and the likely outcomes in terms of both health and economics, and the likelihood of success for each of these trajectories.

[0006] In one embodiment, a method for generating a user interface for a patient's treatment history has been developed. The method includes receiving medical data for the patient using a processor, the medical data corresponding to at least one patient visit to a healthcare provider, generating a first diagnosis for the patient during a current patient visit based on the medical data using the processor, generating a first predictive diagnosis for a future condition of the patient using the processor based at least in part on the first diagnosis and a predictive model stored in a memory operably connected to the processor, and generating graphical data corresponding to a timeline view of the current patient visit and the first predictive diagnosis using the processor. The generation of the graphical data further includes: generating a first graphical element corresponding to the first diagnosis, the first graphical element further including a graphical indicator of the first diagnosis and at least one graphical sub-element, the at least one graphical sub-element being associated with a physiological parameter selected from the medical data, the physiological parameter being associated with the first diagnosis, and generating a second graphical element corresponding to the first predictive diagnosis, the second graphical element further including a graphical indicator of the first predictive diagnosis and at least one graphical sub-element, the at least one graphical sub-element being associated with a physiological parameter associated with the first predictive diagnosis. The method further includes generating a first graphical connector between the first graphical element and the second graphical element, the first graphical connector indicating a temporal progression between a first time and a second time of the current patient visit in the timeline view.

[0007] In another embodiment, 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 for the patient, a predictive model, and stored program instructions, the medical data corresponding to at least one patient visit to a healthcare provider. The processor is configured to execute 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 for a future condition of the patient based at least in part on the first diagnosis and the predictive model, and generate graphical 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 graphical element corresponding to the first diagnosis, the first graphical element further including a graphical indicator of the first diagnosis and at least one graphical sub-element, the at least one graphical sub-element being associated with a physiological parameter selected from the medical data, the physiological parameter being associated with the first diagnosis, and generate a second graphical element corresponding to the first predictive diagnosis, the second graphical element further including a graphical indicator of the first predictive diagnosis and at least one graphical sub-element, the at least one graphical sub-element being associated with a physiological parameter associated with the first predictive diagnosis. The processor is further configured to generate a first graphical connector between the first graphical element and the second graphical element, the first graphical connector indicating a temporal progression between a first time and a second time of the current patient visit in the timeline view. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] To facilitate identification of the discussion of any particular element or act, the most significant digit(s) in a reference number refers to the figure number in which the element is first introduced.

[0009] Figure 1 is a schematic diagram of a computer system configured to generate graphical data for a medical timeline of a patient in an adaptive user interface for a healthcare provider, the graphical data including graphical elements depicting a predictive diagnosis identified using a predictive model.

[0010] Figure 2 It is for Figure 1 A block diagram of a method of operation of a system.

[0011] Figure 3 is a depiction of a timeline view that incorporates graphical data of a diagnosis for a current patient visit, prescribed treatment options for the patient, and one or more predicted diagnoses for future patient visits.

[0012] Figure 4 yes Figure 3 The timeline view is extended to include an additional predicted diagnosis for a second future patient visit.

[0013] Figure 5 yes Figure 3 A depiction of a timeline view with an adjusted sort threshold showing the predicted diagnosis with the highest probability and the second highest probability identified in the predictive model. DETAILED DESCRIPTION

[0014] These and other advantages, effects, features and objects may be better understood from the following description. In the specification, 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 inventive concept. Throughout the several views of the drawings, corresponding reference numerals indicate corresponding parts.

[0015] Although the inventive concept is susceptible to various modifications and alternative forms, its exemplary embodiments are shown by way of example in the accompanying drawings and are described in detail herein. However, it should be understood that the description of the following exemplary embodiments is not intended to limit the inventive concept to the specific form disclosed, but on the contrary, it is intended to cover all advantages, effects and features that fall within its essence and scope, as defined by the embodiments described herein and the following embodiments. Therefore, in order to interpret the scope of the inventive concept, reference should be made to the embodiments described herein and the following embodiments. Therefore, it should be noted that the embodiments described herein may have advantages, effects and features that are useful for solving other problems.

[0016] The devices, systems and methods will now be described more fully hereinafter with reference to the accompanying drawings, in which some, but not all, embodiments of the inventive concept are shown. Indeed, these devices, systems and methods may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will satisfy applicable legal requirements.

[0017] Likewise, many modifications and other embodiments of the devices, systems, and methods described herein will occur to those skilled in the art having the benefit of the above description and the teachings presented in the associated drawings. Therefore, it should be understood that the devices, systems, and methods are not limited to the specific embodiments disclosed, and variations and other embodiments are intended to be included within the scope of the embodiments. Although specific terms are employed herein, these terms are used only in a general and descriptive sense and not for purposes of limitation.

[0018] Unless otherwise defined, all scientific and technological terms used herein have the same meaning as commonly understood by those skilled in the art to which the present 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, preferred methods and materials are described herein.

[0019] In addition, referring to an element by the indefinite article "a" or "a kind" does not exclude the possibility of more than one element, unless the context clearly requires that there is one and only one element. Therefore, the indefinite article "a" or "a kind" usually means "at least one / kind". Similarly, the terms "have", "comprise" or "include" or any arbitrary grammatical variation thereof are used in a non-exclusive manner. Therefore, these terms can refer to the situation where there are no other features in the entity described in this context except the features introduced by these terms, or the situation where there are one or more other features. For example, expressions such as "A has B", "A contains B" and "A includes B" can refer to the situation where there are no other elements in A except B (i.e., A is only and exclusively composed of B), or the situation where there are one or more other elements in A except B, such as element C, element C and D or even other elements.

[0020] 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 comorbidities associated with diabetes. In specific embodiments described herein, a PwD is a patient of a healthcare provider (HCP), and references to a PwD and references to a patient are used interchangeably herein. While specific embodiments described herein relate to improving a user interface for a patient treatment history for an HCP treating a PwD, the systems and methods described herein are not limited to treating a PwD and may be used to implement improvements in user interfaces for treatment of other diseases and medical conditions, and in particular, chronic medical conditions requiring long-term treatment.

[0021] As used herein, the term "physiological parameter" refers to any quantifiable aspect of PwD physiology measured as part of providing medical data to diagnose a new medical condition or track the status of a previously diagnosed medical condition. A non-limiting list of physiological parameters of interest in the treatment of diabetes and diabetic comorbidities includes body mass index (BMI), blood pressure (BP), blood glucose, glycosylated hemoglobin (HbA1c), blood ketones, and estimated glomerular filtration rate (eGFR).

[0022] As used herein, the term "medical data" is meant to include both medical diagnostic data and medical treatment data. Medical diagnostic data includes identification of previous diagnoses, diagnostic test results, and records of previous and current physiological parameter values ​​for the PwD. Medical diagnostic data optionally includes relevant genetic data, phenotypic data, demographic data, and socioeconomic data related to the PwD. Medical treatment data includes records of previously prescribed medications or other medical treatments that have been prescribed to the PwD during previous patient visits. During the current patient visit, the clinical decision support system is configured to generate one or more prescribed treatments for the PwD based on the medical data, and the HCP can adopt the prescribed treatment or manually select different courses of action for the PwD.

[0023] As used herein, the term "prescribed treatment" refers to any medical diagnostic test, medical diagnostic or prognostic algorithm, medical procedure, medical therapy, medication, diet and lifestyle changes, or other recommended course of action that the HCP has proposed or may choose to propose to the PwD during the PwD's treatment history. In particular, with respect to medications, the term "prescribed" herein encompasses both over-the-counter and prescription medications.

[0024] As used herein, the term "graphics data" refers to any form of encoded data that a computing device uses to generate visually perceptible output using a display device, printer, or other output device, including text, geometric figures, pictures, icons, textures, etc. Different forms of graphics data include static image data and moving images such as animations and videos. Examples of graphics data include rasterized image data, vector graphics data, program graphics data, and combinations thereof. Examples of rasterized image data include graphics data that encodes an array of pixel values ​​in an image, wherein a display device generates an output image formed by the array of pixel values. Rasterized image data can be compressed using JPEG, PNG, WEBP, or other compression formats suitable for static images, as well as using video compression codecs (such as h.264, h.265, VP9, ​​AV1) or other compression formats suitable for video or animation. Examples of vector graphics include graphics data that encode declarative parameters that describe the shape, color, arrangement, and other details of an image that a computing device processes to reproduce the image, and examples of vector graphics include Scalable Vector Graphics (SVG), graphics generated by Cascading Style Sheets (CSS) documents, Portable Document Format (PDF), and other suitable vector graphics formats. Program graphics data includes data encoded as mandatory command data that a processor executes to generate graphics data in a dynamic manner. Examples of program graphics data include encoding command parameters to control JavaScript, WebAssembly, WebGL, or other scripting languages ​​to draw graphics as HTML used in publicly available web browsers. <canvas>A portion of an element, or data rendered using a Postscript rendering engine by a computing device encoded in the Postscript language. In addition, a markup language format such as Hypertext Markup Language (HTML), Extensible Markup Language (XML) or a suitable markup language can be used to format the arrangement of one or more groups of graphic data forming a graphic element to generate the timeline view and other graphics described herein. In some configurations, a single computing system generates graphic data and performs a process of rendering the graphic data to a display device for viewing graphics by human users. As described in further detail below, in other configurations, a first computing system generates graphic data and transmits the graphic data to one or more computing systems, which perform the task of rendering the graphics to one or more display devices so that one or more human users can view the graphics.

[0025] Figure 1 A system 100 is depicted that provides clinical decision support information to an HCP using an adaptive user interface as described herein. The 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.

[0026] Figure 1 The CDS system 102 utilizes one or more computing devices to perform the functions described herein, including Figure 1 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 CDS processors 104. The CDS processor 104 is operably connected to the CDS memory 106 and the network transceiver 118. The CDS memory 106 includes one or more volatile data storage devices such as static and dynamic random access memory (RAM) and one or more non-volatile data storage devices such as magnetic, solid-state, and optical storage drives. During operation, the CDS processor 104 reads data and writes data to the CDS memory 106 to execute stored program instructions and store data including medical data received from the HCP terminal 128 and the EHR service 120 and generated graphical data. The CDS processor 104 operates the network transceiver 118, which is a wired or wireless network interface controller that transmits and receives data via the network 148, to receive medical data and other commands from the HCP terminal 128, to transmit and receive EHR data using the EHR service 120, and to transmit graphical data for a timeline view user interface of the PwD's treatment history to the HCP terminal 128. In some configurations, the CDS processor 104 also operates the network transceiver 118 to receive medical data directly from the PWD device 138 and to transmit graphical data for the PwD's treatment history to the PWD device 138.

[0027] In the CDS system 102, the CDS memory 106 stores CDS software 108, a diagnostic database 110, PwD medical data 112, graphical data 114, and a predictive model 116. The CDS software 108 includes stored program instructions that are executed by the CDS processor 104 to perform clinical support functions and generate graphical data corresponding to a timeline view of one or more diagnoses for a PwD and one or more prescribed treatments for treating the PwD over a series of patient visits. 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 to the CDS system, and to enable the CDS system 102 to transmit the generated graphical data described herein to the HCP terminal 128.

[0028] In the CDS memory 106, the diagnostic database 110 includes a stored set of logic rules that the CDS system 102 uses to generate a diagnosis for the PwD based on the medical data for the PwD. In one specific configuration, the diagnostic database 110 encodes guidelines from the American Diabetes Association (ADA) Diabetes Medical Care Standards. Alternative configurations employ different medical guidelines or other algorithms to generate diagnoses and prescribe treatments. Although the CDS system 102 uses the diagnostic database 110 to generate graphical elements that display diagnoses and prescribed treatments in an automated manner during operation of the system 100, the HCP optionally uses the HCP terminal 128 to override a suggested diagnosis or course of action recommendation.

[0029] In the CDS memory 106, the PwD medical data 112 includes both any relevant medical data for the PwD during the current patient visit and historical medical record data including medical data for 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 and the historical medical data stored in the electronic health record for the PwD, as well as data received from external laboratory tests, home diagnostics (such as point-of-care and continuous glucose meter devices), and medical data provided to the CDS system 102 by the HCP via the HCP terminal 128 during the patient visit. In addition, during operation, the CDS system 102 optionally transmits updated medical data for the PwD to the EHR service 120 to reflect updated measurements to physiological parameters, diagnoses, or to record prescribed medications or other medical treatments received by the PwD during the course of treatment.

[0030] In the CDS memory 106, the graphical data 114 includes a graphical representation of a timeline view user interface of a treatment history for a PwD over a series of one or more patient visits based on the PwD medical data 112. For example, the graphical data 114 forms a timeline view including graphical elements and sub-elements to depict one or more diagnoses and related physiological parameters for each diagnosis, prescribed treatments, prescribed medications, diagnostic tests, and graphical connectors connecting the graphical elements in the timeline view. In some configurations, the graphical data 114 further includes stored text, icons, geometric templates, and other visually perceptible data that the CDS system 102 uses to adaptively generate a timeline view for the PwD based on the PwD medical data 112.

[0031] In the CDS memory 106, the prediction model 116 is embodied as, for example, a stochastic model or a machine learning model. Examples of stochastic models include Markov chains, Markov decision processes, semi-Markov chains, or semi-Markov decision processes. Additional details of these stochastic models implemented in the CDS system 102 are provided in further detail below. Although these prediction models are described in further detail herein as non-limiting examples for illustrative purposes, alternative configurations of the CDS system 102 can utilize prediction models that incorporate different stochastic models or rely on machine learning models to generate predictions for disease progression. For example, general artificial neural networks (ANNs), and particularly recurrent neural networks, such as long short-term memory (LSTM) neural networks, can be used to generate disease progression predictions. In general, any prediction model known in the art and suitable for generating predictive diagnosis can be used in the CDS system 102.

[0032] As is known in the art, a Markov chain models the probability of transitioning between states (where each state corresponds to a stage of disease progression) based on the current state, which is the currently diagnosed condition of the PwD and optionally other known information about the PwD that relates the PwD to the states in the Markov chain. The Markov chain provides probability values ​​for transitioning to different states based on discrete time increments corresponding to Figure 1 The time interval between patient visits in the illustrative example of . In addition, a transition that causes the current state to remain (corresponding to the PwD remaining in a stable condition until the next patient visit) is typically a potential outcome of a state transition in a Markov chain. A Markov decision process is a modification of a Markov chain in which probability values ​​for transitions to different states are determined based on the current state (as in a Markov chain) and additionally based on decisions or "actions," where an action in the context of the CDS system 102 refers to a prescribed treatment that may affect disease progression and thus change the probability of transitions to different states in the Markov decision model. In contrast, a Markov chain encodes information for different prescribed treatment options as a current state for the PwD, and thus, in addition to the diagnostic condition and other medical data, each prescribed treatment option corresponds to one of a set of current states for the PwD in the Markov chain, where selecting a different prescribed treatment changes the current state and the corresponding state transition probability for the PwD in the Markov chain.

[0033] Semi-Markov Chain and Semi-Markov Decision Process prediction models refer to variations of the Markov Chain and Markov Decision Process models described above, where transition probabilities are further determined using a "stay time" parameter corresponding to the length of time the PwD has spent in the current state determined based on medical history data for the PwD. For example, the Semi-Markov Chain and Semi-Markov Decision Process prediction models treat a patient who is newly diagnosed with an elevated HbA1c level (zero stay time) differently than a patient who has experienced elevated HbA1c levels for a year, which in turn affects the probability values ​​in the prediction model for future progression of HbA1c levels or other diagnosed conditions.

[0034] In generating the prediction model 116 for use with the CDS system 102, precise probability values ​​for each state transition are derived from empirical data, such as epidemiological study data, actuarial tables, insurance claims data, and other clinical data sources that provide statistics related to disease progression for diabetes and diabetic comorbidities. The prediction model 116 is generated prior to operation of the CDS system 102 and system 100, as further described herein.

[0035] Figure 1 The EHR service 120 provides medical data for PwDs to the CDS system 102 in the form of EHR. Figure 1 In the illustrative embodiment of , the EHR service is a network computing service that includes a digital processor 122, a memory 124 that stores EHR data 126 for the PwD. The EHR data 126 is a digital record encoded in a standard format, such as the Fast Healthcare Interoperable Resources (FHIR) format, a version of the International Health Level 7 (HL7) format, or another suitable electronic health record format. Figure 1 In an embodiment, the EHR service 120 operates independently of the CDS system 102, but in an alternative configuration, the EHR service 120 and the CDS system 102 may be implemented as a unified system. In an actual embodiment, the EHR data 126 for the PwD may include data received from multiple data sources, including external diagnostic testing services, HCPs operating the HCP terminal 128, the CDS system 102, and EHR data from other HCPs (such as medical specialists who treat other medical conditions and comorbidities of the PwD).

[0036] Figure 1 The HCP terminal 128 is a desktop or laptop personal computer (PC), tablet computer, smartphone, or other suitable client computing device of the HCP, which 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 the optional EHR service 120, and to receive and display graphical data corresponding to a timeline view of at least one patient visit for the PwD as the PwD receives treatment from the HCP over a series of visits. In some configurations, the HCP also uses the HCP terminal 128 to communicate with the PWD device 138 between patient visits, or to conduct remote patient visits where the HCP is providing telemedicine services to the PwD. Figure 1 In an embodiment of the present invention, the HCP terminal 128 executes program instructions stored in 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 acts as a client of one or more web services provided by the CDS system 102, but in alternative configurations, 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 graphical data 114, which the CDS system 102 generates and transmits to the HCP terminal 128. The display device 136 is, for example, a flat panel display screen or other electronic display device, although in some configurations a printer can reproduce the graphical 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 enter data and modify the timeline view, as described in further detail below, while 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.

[0037] Figure 1 The PWD device 138 of the PWD is another desktop or laptop PC, tablet computer, smart phone or other suitable client computing device of the PWD, which includes a device processor 140, a device memory 142 storing 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 an on-site or continuous blood glucose meter), a fitness tracking device (such as a smart watch), or other medical device. The PWD device 138 is optionally configured to enable the PWD to conduct a telemedicine patient visit with the HCP via the HCP terminal 128 using video conferencing software and other telemedicine software that is otherwise known in the art and is not described in further detail herein. In some configurations, the CDS system 102 transmits graphical data generated for a timeline view user interface of the PWD's treatment history to the PWD device 138 for display using the display device 146 via the network 148. In another configuration, the HCP terminal 128 retransmits graphical data for the timeline view of the PWD's treatment history to the PWD device 138 during the telemedicine patient visit.

[0038] Figure 2 2 is a block diagram of a process 200 for operating a CDS system to generate a graphical timeline view user interface for a PwD's current diagnostic status, potential prescribed treatment options, and predictions for future disease progression in one or more future patient visits. Although process 200 may be performed at any time, for purposes of illustration, 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 progression. Figure 1 The process 200 is described with reference to the system 100 of FIG. 1 , and references to the process 200 to performing a function or action refer to the operation of a processor (such as the CDS processor 104 in the CDS system 102) executing stored program instructions (such as the CDS software 108) to perform the function or action.

[0039] The process 200 begins when the CDS system 102 receives PwD medical data for at least one patient visit (block 204). In the system 100, the processor 104 in the CDS system 102 receives medical data from one or more sources, including but not limited to the EHR service 120, the HCP terminal 128, and the PWD device 138 in some cases. In particular, the EHR service 120 provides medical data for previous patient visits, including previous diagnoses, prescribed medications and medical treatments, a history of physiological parameter data measurements for the PwD, and optionally socioeconomic and demographic data related to the PwD. During a patient visit, the HCP terminal 128 optionally transmits physiological parameters and other medical data to the CDS system 102 based on manual input from the HCP, automatically uploaded physiological parameters generated by a medical testing device such as a blood glucose meter, or both. Additionally, the CDS system 102 may receive medical data regarding blood tests or other diagnostic tests that the PwD received at an external diagnostic laboratory prior to the patient visit, directly from the diagnostic laboratory's computing system, via the EHR service 120, or from the HCP terminal 128. As described above, the CDS system 102 stores the received PwD medical data 112 in the CDS memory 106.

[0040] When the CDS system 102 identifies the physiological parameters that have the greatest correlation with the diagnosis during each patient visit (block 208), the process 200 continues. Figure 1 In an embodiment of the present invention, the CDS processor 104 uses the diagnostic database 110 to identify physiological parameters in the PwD medical data 112 that have the greatest correlation with each diagnosis in a series of one or more patient visits. For example, if the patient visit includes a diagnosis that the PwD is both obese and has uncontrolled HbA1c, which is indicative of the onset of type 2 diabetes, the CDS processor 104 uses the diagnostic database 110 to identify physiological parameters that have the highest correlation with these diagnoses, such as body mass index (BMI) associated with obesity and measured HbA1c levels for the PwD. In many cases, the PwD medical data 112 includes physiological parameters and other information that are not directly related to the diagnosis, and the CDS processor 104 filters such data from the timeline view, although the HCP can of course access the complete PwD medical data 112 via a conventional user interface if desired.

[0041] When the CDS system 102 generates a graphical element of a diagnostic condition for the PwD during the current patient visit and one or more graphical elements of potential prescribed treatment options (block 212), the process 200 continues. The graphical element of the diagnostic condition further includes at least one graphical sub-element of one or more identified physiological parameters associated with the diagnosis for the PwD. The graphical element and the graphical sub-element provide a graphical indicator of the physiological parameter data that generated the diagnosis and prescribed treatment process. A graphical indicator refers to any type of graphical data in a timeline view that conveys specific information about medical data for the PwD, a prescribed treatment for the PwD, or a recommendation for a prescribed treatment for the PwD. A graphical sub-element is a class of graphical elements that are subordinate to another graphical element in a timeline view, and the CDS system 102 generates graphical data for the graphical sub-element within the boundaries of the parent graphical element or otherwise associates each graphical sub-element with the parent graphical element. The graphical element and the sub-element provide a clear indication of the relationship between the graphical element for the patient visit and one or more graphical sub-elements associated with the patient visit. The CDS system 102 uses the diagnostic database 110 to identify potential prescribed treatments for the diagnosed condition and, for each potential prescribed treatment selection, generates a graphical element that identifies the prescribed treatment, such as a medication type, diagnostic test, or other medical therapy, and optionally includes additional useful information related to the prescribed treatment for the HCP.

[0042] Figure 3 An example of a timeline view 300 is depicted, including a graphical element 302 depicting a diagnosis for a PwD during a current patient visit and a graphical element 306 depicting treatment options for the PwD. In the specific example of the timeline view 300, the diagnosis for the current visit includes a diagnosis of chronic kidney disease (CKD) for a person with type 2 diabetes. CKD is a known comorbidity of PwD, which is also known to be a progressive condition.

[0043] In timeline view 300, graphical element 302 is depicted as a rectangular graphical element including a graphical indicator of a first diagnosis. Figure 3 , is a text label indicating the diagnosis of type 2 diabetes and stage 2 CKD. Graphic element 302 further includes graphic sub-elements 304a and 304b located inside graphic element 302. Graphic sub-element 304a is depicted as a circle, which includes a graphical indicator of a physiological parameter (HbA1c in the upper semicircle and a measured value of HbA1c for PwD in the lower semicircle). The HbA1c physiological parameter is related to the diagnosis of type 2 diabetes. Similarly, graphic sub-element 304b is depicted as another circle, which includes a graphical indicator of another physiological parameter (estimated glomerular filtration rate (eGFR) in the upper semicircle and a numerical value for eGFR in the lower semicircle). The eGFR physiological parameter is related to the diagnosis of CKD stage 2. In some configurations, the graphical data of each physiological parameter graphic sub-element provides additional information to the HCP in addition to 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 in the graphical sub-element to indicate whether the physiological parameter is in range or out of range for a particular PwD. Using the HbA1c physiological parameter 302a as an example, green may indicate an HbA1c value that is considered normal for a healthy individual, yellow may indicate an elevated HbA1c for a non-insulin dependent diabetic patient, and red may indicate an even further elevated HbA1c, indicating the need for insulin therapy. In some configurations, the graphical sub-element of the physiological parameter also includes an arrow or other graphical indicator that shows the trend of the physiological parameter over time since a previous patient visit, such as an upward or downward arrow that indicates an upward or downward trend in the HbA1c level or a change in other related physiological parameters. In some configurations, the graphical indicator of the physiological parameter includes a chart, icon, or other non-textual graphical indicator that can be easily interpreted by the HCP to assess the condition of the PwD.

[0044] In the timeline view 300, the graphical element 306 is depicted as a rectangular graphical element that includes a graphical indicator of a prescribed treatment option for the diagnosed CKD condition. Figure 3 In the example of , the graphical element 306 includes a graphical depiction of a list of CKD treatment options, including blood pressure and cholesterol medications known to affect CKD progression, as well as options for smoking cessation and changes in diet and exercise for the PwD. During operation, the CDS processor 104 identifies the prescribed treatment options based on the diagnostic condition for the PwD and other relevant PwD medical data 112, and identifies the options for the prescribed treatment from the diagnostic database 110. For example, in Figure 3 , smoking cessation prescribed treatments for the PwD are generated only for the PwD with a smoking history as recorded in the PwD medical data 112. Graphic element 306 is also referred to as a triggering graphical element for a prescribed treatment because the HCP optionally selects graphical element 306 to trigger one or more recommended treatment options. In one embodiment, one or more of the prescribed treatment options are displayed using clickable hyperlinks or with associated graphical control buttons to enable the HCP to select the prescribed treatment option. 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 option, such as prescribing medication or enrolling the PwD in a smoking cessation or diet and exercise program.

[0045] Refer again Figure 2 , process 200 continues when the CDS processor 104 generates one or more predictive diagnoses for the patient's future condition based at least in part on the first diagnosis for the current patient visit and the predictive model 116 stored in the CDS memory 106 (box 216). As described above, in a Markov chain, a Markov decision process, or a variation thereof, the CDS processor 102 uses the diagnosis to identify a current state in the predictive model that corresponds to a diagnosis for the PwD. The CDS processor 102 identifies any state in the model that is connected to the current state as a predictive diagnosis, where the transition probabilities in the predictive model correspond to the likelihood of each predictive diagnosis. For some predictive diagnoses, in addition to the first diagnostic condition for the PwD from the current patient visit, the CDS processor 102 also uses the prescribed treatment options to identify the predictive diagnosis in the predictive model and the associated probability values ​​for the predictive diagnosis. For example, in Figure 3 In an example of the present invention, if no additional prescribed treatment is given to the PwD to establish a baseline prediction for disease progression (such as CKD progression in the PwD), the CDS processor 102 generates a predictive diagnosis for the PwD. The CDS processor 102 also uses the recommended prescribed treatment from the diagnostic database 110 to identify different current states for the PwD in the Markov chain or as an action input in addition to the current state of the PwD in the Markov decision process. In at least some cases, the prescribed treatment for the PwD affects the probability value for future predicted diagnoses, and the prediction model 116 returns a set of one or more predicted diagnoses with different corresponding probability values ​​compared to the baseline prediction for disease progression (no treatment). In some cases, the prediction model generates multiple sets of predicted diagnoses for a variety of different prescribed treatment options. In addition, in some embodiments, the CDS processor 104 provides additional medical data from the PwD medical data 112 as an input to the prediction model 116 to refine the predicted diagnostic results. For example, demographic and other relevant medical risk factor data for the PwD beyond the current diagnosis (e.g., if the PwD smokes) can be provided to the prediction model 116 to generate a predicted diagnosis. Additionally, in embodiments of the prediction model 116 using a semi-Markov chain or semi-Markov decision process, the CDS processor 102 also provides data corresponding to the duration that the PwD remains stable at the diagnosis of the current patient visit as the "dwell time" of the prediction model 116.

[0046] The process 200 continues when the CDS processor 104 generates a graphical element for one or more of the predicted diagnoses based on the probability ranking for the predicted diagnoses returned from the predictive model 116 (block 220). Figure 2 In an illustrative embodiment of the invention, the CDS processor 104 identifies the predictive diagnosis with the highest probability as the highest ranked predictive diagnosis for each potential prescribed treatment option (such as the CKD treatment option and the no additional treatment baseline option described above). As described below, during operation, the HCP may provide user input to view additional predictive diagnoses with lower probability values ​​to review different potential disease progression outcomes with the PwD. An alternative configuration may employ another ranking process, such as a predetermined probability threshold for the predictive diagnoses, and select any predictive diagnoses that exceed the predetermined probability threshold. The CDS processor 104 generates a graphical element for each selected predictive diagnosis, the graphical element having a graphical indicator of the predictive diagnosis and at least one graphical sub-element associated with a physiological parameter associated with the predictive diagnosis. In particular, at least one graphical sub-element includes a graphical indicator corresponding to a range of values ​​of a physiological parameter of the predictive diagnosis. The CDS processor 104 generates a graphical element for each predictive diagnosis having at least one of a shape, color, or label that is different from the corresponding shape, color, or label of the first graphical element of the current diagnostic condition to indicate that the graphical element corresponds to a future predictive diagnosis. The distinction between graphical elements for current or past diagnoses and graphical elements for predictive diagnoses helps the HCP quickly assess the information in the timeline view and reduces the likelihood that the HCP will misinterpret the predictive diagnosis as an existing diagnosis for the PwD. In the embodiments described herein, the graphical element for the predictive diagnosis comprises a rectangle with rounded corners compared to the right angles of the graphical element for the first diagnosis in the current patient visit, but in alternative embodiments, the predictive diagnosis may be distinguished by using different colors, text, or graphical icons in the labels, or a combination of different shapes, colors, and labels.

[0047] Reference Figure 3 , the timeline view 300 includes graphical elements 312 and 320 for predictive diagnosis. In the timeline view 300, the graphical elements 312 and 320 for predictive diagnosis indicate the predictive diagnosis for the PwD condition at a future patient visit. Figure 3 In the example of , the future patient visits are a 6 month time span. Graphical element 312 is the predicted diagnosis having the highest probability value in predictive model 116 in response to conducting the prescribed treatment for CKD depicted in graphic element 306. Graphical element 312 includes a graphical indicator for the predicted diagnosis, which in this case is "Type 2 Diabetes / Stage 2 CKD," and a text label "Forecast: Stable" indicating a prediction that the PwD will remain in the same general condition as diagnosed in the current patient visit. Graphical element 312 also contains graphical sub-elements 314a and 314b of estimated ranges for relevant physiological parameters associated with the predicted diagnosis. Graphical sub-element 314a includes a graphical depiction of an estimated range for HbA1c, and graphical sub-element 314b includes a graphical depiction of an estimated range for eGFR. In Figure 3 , graphical element 320 is the predicted diagnosis with the highest probability value in the prediction model 116 in response to not taking additional treatment. Graphical element 320 includes a graphical indicator for the predicted diagnosis, which in this case is "Type 2 Diabetes / Stage 3 CKD"), and a text label "Prediction: Stable" indicating a prediction that the PwD will experience a progression in the disease condition from the condition diagnosed in the current patient visit. Graphical element 320 also contains graphical sub-elements 322a and 322b of estimated ranges of values ​​for related physiological parameters associated with the predicted diagnosis. Graphical sub-element 322a includes a graphical depiction of an estimated range for HbA1c, and graphical sub-element 322b includes a graphical depiction of an estimated range for eGFR that differs from the range of predicted values ​​in graphical sub-element 314a due to a prediction of progression of the CKD condition for the PwD. In the examples disclosed herein, the graphical sub-element for the predicted physiological parameter includes a range of multiple estimated values ​​for the related physiological parameter, but in an alternative configuration, the range is instead a single predicted physiological parameter value. As described above, graphical elements 312 and 320 include rectangular shapes with rounded corners, which differ from the right-angled shape of graphical element 302 for the diagnosis in the current patient visit. Additionally, the text labels in graphical elements 312 and 320 indicate that the diagnosis is a prediction.

[0048] Refer again Figure 2 , the process 200 continues when the CDS processor 104 generates graphical data corresponding to a timeline view including the graphical elements described above with reference to the processing of blocks 212 to 220 and graphical connectors connecting the graphical elements and a timeline slider that enables dynamic adjustment of the timeline view (block 224). In addition to including the arrangement of the previously generated graphical elements, the timeline view also generates one or more graphical elements that depict the time ranges in which the patient visits and prescribed treatments occurred. The timeline view further includes a timeline slider that enables the HCP to adjust the size of the time range depicted in the timeline view and to move the time range depicted in the timeline view forward and backward in time.

[0049] When the graphical data corresponding to the timeline view is generated in block 224 of the process 200, the CDS system 102 transmits the generated graphical data for the timeline view user interface to the client HCP terminal 128 via the network 148 using the CDS processor 104 and the network transceiver 118. The HCP terminal 128 receives the graphical data, and the terminal processor 130 executes terminal software 134, such as a web browser or other client software, to generate a rendered user interface with a visual depiction of the timeline view using a display device 136 provided in the HCP terminal 128. 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, which the CDS system 102 receives via the network 148 and processes to provide an updated set of graphical data for the updated timeline view to the HCP terminal 128. Additionally, in some configurations, the CDS system 102 optionally transmits the generated graphical data for the timeline view user interface to the PWD device 138 for direct display to the PWD using the display device 146. Although for purposes of illustration, the system 100 is embodied as a networked system in which the CDS system 102 is connected to the HCP terminal 128 via the network 148, in another configuration, a single computing system performs the operation of both the CDS system 102 and the HCP terminal 128. In this configuration, a processor in the single computing system generates graphical data corresponding to a timeline view of a patient visit and operates a display device provided in the single computing system to display the graphical data corresponding to the timeline view of the patient visit. In one configuration, the single computing system is the HCP terminal 128, which is further reconfigured to host the CDS software 108, the diagnostic database 110, the PwD data 112, the graphical data 114, and the predictive model 116 in addition to the terminal software 134.

[0050] Refer again Figure 3 , the timeline view 300 includes the aforementioned graphical elements 302, 306, 312, and 320 arranged linearly along a timeline depicted by a timeline graphic element 324. The timeline graphic element 324 includes date information related to the time of the current patient visit (September 2021) and the scheduled time of a future patient visit corresponding to the time range for the predicted diagnosis (March 2022). The timeline slider graphic element 326 in the timeline view graphic element 324 enables the HCP to adjust the time range depicted in the timeline view 300. Although not described in further detail herein, the timeline slider 326 enables the HCP to review previous patient visits and earlier medical history for the PwD based on the PwD medical data 112, and as further described in detail below, the timeline slider 326 enables the HCP to view predicted diagnoses for additional future patient visits. The graphic connectors indicate the relationship between the graphical element 302 of the current patient visit, the prescribed treatment trigger graphic element 306, and the predicted diagnosis graphic elements 312 and 320. In Figure 3 , the graphical connectors are formed as linear straight lines or curved connectors with arrows indicating the flow of time in the timeline view 300. In particular, the graphical connector formed by graphical sub-connectors 308a and 308b connects the current patient visit diagnosis graphical element 302 to the predicted diagnosis graphical element 312 via the prescribed treatment graphical element 306. Graphic sub-connectors 308a and 308b connect the current diagnosis, prescribed treatment, and predicted future diagnosis with an easy-to-understand structure for the HCP. Another graphical connector 316 connects the current patient visit diagnosis graphical element 302 with the predicted diagnosis graphical element 320, which indicates the highest predicted diagnosis probability for the PwD if the PwD does not receive additional treatment. The timeline view 300 also includes a graphical indication of the probability of each predicted diagnosis associated with the corresponding graphical connector in the timeline view. For example, the expected probability value 310 is positioned with the graphical sub-connector 308a or 308b ( Figure 3 308b) in the example of , and another expected probability value 318 is associated with the graphical connector 316. The expected probability value is the predicted probability generated from the prediction model 116 for reaching the corresponding predicted diagnosis. Figure 3 In the examples of FIG. 1 , the expected probability value is a graphical indicator displayed as a numeric value ranging from 0.0 to 1.0, but in other embodiments, the expected probability value is displayed as a percentage, a ranked value (e.g., first, second, third most likely), or qualitatively such as by adjusting the thickness or color of the graphical connector line to indicate the likelihood of a particular predicted diagnosis. Figure 3 Also depicted is a sort selector widget 330, which is embodied as a drop-down selector input in the timeline view 300. The sort selector widget enables the HCP or other user to adjust the sort threshold for the predicted diagnoses displayed in the timeline view and to Figure 3 In the illustrative example of , the default sorting is to display only the highest ranked (1) predicted diagnosis in timeline view 300 .

[0051] Those skilled in the art will recognize that the processing of steps 212 to 220 may occur in a different order than described above or may occur simultaneously. Additionally, the timeline view depicted herein is arranged in a left-to-right format, representing the current time of a patient visit to a future time of a predicted diagnosis, but alternative configurations may orient the timeline in a right-to-left format or in a vertical format from top to bottom or bottom to top. Additionally, alternative configurations of process 200 may include different visual formats and arrangements of the graphical elements, graphical sub-elements, and graphical connectors depicted herein.

[0052] Refer again Figure 2 During process 200, the HCP has the option of modifying the timeline view to adjust the timeline range (block 228), to adjust the sorting threshold (block 240), and to adjust both the timeline range and the sorting threshold. Figure 3 In the default timeline view of the HCP, the time range for the predicted diagnosis extends to the next patient visit, and the HCP has the option of extending 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 pulls the timeline slider to the right using a click-and-drag operation or other suitable user input. The CDS processor 104 uses the predictive model 116 to identify additional predictive diagnoses for the future time range in a manner similar to that described in the processing of box 216 using existing predictive diagnoses and other estimated data as inputs to the predictive model (box 232). The CDS processor 104 generates updated graphical data including additional graphical elements for additional predictive diagnoses in future patient visits in the timeline view (box 236), and the HCP terminal 128 or other client computing device displays the updated timeline view.

[0053] Figure 4 An example of an expanded timeline view 400 is depicted, which the CDS system 102 generates in response to input to display a predicted diagnosis for two future patient visits. The timeline view 400 includes elements of the timeline view 300, wherein the timeline graphical element 324 now displays a larger time frame that includes the second future patient visit in September 2022. Figure 4 In the example of , graphical element 412 represents a second predictive diagnosis for a stable condition of the PwD if the PwD accepts and continues the prescribed treatment for CKD depicted in graphical element 306. Graphic sub-elements 414a and 414b depict estimated HbA1c and eGFR physiological parameter range value estimates, respectively. Graphic connector 406 depicts a progression from the predictive diagnosis in graphical elements 312 and 412, with expected probability indicator 404 depicting the likelihood of the predictive diagnosis 412 along a given treatment path. Similarly, graphical element 420 depicts a second predictive diagnosis of continued progression of diabetes to stage 3 CKD if the PwD does not accept further treatment. Graphic element 420 includes predictions of a range of further elevated HbA1c levels in graphical sub-element 422a and a range of further decreased eGFR levels in graphical sub-element 422b. Graphic connector 418 connects the earlier predicted diagnosis in graphical element 320 to graphical element 420 , where expected probability indicator 416 depicts the likelihood of predicted diagnosis 420 along a given treatment pathway.

[0054] Refer again Figure 2 , to adjust the sorting threshold (box 240), the HCP terminal 128 receives input from the HCP via the sorting selector widget 330 to adjust the sorting threshold for the number of predictive diagnoses to be displayed in the timeline view. Although the sorting selector widget 330 depicted herein selects based on a numerical sort, in an alternative configuration, the sorting threshold is a minimum probability value corresponding to the likelihood of a given predictive diagnosis in the predictive model 116. The CDS system 102 receives the updated sorting threshold data, the CDS processor 104 uses the predictive model 116 to identify all predictive diagnoses that meet the updated sorting threshold, and the CDS processor 104 generates updated graphical data for the timeline view including graphical elements for the newly added predictive diagnoses, or in the case of an increase in the sorting threshold, may delete graphical elements for predictive diagnoses with expected probability values ​​less than the new sorting threshold. The CDS processor 104 generates graphical data for an updated timeline view for predictive diagnoses with expected probabilities exceeding the sorting threshold (box 244), and the HCP terminal 128 or other client computing device displays the updated timeline view.

[0055] Figure 5 An example of a timeline view 500 is depicted that the CDS system 102 generates in response to an input to adjust a ranking threshold to display a predicted diagnosis having both a highest probability and a second highest probability in the prediction model 116. The timeline view 500 includes Figure 3 504 and 512. In addition, the sort selector widget 330 displays "2" to indicate that the predictive diagnoses with the highest and second highest (ranked first and second) expected probabilities in the prediction model 116 are included in the timeline view 500. In more detail, the graphical element 520 depicts another predictive diagnosis in which the PwD experiences diabetes progression with a further increase in HbA1c levels and an accelerated progression to stage 4 CKD with a further decrease in eGFR levels by the next scheduled patient visit if the PwD does not receive treatment for the CKD diagnosis. The graphical element 520 includes graphical sub-elements 522a and 522b that depict estimated ranges for HbA1c and eGFR, respectively. Figure 5 Also included is a new graphical subconnector 508 connecting the graphical element 306 to the graphical element 320, indicating that even if the PwD undergoes the recommended CKD treatment, there is a certain probability of progression to stage 3 CKD. The timeline view 300 displays both the prediction branch with the graphical subconnector 308b and the associated expected probability value 310 graphical indicator and the subconnector 508 with the graphical indicator of the lower expected probability value 504. Similarly, the graphical connector 516 connects the graphical element 302 for the diagnosis in the current patient visit to the graphical element 520 of the third predicted diagnosis. The graphical indicator of expected probability 512 displays the expected probability value that the PwD will reach the advanced CKD stage, which is a lower probability value than the graphical indicator of expected probability 318 for the branching graphical connector 316. In this way, the process 200 as illustrated in the timeline view 500 enables the HCP to view a greater or lesser number of predicted diagnoses and generate a display of how different treatment paths cause the predicted diagnostic conditions to diverge or converge.

[0056] The embodiments described herein enable the generation of a timeline view user interface that presents highly relevant diagnoses, predicted diagnoses, physiological parameters, and recommended prescribed treatment options to the HCP. The user interface reduces the cognitive burden on the HCP, thereby enabling more efficient and effective treatment of PwD and other patients. When integrated into the clinical workflow, the embodiments described herein can help the HCP make improved personalized therapy decisions, thereby improving clinical, patient reports, and economic results. In particular, the embodiments described herein enable the HCP to work with existing clinical guidelines for diabetes therapy conversion in an effective manner, because these guidelines may be difficult to follow or apply in view of the amount of patient data in the prior art system. In addition, the embodiments described herein enable the HCP to consult one or more potential future diagnoses that may be generated by various prescribed treatment options, which enables the HCP to analyze and discuss different treatment options with the PwD in an efficient and effective manner.

[0057] The present disclosure has been described in conjunction with what are believed to be the most practical and most preferred embodiments. However, these descriptions have been presented by way of illustration, and these embodiments are not intended to be limited to the disclosed embodiments. Therefore, those skilled in the art will recognize that the present disclosure encompasses all modifications and alternative arrangements as set forth in the following claims and within the spirit and scope of the present disclosure.< / canvas>

Claims

1. A method for generating a user interface for predicting disease progression for a patient, the method comprising: receiving, with a processor, medical data for the patient, the medical data corresponding to at least one patient visit to a healthcare provider; generating, using the processor, a first diagnosis for the patient during a current patient visit based on the medical data; generating, using the processor, a first predictive diagnosis for a future condition of the patient based at least in part on the first diagnosis and a predictive model stored in a memory operably connected to the processor; as well as generating, using the processor, graphical data corresponding to a timeline view of the current patient visit and the first predictive diagnosis, the generating of the graphical data further comprising: generating a first graphical element corresponding to the first diagnosis, the first graphical element further comprising: a graphical indicator of the first diagnosis; and at least one graphical sub-element, the at least one graphical sub-element being associated with a physiological parameter selected from the medical data, the physiological parameter being associated with the first diagnosis; and generating a second graphical element corresponding to the first predictive diagnosis, the second graphical element further comprising: a graphical indicator of the first predictive diagnosis; and at least one graphical sub-element, the at least one graphical sub-element being associated with a physiological parameter associated with the first predictive diagnosis; and A first graphical connector is generated between the first graphical element and the second graphical element, the first graphical connector indicating a temporal progression between a first time and a second time of the current patient visit in the timeline view.

2. The method according to claim 1, further comprising: generating, using the processor, a second predictive diagnosis for the future condition of the patient based at least in part on the first diagnosis, the recommended prescribed treatment, and the predictive model; as well as The generating of the graphical data corresponding to the timeline view using the processor, the generating further comprising: generating a third graphical element including a graphical indicator of the recommended prescribed treatment; generating a fourth graphical element corresponding to the second predictive diagnosis, the fourth graphical element further comprising: a graphical indicator of the second predictive diagnosis; and at least one graphical sub-element, the at least one graphical sub-element being associated with a physiological parameter associated with the second predictive diagnosis; and A second graphical connector is generated between the first graphical element and the fourth graphical element, the second graphical connector indicating a temporal progression between the first time and a third time of the current patient visit in the timeline view.

3. The method of claim 2, wherein the second connector further comprises: A first subconnector connects the first graphic element with the third graphic element, and a second subconnector connects the third graphic element with the fourth graphic element.

4. The method of claim 2, wherein the generating of the second graphic connector further comprises: A graphical indicator of an expected probability for the second predictive diagnosis is generated, using the processor, in association with the second graphical connector.

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

6. The method of claim 1, wherein the generating of the first graphic connector further comprises: A graphical indicator of an expected probability for the first predictive diagnosis is generated, using the processor, in association with the first graphical connector.

7. The method according to claim 1, further comprising: generating, using the processor, a second predictive diagnosis for a future condition of the patient based at least in part on the first predictive diagnosis and the predictive model; as well as The generating of the graphical data corresponding to the timeline view using the processor, the generating further comprising: generating graphical data corresponding to a timeline slider in the timeline view; generating, in response to user input of the timeline slider moving in the timeline view to a third time, a third graphical element associated with the second predicted diagnosis in the medical data during the third time, the third time occurring after the second time, the third graphical element further comprising: a graphical indicator of the second predictive diagnosis; and at least one graphical sub-element, the at least one graphical sub-element being associated with a physiological parameter associated with the second predictive diagnosis; and A second graphical connector is generated between the second graphical element and the third graphical element, the second graphical connector indicating a temporal progression between the second time of the first predictive diagnosis and the third time of the second predictive diagnosis in the timeline view.

8. The method according to claim 7, further comprising: A graphical indicator of an expected probability for the second predictive diagnosis is generated, using the processor, in association with the second graphical connector.

9. The method according to claim 1, further comprising: generating, using the processor, the first predicted diagnosis for the future condition of the patient based at least in part on the first diagnosis and the predictive model, wherein the first predicted diagnosis has a highest probability in the predictive model; generating, using the processor, a second predicted diagnosis for the future condition of the patient based at least in part on the first diagnosis and the predictive model, wherein the second predicted diagnosis has a second highest probability in the predictive model; as well as The generating of the graphical data corresponding to the timeline view using the processor, the generating further comprising: generating a third graphical element corresponding to the second predictive diagnosis, the second graphical element further comprising: a graphical indicator of the second predictive diagnosis; and at least one graphical sub-element, the at least one graphical sub-element being associated with a physiological parameter associated with the second predictive diagnosis; and A second graphical connector is generated between the first graphical element and the third graphical element, the second graphical connector indicating a temporal progression between a first time and a second time of the current patient visit in the timeline view.

10. A computing system configured to generate a user interface for a patient's treatment history, the computing system comprising: Memory, which is configured to store: medical data for the patient, the medical data corresponding to at least one patient visit to a healthcare provider; Predictive models; and stored program instructions; as well as a processor operably connected to the memory, the processor configured to execute the stored program instructions to: generating a first diagnosis for the patient during a current patient visit based on the medical data; generating a first predictive diagnosis for a future condition of the patient based at least in part on the first diagnosis and the predictive model; as well as generating graphical data corresponding to a timeline view of the current patient visit and the first predicted diagnosis, the processor being further configured to: generating a first graphical element corresponding to the first diagnosis, the first graphical element further comprising: a graphical indicator of the first diagnosis; and at least one graphical sub-element, the at least one graphical sub-element being associated with a physiological parameter selected from the medical data, the physiological parameter being associated with the first diagnosis; and generating a second graphical element corresponding to the first predictive diagnosis, the second graphical element further comprising: a graphical indicator of the first predictive diagnosis; and at least one graphical sub-element, the at least one graphical sub-element being associated with a physiological parameter associated with the first predictive diagnosis; and A first graphical connector is generated between the first graphical element and the second graphical element, the first graphical connector indicating a temporal progression between a first time and a second time of the current patient visit in the timeline view.

11. The computing system of claim 10, wherein the processor is further configured to: generating a second predictive diagnosis for the future condition of the patient based at least in part on the first diagnosis, the recommended prescribed treatment, and the predictive model; as well as generating the graphical data corresponding to the timeline view, the graphical data further comprising: a third graphical element including a graphical indicator of said recommended prescribed treatment; a fourth graphical element corresponding to the second predictive diagnosis, the fourth graphical element further comprising: a graphical indicator of the second predictive diagnosis; and at least one graphical sub-element, the at least one graphical sub-element being associated with a physiological parameter associated with the second predictive diagnosis; and A second graphical connector between the first graphical element and the fourth graphical element, the second graphical connector indicating a temporal progression between the first time and a third time of the current patient visit in the timeline view.

12. The computing system of claim 11, wherein the processor is further configured to: The second graphic connector is generated, the second graphic connector further comprising a first subconnector connecting the first graphic element with the third graphic element, and a second subconnector connecting the third graphic element with the fourth graphic element.

13. The computing system of claim 11 , wherein the processor is further configured to: A graphical indicator of the expected probability for the second predictive diagnosis is generated in association with the second graphical connector.

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

15. The computing system of claim 10, wherein the processor is further configured to: A graphical indicator of an expected probability for the first predictive diagnosis is generated in association with the first graphical connector.

16. The computing system of claim 10, wherein the processor is further configured to: generating a second predictive diagnosis for a future condition of the patient based at least in part on the first predictive diagnosis and the predictive model; as well as generating the graphical data corresponding to the timeline view, the graphical data further comprising: Graphic data corresponding to a timeline slider in the timeline view; a third graphical element associated with the second predicted diagnosis in the medical data during a third time in response to a user input of the timeline slider moving in the timeline view to a third time, the third time occurring after the second time, the third graphical element further comprising: a graphical indicator of the second predictive diagnosis; and at least one graphical sub-element, the at least one graphical sub-element being associated with a physiological parameter associated with the second predictive diagnosis; and A second graphical connector between the second graphical element and the third graphical element, the second graphical connector indicating a progression in time between the second time of the first predictive diagnosis and the third time of the second predictive diagnosis in the timeline view.

17. The computing system of claim 16, wherein the processor is further configured to: A graphical indicator of the expected probability for the second predictive diagnosis is generated in association with the second graphical connector.

18. The computing system of claim 10, wherein the processor is further configured to: generating the first predicted diagnosis for the future condition of the patient based at least in part on the first diagnosis and the predictive model, wherein the first predicted diagnosis has a highest probability in the predictive model; generating a second predicted diagnosis for the future condition of the patient based at least in part on the first diagnosis and the predictive model, wherein the second predicted diagnosis has a second highest probability in the predictive model; as well as generating the graphical data corresponding to the timeline view, the graphical data further comprising: A third graphical element corresponding to the second predictive diagnosis, the second graphical element further comprising: a graphical indicator of the second predictive diagnosis; and at least one graphical sub-element, the at least one graphical sub-element being associated with a physiological parameter associated with the second predictive diagnosis; and A second graphical connector between the first graphical element and the third graphical element, the second graphical connector indicating a temporal progression between a first time and a second time of the current patient visit in the timeline view.

19. The computing system of claim 10, further comprising: Network transceiver; and The processor is operably connected to the network transceiver and is further configured to: generating, using the processor provided in a server computing system, the graphical data corresponding to the timeline view; as well as The graphical data corresponding to the timeline view is transmitted to a client computing system using the network transceiver for display using a display device provided in the client computing system.

20. The computing system of claim 10, further comprising: Display device; and The processor is operably connected to the display device and is further configured to: The graphical data corresponding to the timeline view is displayed using the display device.

Images