Artificial intelligence system and method for prognostic assessment of autoimmune diseases

Abstract

Artificial intelligence systems and methods for prognostic assessment of autoimmune diseases. Particular objects and advantages of the present disclosure include methods and systems configured to aggregate and analyze clinical interaction data, patient biometric data, diagnostic record data, blood biomarker test data, and patient biometric data to tailor increasingly patient-specific metrics in creating dynamic patient phenotypes to enhance clinical understanding of one or more factors specific to the patient's health status. One or more AI frameworks and engines may facilitate the effective integration of communication-related insights into diagnostic and prognostic digital health resources. Exemplary systems, methods, and devices according to the principles herein may include machine learning and deep learning techniques to develop one or more quantitative metrics derived from clinical interaction data.

Description

[Technical Field]

[0001] This application claims the benefit of priority to U.S. Provisional Application No. 63 / 401,584, filed September 16, 2022, and entitled "Novel Method and System for Classifying Undiagnosed Individuals at Risk for Autoimmune Disease Using Innovative Virtual and Digital Models," the entire contents of which are hereby incorporated by reference herein.

[0002] The present disclosure relates to the field of digital health systems and software as medical devices, and in particular to artificial intelligence systems and methods for prognostic assessment of autoimmune diseases. [Background technology]

[0003] The National Institutes of Health currently estimates that 23.5 million people in the United States may have at least one autoimmune disease. However, the American Autoimmune and Related Diseases Association (AARDA) estimates that the actual number of affected individuals in the United States may be as high as 50 million. The economic burden of autoimmune diseases on the U.S. healthcare system is estimated to reach $100 billion annually.

[0004] Diagnosis remains a challenge for many of these patients. In the case of systemic lupus erythematosus (SLE), the average time to diagnosis is more than seven years. Reaching a diagnosis is a long and arduous process. Although autoimmune diseases have unique characteristics, many of their visible symptoms, such as fatigue and pain, overlap with those of common diseases. As a result, clinicians strive to rule out other health conditions before considering an autoimmune disease diagnosis. Furthermore, laboratory tests for specific autoimmune diseases are still being developed. Current best practices, including antinuclear antibody (ANA) testing, measure the presence of common types of antibodies. However, they cannot confirm the presence of an autoimmune disease. Autoimmune diseases can come and go as symptoms change over time. By the time a patient seeks medical attention, symptoms often have already subsided. Summary of the Invention [Problem to be solved by the invention]

[0005] The challenges posed by chronic disease are a global burden that is almost universally exacerbated by communication gaps. In particular, while people with or at risk of chronic disease would almost always achieve better outcomes if they could communicate their health status in a timely manner, healthcare providers are disadvantaged by limited access to detailed and timely information about their patients' health status, preventing them from implementing timely interventions and prevention measures. [Means for solving the problem]

[0006] The following presents a simplified summary of some embodiments of the invention in order to provide a basic understanding of the invention. This summary is not an extensive overview of the invention, and is not intended to identify key / critical elements of the invention or to delineate the scope of the invention. Its sole purpose is to present some embodiments of the invention in a simplified form as a prelude to the more detailed description that is presented later.

[0007] Certain aspects of the present disclosure provide artificial intelligence methods and systems for prognostic evaluation of autoimmune diseases. According to certain aspects of the present disclosure, the methods and systems may include one or more steps or system actions of presenting a plurality of clinical dialogue prompts to a patient-user (e.g., by a dialogue AI agent at one or more timepoints). The methods and systems may further include one or more steps or system actions of receiving a plurality of dialogue responses from the patient-user in response to the plurality of clinical dialogue prompts (e.g., by a dialogue AI agent at one or more timepoints). The methods and systems may further include one or more steps or system actions of receiving a first set of text data including the plurality of dialogue responses from the patient-user (e.g., by a dialogue AI agent at one or more timepoints). The methods and systems may further include one or more steps or system actions of receiving a first set of diagnostic record data for the patient-user (e.g., by a dialogue AI agent at one or more timepoints). In certain embodiments, the first set of diagnostic record data for the patient-user includes at least one of blood biomarker test data and biometric data. The methods and systems may further include one or more steps or system actions of processing (e.g., by at least one server) the first set of text data and the first set of diagnostic record data for the patient-user according to a natural language processing model. In certain embodiments, the natural language processing model is configured to extract one or more features from the first set of text data and the first set of diagnostic record data. In certain embodiments, the natural language processing model is configured to cluster one or more text segments from the first set of text data and the first set of diagnostic record data according to the one or more features. The methods and systems may further include one or more steps or system actions of analyzing the one or more text segments to determine one or more temporal or contextual associations between the one or more text segments and the blood biomarker test data and / or biometric data according to the natural language processing model.The methods and systems may further comprise one or more steps or system actions of assigning one or more prognostic values ​​to one or more text segments according to at least one output of the natural language processing model. The methods and systems may further comprise one or more steps or system actions of analyzing (e.g., by at least one server) the one or more prognostic values ​​for the one or more text segments to generate a prognostic assessment for the patient-user's at least one autoimmune disease. The methods and systems may further comprise one or more steps or system actions of providing (e.g., by at least one server) the prognostic assessment to the practitioner-user via a graphical user interface on a client device.

[0008] According to certain aspects of the present disclosure, the method and system may further comprise one or more steps or system actions of configuring (e.g., by at least one server) a dialogue AI model according to the one or more prognostic values ​​for the one or more text segments. In certain embodiments, the dialogue AI model may comprise a large-scale language model. In certain embodiments, the plurality of clinical dialogue prompts may include a plurality of generated prompts according to the dialogue AI model. In certain embodiments, the prognostic assessment may include a diagnostic assessment of at least one autoimmune disease. In certain embodiments, the prognostic assessment includes a predictive assessment of at least one pathophysiological event associated with at least one autoimmune disorder. In certain embodiments, the prognostic assessment includes a clinical recommendation for at least one pharmaceutical intervention for the patient-user. In certain embodiments, the prognostic assessment includes a clinical recommendation for at least one blood biomarker test for the patient-user. In certain embodiments, the biometric data includes data from at least one body-worn sensor of the patient-user. According to certain aspects of the present disclosure, the method and system may further comprise one or more steps or system actions of modifying the plurality of clinical dialogue prompts according to the one or more prognostic values ​​for the one or more text segments via the dialogue AI model.

[0009] Another aspect of the present disclosure provides artificial intelligence methods and systems for patient phenotyping of autoimmune diseases. According to certain aspects of the present disclosure, the methods and systems may include one or more steps or system actions of presenting a first set of clinical dialogue prompts to a patient-user according to a generative AI model (e.g., by a dialogue AI agent communicatively associated with a first server). The methods and systems may include one or more steps or system actions of receiving (e.g., by the dialogue AI agent) a first set of responses to the first set of clinical dialogue prompts from the patient-user. The methods and systems may include one or more steps or system actions of receiving (e.g., by the first server) a first diagnostic record dataset for the patient, the first diagnostic record dataset including at least one of blood biomarker test data and biometric data for the patient-user. The methods and systems may include one or more steps or system actions of receiving (e.g., by at least one server) a first set of text data including the first set of responses to the first set of clinical dialogue prompts from the patient-user. The methods and systems may include one or more steps or system actions of processing (e.g., by at least one server) the first set of text data and the first set of diagnostic record data according to a natural language processing model. According to certain aspects of the present disclosure, the natural language processing model is configured to extract one or more features from the first set of text data and the first set of diagnostic record data. According to said aspects, the natural language processing model is configured to cluster one or more text segments from the first text data set and the first diagnostic record data set according to the one or more features. The methods and systems may include one or more steps or system actions of analyzing the one or more text segments according to the natural language processing model to determine one or more temporal or contextual associations between the one or more text segments and the blood biomarker test data and / or biometric data.The method and system may comprise one or more steps or system actions of establishing a patient phenotype for the patient-user according to one or more temporal or contextual associations between one or more text segments and blood biomarker test data and / or biometric data according to at least one output of the natural language processing model. According to certain aspects of the present disclosure, the patient phenotype includes one or more symptoms, markers, and pathological triggers for the patient-user's autoimmune disease. The method and system may comprise one or more steps or system actions of providing, by at least one server, the patient phenotype for the patient-user to a practitioner-user via a graphical user interface on a client device.

[0010] According to certain aspects of the present disclosure, the methods and systems may further include one or more steps or system actions of configuring (e.g., by at least one server) a generative AI model according to a patient phenotype. The methods and systems may further include one or more steps or system actions of presenting (e.g., by a dialogue AI agent) a second set of clinical dialogue prompts to the patient-user according to the generative AI model. In certain embodiments, the second set of clinical dialogue prompts is configured according to the patient phenotype (e.g., according to the generative AI model). According to certain aspects of the present disclosure, at least one clinical prompt in the second set of clinical dialogue prompts is different from the first set of clinical dialogue prompts. The methods and systems may further include one or more steps or system actions of receiving (e.g., by the dialogue AI agent) a second set of responses to the second set of clinical dialogue prompts from the patient-user. The methods and systems may further include one or more steps or system actions of receiving (e.g., by a first server) a second diagnostic record dataset for the patient, the second diagnostic record dataset including a second blood biomarker test dataset and / or a second biometric dataset for the patient-user. The methods and systems may further comprise one or more steps or system actions of receiving (e.g., by at least one server) a second set of text data comprising a second set of responses to the second set of clinical dialogue prompts from the patient-user. The methods and systems may further comprise one or more steps or system actions of processing (e.g., by at least one server) the second set of text data according to a natural language processing model. In certain embodiments, the natural language processing model is configured to extract one or more features from the second set of text data according to a patient phenotype. In certain embodiments, the natural language processing model is configured to cluster one or more text segments from the second set of text data according to the one or more features.The methods and systems may further include one or more steps or system actions of processing (e.g., by at least one server) the second set of text data and the second set of diagnostic record data according to a natural language processing model. According to certain aspects of the present disclosure, the natural language processing model is configured to extract one or more features from the second set of text data and the second set of diagnostic record data according to a patient phenotype. In certain embodiments, the natural language processing model is configured to cluster one or more text segments from the second set of text data and the second set of diagnostic record data according to the one or more features. The methods and systems may further include one or more steps or system actions of analyzing (e.g., according to a machine learning model) the one or more text segments to generate a prognosis assessment for the patient-user's autoimmune disease. The methods and systems may further include one or more steps or system actions of providing (e.g., by at least one server) the prognosis assessment to the patient-user via a graphical user interface of an end-user device or a client device associated with the patient-user and / or practitioner-user. The methods and systems may further include one or more steps or system actions of updating or modifying the patient phenotype according to at least one output of the natural language processing model. In certain embodiments, the prognostic assessment includes one or more recommended actions for the management of the autoimmune disease for the patient-user.

[0011] Another aspect of the present disclosure provides artificial intelligence methods and systems for identifying diagnostic triggers for autoimmune disease from clinical interaction data. According to certain aspects of the present disclosure, the methods and systems may include one or more steps or system actions of presenting a plurality of clinical interaction prompts to a patient-user at a user interface of the first client device (by at least one server communicatively associated with the first client device). The methods and systems may further include one or more steps or system actions of receiving a plurality of user-generated responses to the plurality of clinical interaction prompts from the patient-user (e.g., by the at least one server via the first client device), the plurality of user-generated responses to the plurality of clinical interaction prompts including a first set of clinical interaction data. The methods and systems may further include one or more steps or system actions of receiving a first diagnostic record dataset for the patient-user (e.g., by the at least one server), the first diagnostic record dataset including at least one of blood biomarker test data and biometric data for the patient-user. The methods and systems may further include one or more steps or system actions of processing (e.g., by at least one server) the first set of clinical dialogue data and the first set of diagnostic record data according to a natural language processing model. In certain embodiments, the natural language processing model is configured to extract one or more features from the first set of clinical dialogue data and the first set of diagnostic record data. The natural language processing model may be configured to cluster one or more text segments from the first set of clinical dialogue data and the first set of diagnostic record data according to the one or more features. The methods and systems may further include one or more steps or system actions of analyzing the one or more text segments according to at least one output of the natural language processing model to determine one or more temporal or contextual associations between the one or more text segments and the blood biomarker test data and / or biometric data.The methods and systems may further comprise one or more steps or system actions of setting one or more diagnostic triggers for the patient-user according to one or more temporal or contextual associations between one or more text segments and the blood biomarker test data and / or biometric data according to at least one output of the natural language processing model. The methods and systems may further comprise one or more steps or system actions of communicating the one or more diagnostic triggers for the patient-user to the practitioner-user via a graphical user interface of the second client device (e.g., by at least one server via a network interface).

[0012] According to certain aspects of the present disclosure, the methods and systems may further comprise one or more steps or system actions of configuring (e.g., by at least one server) a natural language processing model according to one or more diagnostic triggers. In certain embodiments, the plurality of clinical dialogue prompts are configured according to a generative AI model. In such embodiments, the generative AI model may comprise a large-scale language model. The methods and systems may further comprise one or more steps or system actions of configuring (e.g., by at least one server) the generative AI model according to one or more diagnostic triggers. The methods and systems may further comprise one or more steps or system actions of presenting a second or subsequent plurality of clinical dialogue prompts to the patient-user at a user interface of the first client device (e.g., by at least one server communicatively associated with the first client device). The methods and systems may further include one or more steps or system actions of receiving (e.g., by at least one server via the first client device) second or next plurality of user-generated responses to the second or next plurality of clinical dialogue prompts from the patient-user, where the second or next plurality of user-generated responses to the second or next plurality of clinical dialogue prompts include the second or next set of clinical dialogue data. The methods and systems may further include one or more steps or system actions of processing (e.g., by the at least one server) the second or next set of clinical dialogue data according to a natural language processing model to extract one or more features from the second or next set of clinical dialogue data according to one or more diagnostic triggers. The methods and systems may further include one or more steps or system actions of analyzing at least one output of the natural language processing model according to a machine learning model to identify at least one diagnostic trigger from the second or next set of clinical dialogue data.The methods and systems may further comprise one or more steps or system actions of communicating (e.g., by at least one server) to the practitioner-user via a graphical user interface of a second client device at least one diagnostic trigger from the second or subsequent set of clinical interaction data. The methods and systems may further comprise one or more steps or system actions of communicating (e.g., by at least one server) to the patient-user at a user interface of the first client device at least one diagnostic trigger from the second or subsequent set of clinical interaction data. The methods and systems may further comprise one or more steps or system actions of generating, according to a machine learning model, at least one clinical recommendation for management of the autoimmune disease according to the at least one diagnostic trigger from the second or subsequent plurality of user-generated responses. The methods and systems may further comprise one or more steps or system actions of communicating (e.g., by at least one server) to the practitioner-user via a graphical user interface of a second client device at least one clinical recommendation for management of the autoimmune disease. The methods and systems may further comprise one or more steps or system actions of communicating (e.g., by at least one server) at a user interface of a first client device to a patient-user at least one clinical recommendation for management of the autoimmune disease.

[0013] The foregoing has outlined, rather broadly, the pertinent and important features of the present invention in order that the detailed description of the invention that follows may be better understood, and that the present contribution to the art may be fully appreciated. Additional features of the present invention will now be described which form the subject of the claims of the present invention. It should be appreciated by those skilled in the art that the conception of the present invention, and the specific methods and structures disclosed, may be readily utilized as a basis for modifying or designing other structures for carrying out the same purposes of the present invention. It should also be realized by those skilled in the art that such equivalent constructions do not depart from the spirit and scope of the invention as set forth in the appended claims. [Brief explanation of the drawings]

[0014] Those skilled in the art will understand that the figures described herein are for illustrative purposes. It should be understood that in some instances, various aspects of the described embodiments may be shown exaggerated or enlarged to facilitate understanding of the described embodiments. In the drawings, like reference characters generally refer to like features, functionally similar elements, and / or structurally similar elements throughout the various views. The drawings are not necessarily to scale, emphasis instead being placed upon illustrating the principles of the teachings. The drawings are not intended to limit the scope of the present teachings in any way. The systems, methods, and computer program products of the present disclosure can be better understood from the following exemplary description, taken in conjunction with the following drawings:

[0015] [Figure 1] FIG. 1 is an exemplary embodiment of a computer system that may implement one or more aspects of the present disclosure. [Figure 2] FIG. 2 is an architecture diagram of an artificial intelligence system for prognostic evaluation of autoimmune diseases according to certain embodiments of the present disclosure. [Figure 3] FIG. 3 is a flow diagram of an artificial intelligence system and method for prognostic assessment of autoimmune disease according to certain embodiments of the present disclosure. [Figure 4] FIG. 4 is a functional block diagram of an artificial intelligence system and method for prognostic assessment of autoimmune disease according to certain embodiments of the present disclosure. [Figure 5] FIG. 5 is a process flow diagram of an artificial intelligence system and method for prognostic assessment of autoimmune disease according to certain embodiments of the present disclosure. [Figure 6] FIG. 6 is a routine process flow diagram of an artificial intelligence system and method for prognostic assessment of autoimmune disease according to certain embodiments of the present disclosure. [Figure 7] FIG. 7 is a routine process flow diagram of an artificial intelligence system and method for prognostic assessment of autoimmune disease according to certain embodiments of the present disclosure. [Figure 8]FIG. 8 is a routine process flow diagram of an artificial intelligence system and method for prognostic assessment of autoimmune disease according to certain embodiments of the present disclosure. [Figure 9] FIG. 9 is a process flow diagram of an artificial intelligence method for prognostic assessment of autoimmune disease according to certain embodiments of the present disclosure. [Figure 10] FIG. 10 is a process flow diagram of an artificial intelligence method for prognostic assessment of autoimmune disease according to certain embodiments of the present disclosure. [Figure 11] FIG. 11 is a process flow diagram of an artificial intelligence method for prognostic assessment of autoimmune disease according to certain embodiments of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0016] It should be understood that all combinations of concepts described in more detail below (provided such concepts are not mutually inconsistent) are contemplated as part of the inventive subject matter disclosed herein, and it should be understood that terms used explicitly herein and that also appear in disclosures incorporated by reference are to be accorded the meaning most consistent with the particular concepts disclosed herein.

[0017] The following is a more detailed description of various concepts and embodiments of the methods, devices and systems of the present invention configured to facilitate the acquisition, management and utilization of health information resulting from a) medical records, b) biometric profiling and c) medical communications to people (users or patients) whose health conditions suggest they would benefit from proactive health monitoring and medical promotion.

[0018] It should be understood that the various concepts introduced above and described in more detail below may be implemented in any of numerous ways, as the disclosed concepts are not limited to specific embodiments. Specific examples and applications are provided primarily for illustrative purposes. The present disclosure should not be limited to the exemplary implementations and techniques shown in the drawings and described below.

[0019] Before describing the present invention and specific exemplary embodiments thereof, it is to be understood that the present invention may vary and is not limited to the specific embodiments described. It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting, since the scope of the present invention will be limited only by the appended claims.

[0020] Where a range of values ​​is stated, unless the context clearly dictates otherwise, it is to be understood that each intervening value, to the tenth of the unit of the lower limit, between the upper and lower limit of that range, and each other stated or intervening value within that stated range, is encompassed within the invention. The upper and lower limits of these smaller ranges may independently be included in the smaller ranges and are also encompassed within the invention, subject to any specifically excluded upper limit in the stated range. Where the stated range includes one or both of the endpoint limits, ranges excluding either or both of those included endpoints are also included within the invention.

[0021] As used herein, "exemplary" means serving as an example or explanation, and does not necessarily mean ideal or best.

[0022] As used herein, the terms "computer," "processor," and "computer processor" include a personal computer, workstation computer, tablet computer, smartphone, microcontroller, microprocessor, field programmable object array (FPOA), digital signal processor (DSP), application specific integrated circuit (ASIC), field programmable gate array (FPGA), programmable logic array (PLA), or other digital processing engine, device, or equivalent capable of executing software code, including associated memory devices, transmission devices, pointing devices, input / output devices, displays, and equivalents.

[0023] As used herein, the terms "conversational agent" or "conversational AI agent" or "agent" refer to any device, system, and / or program configured to autonomously perform one or more desired functions in response to one or more inputs. The terms may be used interchangeably. The one or more inputs may include one or more user-generated inputs, sensor-based inputs, internal system inputs, external system inputs, environmental perceptions, etc. Examples of conversational agents include, but are not limited to, one or more virtual assistants, personal assistants, or chatbots.

[0024] As used herein, the term "mobile device" includes any portable electronic device capable of performing one or more digital functions or operations, including, but not limited to, smartphones, tablet computers, personal digital assistants, wearable activity trackers, smart watches, smart speakers, etc.

[0025] As used herein, the terms "provider" and "practitioner" refer to a medical professional or provider responsible for one or more aspects of a patient's care, including, but not limited to, a doctor, nurse, physician assistant, pharmacist, technician, etc. The terms "provider" and "practitioner" may be used interchangeably throughout this disclosure. As used herein, the term "practitioner user" refers to a provider / practitioner who is also a user of the systems and methods described herein.

[0026] As used herein, the term "patient" refers to any recipient of medical services performed or facilitated by a medical practitioner, including, but not limited to, individuals with autoimmune diseases. As used herein, the term "patient-user" refers to a patient who is also a user of the systems and methods described herein.

[0027] As used herein, the term "comprising" means including but not limited to. The term "based on" means based at least in part on.

[0028] As used herein, the term "interface" refers to a shared boundary through which two or more distinct components of a computer system can exchange information, whether between software, computer hardware, peripheral devices, humans, or combinations thereof.

[0029] As used herein, the terms "transmit" or "communicate" and combinations thereof refer to the transmission of digital and / or analog signal information by electronic transmission, Wi-Fi®, Bluetooth® technology, wireless, wired or other known transmission technology, including transmission to an internet website.

[0030] As used herein, the term "biometric" refers to a measurable biological (i.e., anatomical and / or physiological) and / or behavioral characteristic of a human being (i.e., a patient). According to certain aspects of the present disclosure, examples of biometric measurements may include, but are not limited to, heart rate and cardiac activity (e.g., pulse, electrocardiogram), sleep data, electroencephalogram data (e.g., MRI and fMRI), activity data (i.e., movement / telemetry), body temperature, blood pressure, etc.

[0031] The terms "program" or "software" are used herein in a generic sense to refer to any type of computer code or set of computer-executable instructions that can be employed to program a computer or other processor to perform various aspects of the present technology, as described above. Furthermore, it should be understood that, according to one aspect of the present embodiments, one or more computer programs that, when executed, perform the methods of the present technology need not reside on a single computer or processor, but may be distributed in a modular manner among several different computers or processors to perform various aspects of the technology. Computer-executable instructions may be in many forms, such as program modules executed by one or more computers or other devices. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Typically, the functionality of the program modules may be combined or distributed as desired in various embodiments.

[0032] Particular benefits and advantages of the present disclosure include artificial intelligence methods and systems configured to identify and train diagnostically relevant triggers to alert healthcare providers of urgent pathological risks or opportunities for pharmaceutical intervention in the treatment and management of autoimmune diseases.

[0033] Specific objects and advantages of the present disclosure include artificial intelligence methods and systems for analyzing written and verbal content of interpersonal communications (e.g., according to one or more machine learning frameworks) that contain subjective information related to a person's health status. Embodiments of the present disclosure include methods and systems for analytically tractable acquisition and management of clinical communication data for diagnostic and prognostic purposes. Embodiments of the present disclosure include methods and systems for systematically leveraging existing information in concert with rigorously quantifiable medical data such as laboratory tests and other standardized diagnoses.

[0034] Particular objects and advantages of the present disclosure include artificial intelligence methods and systems for the effective integration of communication-related insights into diagnostic and prognostic digital health resources. Exemplary systems, methods, and apparatuses according to the principles herein may include machine learning and deep learning techniques for developing one or more quantitative metrics derived from clinical dialogue data. Such techniques may include natural language processing (NLP) and generative artificial intelligence (gAI). According to certain aspects of the present disclosure, the NLP may include one or more computer-implemented machine learning frameworks for analytically deconvolving free text into informative granules and broad trends. According to certain aspects of the present disclosure, the gAI may comprise one or more artificial neural networks that include the ability to simulate normal human communication. According to certain aspects of the present disclosure, the gAI comprises a clinical dialogue framework configured as an artificial intelligence vehicle for facilitating productive engagement between medical patients and digital health resources intended to improve reactive and preventative healthcare for those patients.

[0035] Particular objects and advantages of the present disclosure include methods and systems configured to aggregate and analyze clinical interaction data, patient biometric data, diagnostic record data, blood biomarker test data, and patient biometric data to tailor increasingly patient-specific metrics in creating a dynamic patient phenotype to enhance clinical understanding of one or more factors specific to the patient's health condition. According to certain aspects of the present disclosure, the patient phenotype is used in the configuration and / or modification of one or more gAI models to drive one or more gAI communications tailored to the patient.

[0036] Particular objects and advantages of the present disclosure include one or more systems, methods, devices, and digital platform products, including one or more NLP and gAI engines and frameworks, for presenting desirable (i.e., useful and unburdensome) communication resources to patients that are patient-specific and encourage context-adaptive inquiry in a manner that facilitates regular information exchanges that do not unduly burden healthcare providers, while at the same time sharing with people the person knows and trusts. According to certain embodiments, data obtained from these information exchanges is communicated (e.g., according to one or more communication protocols) to alert healthcare providers to the need to respond to medically specific questions or requests from the patient, and in some scenarios, NLP-driven AI models detect possible confluences of situations (e.g., potentially a series of related phrases in a transcript combined with specific recent test results) that may flag adverse events and conditions that may indicate the need for one or more specific therapeutic interventions.

[0037] Particular objects and advantages of the present disclosure include one or more systems, methods, devices, and digital platform products that facilitate the proactive assessment and care of people assessed for risk of autoimmune diseases, including chronic connective tissue disorders. While the present disclosure discusses autoimmune diseases with some specificity, the systems, methods, devices, and digital platform products may be further applicable to numerous other conditions, diseases, and disorders.

[0038] Turning now illustratively to the drawings, wherein like reference characters indicate like elements throughout the several views, FIG. 1 illustrates an exemplary computer system in which certain illustrated embodiments of the present invention may be implemented.

[0039] Referring now to FIG. 1 , a processor-implemented computing device is shown that may implement one or more aspects of the present disclosure. According to one embodiment, a processing system 100 may generally include at least one processor 102 or processing unit or processors, memory 104, at least one input device 106, and at least one output device 108 coupled via a bus or buses 110. In certain embodiments, the input device 106 and the output device 108 may be the same device. An interface 112 may also be provided for coupling the processing system 100 to one or more peripheral devices; for example, the interface 112 may be a PCI card or PC card. At least one storage device 114 may also be provided that houses at least one database 116. The memory 104 may be any type of storage device, such as volatile or non-volatile memory, solid-state storage, magnetic devices, etc. The processor 102 may include multiple separate processing devices, for example, for handling various functions within the processing system 100. The input device(s) 106 receive input data 118 and may include, for example, a keyboard, a pointer device such as a pen-like device or mouse, an audio receiving device for voice-controlled activation such as a microphone, a data receiving device or antenna such as a modem or wireless data adapter, a data acquisition card, etc. The input data 118 may originate from a variety of sources; for example, the input data 118 may be keyboard commands in conjunction with data received over a network. The output device(s) 108 generate or create output data 120 and may include, for example, a display device or monitor if the output data 120 is visual, a printer if the output data 120 is printed, a data transmitter or antenna such as a port, e.g., a USB port, a peripheral component adapter, a modem or a wireless network adapter, etc. The output data 120 may be derived from individual and various output devices, for example, a visual display on a monitor in conjunction with data transmitted over a network.The data output or an interpretation of the data output may be viewed by a user, for example, on a monitor or using a printer. The storage device 114 may be any type of data or information storage means, such as volatile or non-volatile memory, solid state storage, magnetic devices, etc.

[0040] In use, the processing system 100 is adapted to enable data or information to be stored in and / or retrieved from at least one database 116 via wired or wireless communication means. The interface 112 may enable wired and / or wireless communication between the processing device 102 and peripheral components capable of serving specialized purposes. In general, the processing device 102 may receive instructions as input data 118 via the input device(s) 106 and may display processed results or other output to a user by utilizing the output device(s) 108. More than one input device 106 and / or output device 108 may be provided. It should be understood that the processing system 100 may take any form, such as a terminal, a server, dedicated hardware, etc.

[0041] It should be understood that processing system 100 may be part of a networked communication system. Processing system 100 may be connected to a network, such as the Internet or a WAN. Input data 118 and output data 120 may be communicated to other devices via the network. Transfer of information and / or data over the network may be accomplished using wired or wireless communication means. A server may facilitate data transfer between the network and one or more databases. The server and one or more databases provide examples of information sources.

[0042] 1 may operate in a networked environment using logical connections to one or more remote computers, which may be personal computers, servers, routers, network PCs, peer devices or other common network nodes, and typically include many or all of the elements described above.

[0043] It should also be understood that the logical connections depicted in FIG. 1 include a local area network (LAN) and a wide area network (WAN), but also include other networks, such as a personal area network (PAN). Such networking environments are commonplace in offices, enterprise-wide computer networks, intranets, and the Internet. For example, when used in a LAN networking environment, computer system environment 100 is connected to the LAN through a network interface or adapter. When used in a WAN networking environment, the computer system environment typically includes a modem or other means for establishing communications over the WAN, such as the Internet. The modem may be internal or external and may be connected to the system bus through a user input interface or other appropriate mechanism. In a networked environment, program modules depicted relative to computer system environment 100, or portions thereof, may be stored in a remote memory storage device. It should be understood that the network connections shown in FIG. 1 are exemplary and other means of establishing a communications link between two or more computers may be used.

[0044] FIG. 1 is intended to provide a brief, general description of an exemplary and / or suitable example environment in which embodiments of the invention described below may be implemented. FIG. 1 is one example of a suitable environment and is not intended to suggest limitations on the structure, scope of use, or functionality of embodiments of the invention. No particular environment should be interpreted as having any dependency or requirement relating to any one or combination of components illustrated in the example operating environment. For example, in particular examples, one or more elements of an environment may be deemed unnecessary and omitted. In other examples, one or more other elements may be deemed necessary and added.

[0045] In the description that follows, certain embodiments may be described with reference to acts and symbolic representations of operations that are performed by one or more computing devices, such as the computing system environment 100 of FIG. 1 . As such, it should be understood that such acts and operations, sometimes referred to as being computer-executed, include the manipulation by the computer's processor of electrical signals representing data in a structured form. This manipulation transforms the data or maintains it in locations within the computer's memory system, reconfiguring or altering the operation of the computer in ways understood by those skilled in the art. The data structures in which data is maintained are typically physical locations in memory that have particular characteristics defined by the format of the data. However, while the embodiments are described in the above context, the embodiments are not meant to be limiting, as those skilled in the art will understand that the acts and operations described below can also be implemented in hardware.

[0046] Embodiments may be practiced with numerous other general-purpose or special-purpose computing devices and computing system environments or configurations. Examples of well-known computing systems, environments, and configurations suitable for use with embodiments include, but are not limited to, personal computers, handheld or laptop devices, personal digital assistants, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, networks, minicomputers, server computers, game server computers, web server computers, mainframe computers, and distributed computing environments that include any of the above systems or devices.

[0047] The embodiments may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The embodiments may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including memory storage devices.

[0048] Having generally illustrated and described above the exemplary computer system environment 100 of FIG. 1, exemplary embodiments of the present invention will now be described relating to systems and methods for the presentation and analysis of clinical interaction data to support prognosis assessment and personalized management of autoimmune diseases.

[0049] Referring now to FIG. 2 , an architecture diagram of an artificial intelligence system 200 for prognostic evaluation of autoimmune diseases is shown. According to certain aspects of the present disclosure, system 200 comprises a computer architecture 204 including an artificial intelligence analytics framework for acquiring, managing, and progressively learning from information and associated relationships in patient profiles, communications, and medical records. According to certain embodiments, system 200 may comprise a patient client device 234, a practitioner client device 238, and one or more electronic health record (EHR) servers 236 communicatively coupled with one or more components of computer architecture 204 via a network communication interface 232. According to certain aspects of the present disclosure, system 200 enables one or more practitioner users 23 to proactively evaluate various data points to improve time to diagnosis and personalized management of one or more autoimmune diseases of a patient user 21. The one or more autoimmune diseases include, but are not limited to, SLE, rheumatoid arthritis, scleroderma, polymyositis, Sjögren's syndrome, Raynaud's syndrome, and mixed connective tissue disease. According to certain aspects of the present disclosure, the patient client devices 234 can facilitate the exchange of patient-specific data with the computer architecture 204 via the network communication interface 232. The patient client devices 234 may be communicatively coupled to one or more of the physiological measurement devices 240 and the body-worn sensor devices 242 via a wireless (e.g., Bluetooth) interface or a wired (e.g., USB) interface. The physiological measurement devices 240 and the body-worn sensor devices 242 may be configured to collect multiple biometric data from the patient-user 21. According to certain aspects of the present disclosure, the biometric data may include heart rate data, heart rate variability data, ECG data, sleep data, activity (i.e., movement / telemetry) data, blood pressure, body temperature, pulse oximetry, etc. According to certain embodiments, the physiological measurement devices 240 and the body-worn sensor devices 242 may be communicatively coupled directly to the computer architecture 204 via the network communication interface 232 (e.g., without a communication interface with the patient client device 234).According to certain embodiments, patient client device 234 may transmit biometric data from physiological measurement device 240 and body-worn sensor device 242 to practitioner client device 238 via network communication interface 232 (e.g., according to one or more data transfer protocols). According to certain aspects of the present disclosure, EHR server 236 may include electronic health record (EHR) data 248 and / or laboratory test data 246 of patient-user 21 stored thereon. EHR data 248 may include a plurality of longitudinal health data for patient-user 21 and a plurality of EHR data specific to the diagnosis, management, and treatment of one or more autoimmune conditions of user 21. Laboratory test data 246 may include blood biomarker test data related to the diagnosis, management, and treatment of one or more autoimmune conditions of user 21. EHR server 236 may communicate EHR data 248 and / or laboratory test data 246 via network communication interface 232 to computer architecture 204 (e.g., according to one or more data transfer protocols). In certain embodiments, the EHR server 236 may transmit and receive EHR data 248 and / or lab test data 246 to and from the practitioner client device 238 via the network communication interface 232 (e.g., according to one or more data transfer protocols).

[0050] According to certain aspects of the present disclosure, computer architecture 204 may include an application programming interface (API) gateway 205 configured to facilitate data transfer between computer architecture 204 and one or more other elements of system 200. In certain embodiments, API gateway 205 may include a Lambda function 206 and an integration service 208. Lambda function 206 may include an event-driven function for managing computer resources of computer architecture 204. In various embodiments, Lambda function 206 (or an equivalent function) is configured to scale up a runtime environment to perform one or more functions (e.g., processing medical record uploads) and scale down runtime functions as needed to efficiently manage computer resources. An example of a Lambda function 206 includes AWS LAMBDA, available from AMAZON WEB SERVICES, Seattle, Washington. Integration service 208 may include a bidirectional data transfer interface for managing the flow of data between computer architecture 204 and one or more elements of system 200. An example of integration service 208 may include AMAZON APPFLOW, available from AMAZON WEB SERVICES, Seattle, Washington. According to certain aspects of the present disclosure, computer architecture 204 may further include one or more web service functions 210-214. In certain embodiments, first web service function 210 may include a simple storage service function configured to provide object storage to computer architecture 204. First web service function 210 may comprise a bucket-based storage architecture and may be configured to manage the storage and routing of multiple object files (e.g., diagnostic record data and laboratory test data). An example of first web service function 210 may include AMAZON S3, available from AMAZON WEB SERVICES, Seattle, Washington. In certain embodiments, second web service function 212 may comprise a real-time data processing function.The second web services function 212 may comprise a scalable and durable real-time data streaming service that ingests and processes data from multiple sources in real time. The second web services function 212 may facilitate a real-time data transfer interface between, among other things, the patient client devices 234, the physiological measurement devices 240, and the body-worn sensor devices 242. An example of the second web services function 212 may include AMAZON KINESIS, available from AMAZON WEB SERVICES, Seattle, Washington. In certain embodiments, the third web services function 214 may comprise relational database functionality for setting up, operating, and scaling one or more relational databases for use with the care management application 230 (described in more detail below). An example of the third web services function 214 may include AMAZON RDS, available from AMAZON WEB SERVICES, Seattle, Washington.

[0051] According to certain aspects of the present disclosure, the computer architecture 204 may include an optical character recognition (OCR) engine 216. The OCR engine 216 may be communicatively engaged with the first web service function 210 to receive one or more medical record files or laboratory test data files. The one or more medical record files or laboratory test data files may comprise scanned PDF documents and / or image file formats. The OCR engine 216 may be configured to operate to process the one or more medical record files or laboratory test data files according to a number of pattern matching algorithms that enable data extraction from printed or written text from scanned documents or image files. The OCR engine 216 may be configured to operate to convert the text into a machine-readable format for use in further data processing (e.g., by an AI engine 218). According to certain aspects of the present disclosure, the computer architecture 204 may include an artificial intelligence (AI) engine 218. The AI ​​engine 218 may be communicatively engaged to receive multiple data streams / inputs from the first web service function 210, the second web service function 212, the third web service function 214, and / or the OCR engine 216. The AI ​​engine 218 may comprise one or more AI frameworks (i.e., models) for acquiring, managing, and progressively learning from information and associated relationships within patient profiles, communications, and medical records in accordance with one or more aspects of the system 200. According to certain embodiments, the AI ​​engine 218 may comprise one or more sub-engines, including a generative AI (gAI) engine 220, a natural language processing (NLP) engine 222, and a machine learning (ML) engine 224. According to certain aspects of the present disclosure, the gAI engine 220 comprises a neural network architecture configured to identify patterns and structures within existing data to generate new original content (e.g., clinical dialogue interactions). In certain embodiments, the gAI engine 220 comprises a large-scale language model.In certain embodiments, the gAI engine 220 is configured to generate clinical dialogue content to facilitate multi-turn dialogue interactions between the dialogue AI agent 228 and the patient-user 21. In accordance with certain aspects of the present disclosure, the gAI engine 220 encompasses a set of computational techniques aimed at realistically simulating human expression (e.g., communication) by assimilating a given situation (e.g., a communication prompt such as, "I felt dizzy when I got out of bed this morning. Should I be worried?") with a predetermined context (e.g., a response should be commensurate with that of a medical professional trained in immunometabolic disorders) and adhering to certain semantic rules (e.g., a response should be friendly and inviting while avoiding aggressive or invasive interrogative behavior and should seek corroborating information). Methods for training such simulated behavior include applying deep learning algorithms to process a previously compiled volume of human expression examples that address both context (i.e., formal and informal literature sources that convey numerous examples of immunometabolic physiology and pathology terms and concepts) and semantics (i.e., specific examples of effective communication and inquiries to emulate, and other examples of undesirable communication to avoid). According to certain aspects of the present disclosure, the gAI engine 220 is comprised of a gAI model that has been rigorously trained (by exposure to examples of best practice medical communication) to tilt the interaction toward a typical “bedside manner” mode of interaction with the patient-user 21 that prompts patient input and mixes medically relevant topics with non-technical “small talk,” the latter of which may provide extraneous topical cues related to the participant / patient’s mood or health status. According to certain aspects of the present disclosure, the gAI model is configured to steer the interaction toward evaluating specific medically related queries while avoiding suggestive bias toward specific answers.

[0052] According to certain aspects of the present disclosure, NLP engine 222 comprises one or more NLP models including one or more NLP algorithms configured to process text data derived from diagnostic record data (e.g., received from OCR engine 216) and patient interaction data (e.g., in response to multiple generated outputs from gAI engine 220) to derive one or more subsets of data that are directly related to (or statistically likely to be related to) criteria indicative of a disease-related health condition of patient-user 21. According to certain embodiments, NLP engine 222 comprises one or more NLP models including one or more NLP algorithms configured to analyze the text data so that text granules (phrases, sentences, paragraphs, etc.) can be targeted for extraction according to context-sensitive criteria (e.g., interest in "expression," but in the specific context of elevated or depressed expression of a given protein marker, as opposed to all other contexts in which that word may be used). According to certain embodiments, the NLP engine 222 comprises one or more NLP models, including one or more NLP algorithms configured to analyze the text data to generate one or more quantitative metrics. The quantification may, for example, evaluate functional similarity to the original query, temporal or spatial proximity within the document to other queries, or corresponding sentiment context to suggest to the patient-user 21 to assign a prognostic value to a given term or terms. Such quantification supports systematic analysis of text documents to temporally or contextually group granules of text insights with other forms of data, such as lab results or biometric measurements. Such grouping enables association, such that text granules frequently observed in periods closely preceding or proximate to major medical events (e.g., flare-ups, recurrences, new diagnoses, etc.) may be assigned greater prognostic value for future monitoring and clinical management of the patient 21.

[0053] According to certain aspects of the present disclosure, the ML engine 224 comprises one or more ML models including one or more ML algorithms configured to process the MR data and the interaction data and one or more outputs from the NLP engine 222 to generate one or more clinical recommendations, clinical insights, pharmaceutical interventions, lab test recommendations, and / or facilitation of one or more interactions between the patient-user 21 and the provider-user 23. Exemplary ML models that may be incorporated into the ML engine 224 include deep learning models such as deep Boltzmann machines, deep belief networks, recurrent neural networks (RNNs), fully convolutional neural networks (FCNs), augmented residual networks (DRNs), generative paradoxical networks (GANs), and deep neural networks (DNNs); ensembles such as random forests, gradient boosting machines, boosting, adaptoboosting, stacked generalization, and gradient boosted regression trees; perceptual, backpropagation, Hopfield, ridge regression, LNNs, and the like. These may include, but are not limited to, neural networks such as ASSO and elastic; rule systems such as cubist, one-rule and zero-rule; linear regression such as ordinary least squares regression, stepwise regression, multivariate adaptive regression splines, local estimation scatterplot smoothing and logistic regression; Bayesian estimation methods such as naive, averaged one-dependent estimators, Gaussian-naive and polynomial-naive; classification, regression, decision trees such as iterative bisection and conditional decision; instance-based methods such as k-nearest neighbors, learning vector quantization and local weighted learning; and clustering methods such as k-means, k-median, expectation-maximum and hierarchical.

[0054] According to certain aspects of the present disclosure, the computer architecture 204 may further comprise an application database 226 communicatively engaged with the AI ​​engine 218 to facilitate data transfer and storage between one or more of the first web services function 210, the second web services function 212, the third web services function 214, and the OCR engine 216. The application database 226 may store one or more model configurations and / or model outputs for the gAI engine 220, the NLP engine 222, and the ML engine 224. According to certain embodiments, the AI ​​engine 218 may be communicatively engaged with a dialogue AI agent 228 configured to present one or more generative clinical dialogue prompts to the patient-user 21 and facilitate one or more multi-turn dialogues with the patient-user 21 (e.g., via a patient-user instance 228′). The patient-user instance 228′ of the conversational AI agent 228 may be configured to present generative clinical dialogue prompts to the patient-user 21 via a user interface of the patient-user device 234 and to receive a plurality of patient responses to the generative clinical dialogue prompts via at least one input device of the patient-user device 234. The computer architecture 204 may further comprise a care management application 230. The care management application 230 may comprise a plurality of application modules, functions, and processor-executable operations for the personalized management of one or more autoimmune diseases of the patient-user 21. According to certain aspects of the present disclosure, the care management application 230 may be operatively associated with the AI ​​engine 218 to provide one or more diagnostic insights, clinical recommendations, pharmaceutical interventions, and lab test recommendations to the patient-user 21 (e.g., via the patient-user application instance 230′) and the provider-user 23 (e.g., via the practitioner-user application instance 230″), and / or to facilitate one or more communications or real-time interactions between the patient-user 21 and the provider-user 23.

[0055] Referring now to FIG. 3 , a flow diagram of an artificial intelligence system 300 for prognosis assessment of autoimmune disease is shown. According to certain aspects of the present disclosure, system 300 is equivalent to system 200 shown and described in FIG. 2 . According to certain aspects of the present disclosure, system 300 illustrates the flow of data and associated operations from data sources 302 to application computing environment 304 and client interface 306. According to certain embodiments, data sources 302 include a conversational AI agent 308 (i.e., a chatbot), a wearable sensor device 310, a physiological sensor device 312, patient diagnostic record data 314, and laboratory test data 316. System 300 is configured to aggregate multiple data types across data sources 302 to receive and process multiple patient-specific data within application computing environment 304. The patient-specific data includes patient-reported data from various applications, sensor-based information from wearable devices, medical records, survey and questionnaire data, and other external data. According to certain aspects of the present disclosure, the application computing environment 304 is configured to receive and process data via web services 318. The web services 318 may process the data and provide it to an application server 320. The application server 320 may include one or more gAI engines, natural language processing engines, and machine learning engines (e.g., deep learning engines) to analyze the data and set up iterative learning and refinement modes. The natural language processing engines, gAI engines, and machine learning engines are configured to analyze the data to generate intelligent recommendations for patient identification, treatment, and other interventions and to track outcomes. Recommendations for patient identification, treatment, and other interventions may be delivered to one or more client devices 322. Patient outcome data and other patient management data may be presented in one or more graphical user interfaces 324.

[0056] Referring now to FIG. 4, a functional block diagram 400 of an artificial intelligence system and method for prognosis assessment of autoimmune disease is shown. According to certain aspects of the present disclosure, the artificial intelligence system for prognosis assessment of autoimmune disease comprises the system 200 shown and described in FIG. 2. According to certain aspects of the present disclosure, a system computer module 401 may be configured to receive and evaluate multiple data inputs, including medical record and lab test data 402 and clinical interaction data 404. According to certain aspects of the present disclosure, the system computer module 401 may be implemented within the computer architecture 204 shown and described in FIG. 2. According to certain aspects of the present disclosure, the system computer module 401 may be configured to receive and process the medical record and lab test data 402 and the clinical interaction data 404 in an AI engine 406. The AI ​​engine 406 may be configured to execute one or more gAI models, NLP models, and ML models according to blocks 408-414. According to certain embodiments, the system 400 may be configured to generate multiple gAI prompts according to the gAI models of the AI ​​engine 406 (block 408). The gAI prompts may drive multiple multi-turn dialogues with the patient-user to derive clinical dialogue data 404 via the AI ​​dialogue agent. The clinical dialogue data 404 may be processed according to an NLP model to identify one or more temporal and / or contextual associations between the medical record and laboratory test data 402 and the clinical dialogue data 404 (block 410). The NLP model may be continuously refined according to the one or more temporal and / or contextual associations between the medical record and laboratory test data 402 and the clinical dialogue data 404 (block 410). One or more outputs of the NLP model may be analyzed by at least a machine learning or deep learning model to derive one or more clinical recommendations, clinical insights, pharmaceutical interventions, laboratory test recommendations, and / or one or more patient-practitioner dialogue facilitation.The output of block 410 may be used to provide a feedback loop in block 414 to further refine / develop one or more AI models (e.g., gAI models, NLP models, and / or ML models).

[0057] According to certain aspects of the present disclosure, system 400 facilitates adaptive refinement, such that growing volumes of disease-specific information (e.g., medical records, lab results, biometric observations, and key text phrases, concepts, and relationships therein) can be periodically subjected to feature selection analysis to identify specific information features or combinations thereof that tend to coincide with or precede significant changes in a patient's condition. This gradually refines the AI ​​models currently present within system 400, highlighting both their specificity and accuracy in characterizing a patient's condition and flagging new conditions that may require medical intervention. Furthermore, a set of spurious metrics (measurements, observations, or text instances not known to be disease-related) can be maintained in parallel and periodically explored using feature selection to potentially determine whether previously unidentified features should be monitored for potential disease associations. This facilitates pathophysiological and pharmacological learning as a by-product of continuous monitoring.

[0058] According to certain aspects of the present disclosure, the system computer module 401 may drive one or more system outputs 416-424. The system outputs may enable multiple actionable application functions for one or more stakeholder users of a care management application for personalized management of autoimmune conditions for patients. According to certain embodiments, the outputs of the system computer module 401 may include multiple provider management outputs 416 including one or more clinical recommendations, clinical insights, pharmaceutical interventions, and laboratory testing recommendations for provider users of the system 400. According to certain embodiments, the outputs of the system computer module 401 may include, for example, a clinical research / trial output 418 including one or more recommendations for participant recruitment / enrollment based on analysis of the medical record and laboratory test data 402 and the clinical interaction data 404. According to certain embodiments, the outputs of the system computer module 401 may include, for example, a prescription and dose management output 420 including pharmaceutical intervention or prescription escalation recommendations for patient-users and / or provider-users based on analysis of the medical record and laboratory test data 402 and the clinical interaction data 404. According to certain embodiments, the output of the system computer module 401 may include a plurality of patient insights 422, including one or more activity or behavior recommendations, patient phenotypes, medication recommendations, lab test recommendations, and pathophysiological insights for the patient-user of the system 400. According to certain embodiments, the output of the system computer module 401 may include the facilitation of one or more patient-caregiver interactions 424, such as automated scheduling of a virtual or in-person medical appointment, a phone call, email, text message, or other communication.

[0059] Referring now to FIG. 5 , a diagram of a process flow 500 of an artificial intelligence system and method for prognostic evaluation of autoimmune disease is shown. The operations of process flow 500 may be performed in the order presented, in a different order, or simultaneously. Furthermore, in some exemplary embodiments, some of the operations may be omitted, added, modified, skipped, etc., without departing from the scope of the present invention. According to certain aspects of the present disclosure, the operations of process flow 500 may be embodied as one or more system routines of system 200 shown and described in FIG. 2 . According to certain aspects of the present disclosure, process flow 500 may include one or more steps or operations for screening a patient according to multiple generated prompts generated by a generative AI model (step 502). Step 502 may include multiple multi-turn dialogues between a conversational AI agent (e.g., a chatbot) and the patient. The conversational AI agent may be configured to receive multiple patient-generated responses (e.g., via voice or text) to the multiple generated prompts. Process flow 500 may proceed by performing one or more steps or actions to receive and process a plurality of patient-generated responses according to a natural language processing model to assess the patient's risk of exhibiting one or more symptoms or signs of an autoimmune disease (step 504). Process flow 500 may further include one or more steps or actions to analyze the plurality of patient-generated responses and / or one or more outputs of the natural language processing model according to at least one machine learning or deep learning framework to refine the patient's risk level and / or provide a recommended diagnosis for the patient (step 506). Process flow 500 may further include one or more steps or actions to provide the patient with one or more remote management tools for managing the diagnosed autoimmune disease (step 508). Step 508 may further include one or more steps or actions of continuous data collection via one or more modalities, including sensor data, biometric data, clinical interaction data (e.g., via a gAI model), blood biomarker test data, diagnostic record data, etc.Process flow 500 may further comprise one or more steps or actions of providing one or more recommended interventions for the management of the diagnosed autoimmune disease to the patient and / or one or more medical practitioners or stakeholder users (step 510). Process flow 500 may further comprise one or more steps or actions of continuously monitoring and processing patient data to track the patient's disease status (e.g., progression, improvement, etc.) (step 512). Process flow 500 may further comprise one or more steps or actions of analyzing system data ad hoc or according to one or more predefined intervals or milestones to assess one or more clinical outcomes for the patient (step 514).

[0060] Referring now to FIG. 6, a process flow diagram of a routine 600 for an artificial intelligence system and method for prognostic assessment of autoimmune disease is shown. The operations of routine 600 may be performed in the order presented, in a different order, or simultaneously. Furthermore, in some exemplary embodiments, some of the operations may be omitted, added, modified, skipped, etc., without departing from the scope of the present invention. According to certain aspects of the present disclosure, routine 600 may be embodied as one or more system routines for system 200 shown and described in FIG. 2. Routine 600 may facilitate one or more steps of process flow 500, as shown in FIG. 5. According to certain aspects of the present disclosure, routine 600 may include one or more steps or operations 602-616 for assessing the risk of an undiagnosed autoimmune condition in a patient-user.

[0061] According to certain aspects of the present disclosure, the routine 600 may include one or more steps or actions of presenting a plurality of clinical dialogue prompts (e.g., according to a generative AI model) to a patient-user via a dialogue AI agent (step 602) and receiving a plurality of dialogue responses from the patient-user via the dialogue AI agent (step 604). In certain embodiments, steps 602-604 comprise a plurality of multi-turn (i.e., conversational) dialogues between the patient-user and the dialogue AI agent. The routine 600 may proceed by performing one or more steps or actions for processing the plurality of dialogue responses received from the patient-user according to an NLP model (step 606). According to certain aspects of the present disclosure, the NLP model is configured to extract one or more features from the plurality of dialogue responses and cluster one or more text segments from the plurality of dialogue responses according to the one or more features. The routine 600 may proceed by performing one or more steps or actions for assessing the patient-user's risk of having an undiagnosed autoimmune condition according to a machine learning model (step 608). In certain embodiments, the routine 600 may assess the patient-user's risk of having an undiagnosed autoimmune condition according to the output of the NLP model (i.e., without separate analysis by a machine learning model). According to certain aspects of the present disclosure, the routine 600 may include a decision step 610 that determines whether the patient-user is at risk (i.e., meets a specified risk threshold) based on the output of step 608. If no (i.e., the patient-user does not meet the specified risk threshold based on multiple interactive responses), the routine 600 proceeds by performing one or more steps or actions to provide the patient-user (e.g., via a conversational AI agent) with a generated response indicating that the patient-user does not exhibit a risk for the autoimmune condition (step 612). If yes (i.e., the patient-user meets the specified risk threshold based on multiple interactive responses), the routine 600 proceeds by performing one or more steps or actions to provide the patient-user (e.g., via a conversational AI agent) with a generated response that provides the patient-user with a risk profile or diagnostic analysis (step 614).According to certain aspects of the present disclosure, the routine 600 may proceed by performing one or more steps or actions to set one or more account parameters for the patient-user within the care management application to enable the patient-user to proceed with one or more subsequent computerized interactions with the artificial intelligence diagnostic framework (step 616).

[0062] 7, there is shown a process flow diagram of a routine 700 for an artificial intelligence system and method for prognostic assessment of autoimmune disease. The operation of the routine 700 can be summarized as follows: The operations may be performed in the order presented, in a different order, or simultaneously. Furthermore, in some exemplary embodiments, some of the operations may be omitted, added, modified, skipped, etc., without departing from the scope of the present invention. Routine 700 may be sequential or sequential to one or more steps or operations of routine 600 (shown in FIG. 6 ) and / or may comprise one or more sub-steps or sub-operations of routine 600. According to certain aspects of the present disclosure, routine 700 may be embodied as one or more system routines for system 200 shown and described in FIG. 2 . Routine 700 may facilitate one or more steps of process flow 500, as shown in FIG. 5 . According to certain aspects of the present disclosure, routine 700 may comprise one or more steps or operations 702-714 that analyze a plurality of diagnostic record data and clinical interaction data to derive a patient phenotype or other patient-specific insight for use in managing the patient-user's autoimmune condition. According to certain aspects of the present disclosure, one or more steps or operations 702-714 follow step 616 of FIG. 6 .

[0063] According to certain aspects of the present disclosure, the routine 700 may comprise one or more steps or operations of receiving and aggregating multiple diagnostic record data (e.g., including multiple medical records for a patient-user) in an application server or distributed computing environment (step 702). The routine 700 may proceed by performing one or more steps or operations of processing the medical records (e.g., one or more scanned PDF files or image files) with an OCR engine to extract (i.e., convert) multiple text data from the medical records (step 704). The routine 700 may proceed by performing one or more steps or operations of processing the diagnostic record data (i.e., the converted text data) and clinical dialogue data (e.g., the multiple dialogue responses and / or one or more additional dialogue responses received by the patient in FIG. 6 ) according to a natural language processing model (step 706). In certain embodiments, the natural language processing model is configured to extract one or more features from the clinical dialogue data and the diagnostic record data and to cluster one or more text segments from the clinical dialogue data and the diagnostic record data according to the one or more features. According to certain aspects of the present disclosure, routine 700 may proceed by performing one or more steps or operations of analyzing one or more text segments to determine one or more temporal or contextual associations between the one or more text segments to generate one or more quantitative data metrics (step 708). According to certain aspects of the present disclosure, routine 700 may generate the one or more quantitative data metrics according to at least one machine learning engine. In certain embodiments, the quantitative data metrics include one or more prognostic values ​​associated with the one or more text segments. According to certain embodiments, step 708 may comprise one or more steps or operations of analyzing the one or more prognostic values ​​for the one or more text segments to generate a prognostic assessment for the patient-user's at least one autoimmune disease.According to certain aspects of the present disclosure, the routine 700 may proceed by performing one or more steps or actions to update and / or modify (i.e., refine) one or more aspects of the NLP model according to the data metrics (step 710). The routine 700 may further comprise one or more steps or actions to update and / or modify (i.e., refine) one or more aspects of the gAI model according to the data metrics (step 712). According to certain aspects of the present disclosure, the routine 700 may proceed according to one or more steps or actions of an artificial intelligence patient management framework (step 714).

[0064] Referring now to FIG. 8 , a process flow diagram of routine 800 for an artificial intelligence system and method for prognostic evaluation of autoimmune disease is shown. The operations of routine 800 may be performed in the order presented, in a different order, or simultaneously. Furthermore, in some exemplary embodiments, some of the operations may be omitted, added, modified, skipped, etc., without departing from the scope of the present invention. Routine 800 may be sequential or sequential to one or more steps or operations of routines 600 and / or 700 (shown in FIGS. 6 and 7 , respectively) and / or may comprise one or more sub-steps or sub-operations of routines 600 and / or 700. According to certain aspects of the present disclosure, routine 800 may be embodied as one or more system routines of system 200 shown and described in FIG. 2 . Routine 800 may facilitate one or more steps of process flow 500, as shown in FIG. 5 . According to certain aspects of the present disclosure, routine 800 may include one or more steps or operations 802-824 for analyzing the plurality of diagnostic record data and clinical interaction data to derive one or more interventions or clinical recommendations for the treatment and / or management of the patient-user's autoimmune condition. According to certain aspects of the present disclosure, one or more steps or operations 702-714, 802-824, follow step 714 of FIG. 7.

[0065] According to certain aspects of the present disclosure, the routine 800 may include one or more steps or operations of presenting a plurality of clinical dialogue prompts (e.g., according to a generative AI model) to a patient-user via a dialogue AI agent (step 802) and receiving a plurality of dialogue responses from the patient-user via the dialogue AI agent (step 804). The plurality of dialogue responses includes a plurality of clinical dialogue data. In certain embodiments, steps 802-804 constitute a plurality of multi-turn (i.e., conversational) dialogues between the patient-user and the dialogue AI agent. The routine 800 may proceed by performing one or more steps or operations of receiving a plurality of patient medical data via one or more data sources. According to certain embodiments, the patient medical data may include a plurality of patient biometric and / or physiological sensor data 808, diagnostic record data 810, and / or blood biomarker test data 812. The routine 800 may proceed by performing one or more steps or operations of processing the patient medical data and the clinical dialogue data according to an NLP model to extract one or more features from the clinical dialogue data and the diagnostic record data and to cluster one or more text segments from the clinical dialogue data and the diagnostic record data according to the one or more features (step 814). In certain embodiments, step 814 may further comprise processing the diagnostic record data 810 and / or the blood biomarker test data 812 according to an OCR engine to transform or extract text from the data for analysis by the NLP engine. The routine 800 may proceed by performing one or more steps or operations of analyzing one or more outputs of step 814 according to an ML engine to generate one or more quantitative metrics for the clinical dialogue data based on one or more temporal or contextual associations between the clinical dialogue data and the patient medical data (step 816). According to certain embodiments, routine 800 may include one or more steps or actions of updating or modifying (i.e., refining) the gAI model(s) and / or NLP model(s) based on the output of step 816 (step 818).The routine 800 may proceed by performing one or more steps or operations processing one or more outputs of step 816 to generate one or more clinical recommendations (step 820). According to certain embodiments, the one or more clinical recommendations may include one or more prognostic or diagnostic insights for the patient. In certain embodiments, the one or more clinical recommendations may include a patient phenotype including one or more personalized pathophysiological insights for the patient. In certain embodiments, the one or more clinical recommendations may include one or more recommended pharmaceutical interventions. In certain embodiments, the one or more clinical recommendations may include a predictive assessment of at least one pathophysiological event associated with an autoimmune disorder. In certain embodiments, the one or more clinical recommendations may include one or more behavioral or environmental recommendations for the patient-user. In certain embodiments, the one or more clinical recommendations may include a clinical recommendation for at least one blood biomarker test for the patient. The routine 800 may proceed by performing one or more steps or operations communicating the clinical recommendations and interventions to the patient-user (step 822) and to the practitioner-user (step 824).

[0066] Referring now to FIG. 9 , a process flow diagram of an artificial intelligence method 900 for prognostic assessment of autoimmune disease is shown. The operations of method 900 may be performed in the order presented, in a different order, or simultaneously. Furthermore, in some exemplary embodiments, some of the operations may be omitted, added, modified, skipped, etc., without departing from the scope of the present invention. According to certain aspects of the present disclosure, method 900 may be embodied as one or more system routines of system 200 shown and described in FIG. 2 . Method 900 may facilitate one or more steps of process flow 500, as shown in FIG. 5 . According to certain aspects of the present disclosure, method 900 may comprise one or more steps or operations 902-918 of analyzing a plurality of clinical interaction data and diagnostic record data of a patient (e.g., according to one or more gAI, NLP, and / or ML models) to identify one or more temporal or contextual associations within the data to generate a personalized prognostic assessment of autoimmune disease for the patient-user.

[0067] According to certain aspects of the present disclosure, method 900 may include one or more steps or actions of presenting a plurality of clinical dialogue prompts to a patient-user (e.g., via a gAI engine executing on at least one server) according to a gAI model (e.g., at one or more timepoints, by a dialogue AI agent) (step 902). Method 900 may further include one or more steps or actions of receiving a plurality of dialogue responses from the patient-user in response to the plurality of clinical dialogue prompts (e.g., at one or more timepoints, by the dialogue AI agent) (step 904). Method 900 may further include one or more steps or actions of receiving (e.g., by at least one server) a first set of text data including the plurality of dialogue responses from the patient-user (step 906). Method 900 may further include one or more steps or actions of receiving (e.g., by at least one server via at least one application programming interface) a first set of diagnostic record data for the patient-user (step 908). In certain embodiments, the first set of diagnostic record data for the patient-user includes at least one of blood biomarker test data and biometric data. Method 900 may further include one or more steps or actions of processing (e.g., by at least one server) the first set of patient-user text data and the first set of diagnostic record data according to a natural language processing model (step 910). In certain embodiments, method 900 may include one or more steps or actions of processing the first diagnostic record data set through an OCR engine to convert one or more scan or image files into a text-searchable format. In certain embodiments, the natural language processing model is configured to extract one or more features from the first set of text data and the first set of diagnostic record data. In certain embodiments, the natural language processing model is configured to cluster one or more text segments from the first set of text data and the first set of diagnostic record data according to the one or more features.Method 900 may further include one or more steps or actions of analyzing one or more text segments according to a natural language processing model to determine one or more temporal or contextual associations between the one or more text segments and the blood biomarker test data and / or biometric data (step 912). Method 900 may further include one or more steps or actions of assigning one or more prognostic values ​​to the one or more text segments according to at least one output of the natural language processing model (step 914). Method 900 may further include one or more steps or actions of analyzing (e.g., by at least one server) the one or more prognostic values ​​for the one or more text segments to generate a prognostic assessment for the patient-user's at least one autoimmune disease (step 916). Method 900 may further include one or more steps or actions of providing (e.g., by at least one server) the prognostic assessment to the practitioner-user and / or the patient-user via a graphical user interface on at least one client device (step 918).

[0068] According to certain aspects of the present disclosure, method 900 may further include one or more steps or operations of configuring (e.g., by at least one server) a dialogue AI model according to the one or more prognostic values ​​for the one or more text segments. In certain embodiments, the dialogue AI model may comprise a large-scale language model. In certain embodiments, the plurality of clinical dialogue prompts may include a plurality of generated prompts according to the dialogue AI model. In certain embodiments, the prognostic assessment includes a diagnostic assessment of at least one autoimmune disease. In certain embodiments, the prognostic assessment includes a predictive assessment of at least one pathophysiological event associated with at least one autoimmune disorder. In certain embodiments, the prognostic assessment includes a clinical recommendation for at least one pharmaceutical intervention for the patient-user. In certain embodiments, the prognostic assessment includes a clinical recommendation of at least one blood biomarker test for the patient-user. In certain embodiments, the biometric data includes data from at least one body-worn sensor of the patient-user. According to certain aspects of the present disclosure, method 900 may further comprise one or more steps or actions of modifying the dialogue AI model to refine one or more clinical dialogue prompts according to one or more prognostic values ​​for one or more text segments to improve the relevance or specificity of one or more future dialogues between the patient-user and the dialogue AI agent.

[0069] Referring now to FIG. 10 , a process flow diagram of an artificial intelligence method 1000 for prognostic assessment of autoimmune disease is shown. The operations of method 1000 may be performed in the order presented, in a different order, or simultaneously. Furthermore, in some exemplary embodiments, some of the operations may be omitted, added, modified, skipped, etc., without departing from the scope of the present invention. According to certain aspects of the present disclosure, method 1000 may be embodied as one or more system routines of system 200 shown and described in FIG. 2 . Method 1000 may facilitate one or more steps of process flow 500, as shown in FIG. 5 . According to certain aspects of the present disclosure, method 1000 may comprise one or more steps or operations 1002-1016 of analyzing a plurality of clinical interaction data and diagnostic record data for a patient (e.g., according to one or more gAI, NLP, and / or ML models) to identify one or more temporal or contextual associations within the data to generate a personalized patent phenotype for the patient-user to drive one or more pathophysiological insights for the patient-user's management of the autoimmune disease.

[0070] According to certain aspects of the present disclosure, method 1000 may include one or more steps or actions of presenting a first set of clinical dialogue prompts to the patient-user (e.g., via a gAI engine executing on the first server) according to a generative AI model (e.g., by a dialogue AI agent communicatively engaged with the first server) (step 1002). Method 1000 may include one or more steps or actions of receiving (e.g., by the dialogue AI agent) a first set of responses to the first set of clinical dialogue prompts from the patient-user (step 1004). Method 1000 may include one or more steps or actions of receiving (e.g., by the first server) a first set of patient diagnostic record data, the first set of diagnostic record data including at least one of blood biomarker test data and biometric data for the patient-user (step 1006). Method 1000 may include one or more steps or actions of receiving (e.g., by a first server) a first set of text data including a first set of responses to a first set of first clinical dialogue prompts from a patient-user (step 1008). Method 1000 may also include one or more steps or actions of processing (e.g., by the first server) the first set of text data and the first set of diagnostic record data according to a natural language processing model (e.g., via an NLP engine executing on the first server) (step 1010). According to certain aspects of the present disclosure, the natural language processing model is configured to extract one or more features from the first set of text data and the first set of diagnostic record data. According to the aspects, the natural language processing model is configured to cluster one or more text segments from the first set of text data and the first set of diagnostic record data according to the one or more features. Method 1000 may include one or more steps or actions of analyzing one or more text segments according to a natural language processing model to determine one or more temporal or contextual associations between the one or more text segments and the blood biomarker test data and / or biometric data (step 1012).Method 1000 may include one or more steps or actions of establishing a patient phenotype for the patient-user according to one or more temporal or contextual associations between one or more text segments and the blood biomarker test data and / or biometric data according to at least one output of the natural language processing model (step 1014). According to certain aspects of the present disclosure, the patient phenotype includes one or more personalized insights about the patient-user, including, for example, one or more symptoms, markers, and pathology triggers for the patient-user's autoimmune disease. Method 1000 may include one or more steps or actions of providing, by at least one server, the patient phenotype for the patient-user to a practitioner-user and / or the patient-user via a graphical user interface on one or more client devices (step 1016).

[0071] According to certain aspects of the present disclosure, method 1000 may further include one or more steps or operations of configuring (e.g., by at least one server) the generative AI model according to the patient phenotype. Method 1000 may further include one or more steps or operations of presenting (e.g., by a dialogue AI agent) a second set of clinical dialogue prompts to the patient-user according to the generative AI model. In certain embodiments, the second set of clinical dialogue prompts is configured (e.g., by the generative AI model) according to the patient phenotype. According to certain aspects of the present disclosure, at least one clinical prompt in the second set of clinical dialogue prompts is different from the first set of clinical dialogue prompts. Method 1000 may further include one or more steps or operations of receiving (e.g., by a dialogue AI agent) a second set of responses to the second set of clinical dialogue prompts from the patient-user. Method 1000 may further include one or more steps or operations of receiving (e.g., by the first server) a second set of diagnostic record data for the patient, the second set of diagnostic record data including a second set of blood biomarker test data and / or a second set of biometric data for the patient-user. Method 1000 may further include one or more steps or operations of receiving (e.g., by the at least one server) a second set of text data including a second set of responses to the second set of clinical dialogue prompts from the patient-user. Method 1000 may further include one or more steps or operations of processing (e.g., by the at least one server) the second set of text data according to a natural language processing model. In certain embodiments, the natural language processing model is configured to extract one or more features from the second set of text data according to a patient phenotype. In certain embodiments, the natural language processing model is configured to cluster one or more text segments from the second set of text data according to the one or more features.Method 1000 may further include one or more steps or operations of processing (e.g., by at least one server) the second set of text data and the second set of diagnostic record data according to a natural language processing model. According to certain aspects of the present disclosure, the natural language processing model is configured to extract one or more features from the second text data set and the second diagnostic record data set according to a patient phenotype. In certain embodiments, the natural language processing model is configured to cluster one or more text segments from the second set of text data and the second set of diagnostic record data according to the one or more features. Method 1000 may further include one or more steps or operations of analyzing (e.g., according to a machine learning model) the one or more text segments to generate a prognostic assessment of the patient-user's autoimmune disease. Method 1000 may further include one or more steps or operations of providing (e.g., by at least one server) the prognostic assessment to the patient-user via a graphical user interface of an end-user device associated with the patient-user and / or providing the prognostic assessment to a practitioner-user via a graphical user interface of a client device. The method 1000 may further comprise one or more steps or actions of updating or modifying the patient phenotype according to at least one output of the natural language processing model. In certain embodiments, the prognostic assessment includes one or more recommended actions for the management of the autoimmune disease for the patient-user.

[0072] Referring now to FIG. 11 , a process flow diagram of an artificial intelligence method for prognostic evaluation of autoimmune disease is shown. The operations of method 1100 may be performed in the order presented, in a different order, or simultaneously. Furthermore, in some exemplary embodiments, some of the operations may be omitted, added, modified, skipped, etc., without departing from the scope of the present invention. According to certain aspects of the present disclosure, method 1100 may be embodied as one or more system routines of system 200 shown and described in FIG. 2 . Method 1100 may facilitate one or more steps of process flow 500, as shown in FIG. 5 . According to certain aspects of the present disclosure, method 1100 may comprise one or more steps or operations 1102-1114 of analyzing a plurality of clinical interaction data and diagnostic record data of a patient (e.g., according to one or more gAI, NLP, and / or ML models) to identify one or more diagnostic triggers of autoimmune disease from the clinical interaction data to improve diagnostic accuracy and shorten time to autoimmune disease diagnosis.

[0073] According to certain aspects of the present disclosure, method 1100 may include one or more steps or actions of presenting a plurality of clinical dialogue prompts to a patient-user at a user interface of the first client device (e.g., by at least one server communicatively engaged with the first client device) in accordance with a generative AI model (e.g., via a gAI engine executing on the at least one server) (step 1102). Method 1100 may further include one or more steps or actions of receiving a plurality of user-generated responses to the plurality of clinical dialogue prompts from the patient-user (e.g., via a dialogue AI agent) (e.g., by the at least one server via the first client device), the plurality of user-generated responses to the plurality of clinical dialogue prompts including a first set of clinical dialogue data (step 1104). Method 1100 may further include one or more steps or actions of receiving a first set of diagnostic record data for the patient-user (e.g., by the at least one server), the first set of diagnostic record data including at least one of blood biomarker test data and biometric data for the patient-user (step 1106). Method 1100 may further include one or more steps or actions of processing (e.g., by at least one server) the first set of clinical dialogue data and the first set of medical record data according to a natural language processing model (e.g., via an NLP engine executing on the at least one server) (step 1108). In certain embodiments, the natural language processing model is configured to extract one or more features from the first set of clinical dialogue data and the first set of diagnostic record data. The natural language processing model may be configured to cluster one or more text segments from the first set of clinical dialogue data and the first set of diagnostic record data according to the one or more features.Method 1100 may further comprise one or more steps or actions of analyzing the one or more text segments according to at least one output of a natural language processing model to determine one or more temporal or contextual associations between the one or more text segments and the blood biomarker test data and / or biometric data (step 1110). Method 1100 may further comprise one or more steps or actions of setting one or more diagnostic triggers for the patient-user according to the one or more temporal or contextual associations between the one or more text segments and the blood biomarker test data and / or biometric data according to the at least one output of the natural language processing model (step 1112). In certain embodiments, step 1112 may further comprise one or more steps or actions of analyzing the at least one output of the natural language processing model according to at least one machine learning model (e.g., via at least one ML engine executing on at least one server). Method 1100 may further include one or more steps or actions of communicating (e.g., by at least one server via a network interface) one or more diagnostic triggers to a patient-user via a first client device and / or one or more diagnostic triggers to a practitioner-user via a second client device (step 1114).

[0074] According to certain aspects of the present disclosure, method 1100 may further comprise one or more steps or actions of configuring (e.g., by at least one server) a natural language processing model according to one or more diagnostic triggers. In certain embodiments, a plurality of clinical dialogue prompts are set according to a generative AI model. In such embodiments, the generative AI model may comprise a large-scale language model. Method 1100 may further comprise one or more steps or actions of configuring (e.g., by at least one server) the generative AI model according to one or more diagnostic triggers. Method 1100 may further comprise one or more steps or actions of presenting a second or subsequent plurality of clinical dialogue prompts to the patient-user at a user interface of the first client device (e.g., by at least one server communicatively associated with the first client device). Method 1100 may further include one or more steps or operations of receiving (e.g., by at least one server via the first client device) second or next plurality of user-generated responses to the second or next plurality of clinical dialogue prompts from the patient-user, where the second or next plurality of user-generated responses to the second or next plurality of clinical dialogue prompts include the second or next set of clinical dialogue data. Method 1100 may further include one or more steps or operations of processing (e.g., by the at least one server) the second or next set of clinical dialogue data according to a natural language processing model to extract one or more features from the second or next set of clinical dialogue data according to the one or more diagnostic triggers. Method 1100 may further include one or more steps or operations of analyzing at least one output of the natural language processing model according to a machine learning model to identify at least one diagnostic trigger from the second or next set of clinical dialogue data. Method 1100 may further include one or more steps or actions of communicating (e.g., by at least one server) at least one diagnostic trigger from the second or subsequent set of clinical interaction data to the practitioner-user via a graphical user interface of a second client device.Method 1100 may further comprise one or more steps or operations of communicating (e.g., by at least one server) at a user interface of the first client device to the patient-user at least one diagnostic trigger from the second or subsequent set of clinical interaction data. Method 1100 may further comprise one or more steps or operations of generating, according to a machine learning model, at least one clinical recommendation for management of the autoimmune disease according to the at least one diagnostic trigger from the second or subsequent plurality of user-generated responses. Method 1100 may further comprise one or more steps or operations of communicating (e.g., by at least one server) at a graphical user interface of the second client device to the practitioner-user at least one clinical recommendation for management of the autoimmune disease. Method 1100 may further comprise one or more steps or operations of communicating (e.g., by at least one server) at a user interface of the first client device to the patient-user at least one clinical recommendation for management of the autoimmune disease.

[0075] 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 invention belongs. Although any methods and materials similar or equivalent to those described herein can also be used in the practice or testing of the present invention, exemplary methods and materials are described below. All publications mentioned herein are incorporated by reference to disclose and describe the methods and / or materials in connection with which the publications are cited.

[0076] It should be noted that when the singular forms "a," "an," and "the" are used in this specification and the appended claims, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. Thus, for example, a reference to a "stimulus" includes a plurality of such stimuli, a reference to a "signal" includes a reference to one or more signals and equivalents thereof known to those skilled in the art, and so forth.

[0077] Any publications discussed herein are provided solely for their disclosure prior to the filing date of the present application. Nothing herein should be construed as an admission that the present invention is not entitled to antedate such publication by virtue of prior invention. Further, the publication dates provided may be different from the actual publication dates, which may need to be independently confirmed.

[0078] As will be appreciated by those skilled in the art, the present invention may be embodied as a method (including, for example, a computer-implemented process, a business process, and / or any other process), an apparatus (including, for example, a system, a machine, a device, a computer program product, and / or any combination thereof), or a combination of the above. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, which may be generally referred to herein as a "system." Furthermore, embodiments of the present invention may take the form of a computer program product, which is a computer-readable medium having computer-executable program code embodied in the medium.

[0079] Any suitable transitory or non-transitory computer-readable medium may be utilized. The computer-readable medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device. More specific examples of computer-readable media include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a compact disc read-only memory (CD-ROM), or other optical or magnetic storage device.

[0080] In the context of this document, a computer-readable medium may be any medium that can contain, store, communicate or transmit a program for use by or in connection with an instruction execution system, apparatus or device. The computer usable program code may be transmitted using any suitable medium, including, but not limited to, the Internet, wire, fiber optic cable, radio frequency (RF) signal or other medium.

[0081] Computer-executable program code for carrying out operations of embodiments of the present invention may be written in an object-oriented, scripted or non-scripted programming language such as Java, Perl, Smalltalk, C++, etc. However, computer program code for carrying out operations of embodiments of the present invention may also be written in conventional procedural programming languages, such as the "C" programming language or a similar programming language.

[0082] Embodiments of the present invention have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products. It will be understood that each block of the flowchart illustrations and / or block diagrams and / or combinations of blocks in the flowchart illustrations and / or block diagrams can be implemented by computer-executable program code portions. These computer-executable program code portions may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to generate a specific machine, such that the code portions, which execute via the processor of the computer or other programmable data processing apparatus, create mechanisms for performing the functions / acts specified in the blocks or blocks of the flowchart illustrations and / or block diagrams.

[0083] These computer-executable program code portions may be stored in computer-readable memory that can instruct a computer or other programmable data processing apparatus to function in a particular manner to produce an article of manufacture that includes an instruction mechanism that performs the functions / acts specified in the flowchart and / or block diagram blocks, the code portions stored in the computer-readable memory.

[0084] The computer-executable program code may be loaded into a computer or other programmable data processing apparatus to cause the computer or other programmable apparatus to execute a series of operational phases to generate a computer-implemented process such that the code portions executing on the computer or other programmable apparatus provide phases for performing the functions / acts specified in the flowchart and / or block diagram blocks. Alternatively, the steps or acts performed by a computer program may be combined with steps or acts performed by an operator or human being to implement embodiments of the present invention.

[0085] As used herein, a processor may be "configured" to perform particular functions in various ways, such as by executing particular computer-executable program code embodied on a computer-readable medium, by causing one or more general-purpose circuits to perform the functions, and / or by causing one or more application-specific circuits to perform the functions.

[0086] Embodiments of the present invention have been described above with reference to flowcharts and / or block diagrams. It should be understood that process steps described herein may be performed in an order other than the order shown in the flowcharts. In other words, the steps represented by flowchart blocks may, in some embodiments, be performed in an order other than that shown, or may be combined, divided, or performed simultaneously. It should also be understood that block diagram blocks merely represent conceptual divisions between systems, and that, in some embodiments, one or more of the systems illustrated by the block diagram blocks may be combined with or share hardware and / or software with one or more of the systems illustrated by the block diagram blocks. Similarly, devices, systems, apparatuses, and / or the like may be comprised of one or more devices, systems, apparatuses, and / or the like. For example, when a processor is illustrated or described herein, the processor may be comprised of multiple microprocessors or other processing devices, which may or may not be coupled to each other. Similarly, when a memory is illustrated or described herein, the memory may be comprised of multiple memory devices, which may or may not be coupled to each other.

[0087] As in the above specification, in the claims, all transitional phrases such as "comprise," "include," "have," "have," "include," "involve," "hold," and "consist" are to be understood to be open-ended, i.e., to mean including but not limited to. As provided for in the U.S. Patent Office's Manual of Patent Examining Procedure, Section 211.03, only the transitional phrases "consisting of" and "consisting essentially of" shall be closed or semi-closed transitional phrases, respectively.

[0088] While certain exemplary embodiments have been described and illustrated in the accompanying drawings, it is to be understood that such embodiments are merely illustrative of the broad invention, and are not limiting, and that the invention is not limited to the specific construction and arrangement shown and described, since various other changes, combinations, omissions, modifications, and substitutions are possible in addition to those described in the preceding paragraphs. Those skilled in the art will appreciate that various adaptations and modifications of the embodiments just described can be made without departing from the scope and spirit of the invention. It is therefore to be understood that within the scope of the appended claims, the invention may be practiced other than as specifically described herein.

Claims

1. 1. A computer-implemented method for assessing the prognosis of an autoimmune disease, comprising: presenting, by the dialogue AI agent, a plurality of clinical dialogue prompts to the patient-user at one or more time points; receiving, by the dialogue AI agent, a plurality of dialogue responses from the patient-user in response to the plurality of clinical dialogue prompts at the one or more time points; receiving, by at least one server, a first set of text data including the plurality of dialogue responses from the patient-user; receiving, by the at least one server via at least one application programming interface, a first set of diagnostic record data for the patient-user; the first set of diagnostic record data for the subject-user includes at least one of blood biomarker test data and biometric data; processing, by the at least one server, the first set of text data and the first set of diagnostic record data for the patient-user according to a natural language processing model; the natural language processing model is configured to extract one or more features from the first set of text data and the first set of diagnostic record data; the natural language processing model is configured to cluster one or more text segments from the first set of text data and the first set of diagnostic record data according to the one or more features; analyzing the one or more text segments according to the natural language processing model to determine one or more temporal or contextual associations between the one or more text segments and blood biomarker test data and / or biometric data; assigning one or more prognostic values ​​to the one or more text segments according to at least one output of the natural language processing model; analyzing, by the at least one server, the one or more prognostic values ​​for the one or more text segments to generate at least one autoimmune disease prognostic assessment for the patient-user; providing, by said at least one server, said prognostic assessment to a practitioner user via a graphical user interface on a client device; 1. A computer-implemented method comprising:

2. The computer-implemented method of claim 1 , further comprising: configuring, by the at least one server, the dialogue AI model according to the one or more prognostic values ​​for the one or more text segments.

3. The computer-implemented method of claim 2 , wherein the dialogue AI model comprises a large-scale language model.

4. The computer-implemented method of claim 2 , wherein the plurality of clinical dialogue prompts comprises a plurality of generated prompts according to the dialogue AI model.

5. The computer-implemented method of any one of claims 1 to 4, wherein the prognostic evaluation comprises a diagnostic evaluation of at least one autoimmune disease.

6. The computer-implemented method of any one of claims 1 to 5, wherein said prognostic assessment comprises a predictive assessment of at least one pathophysiological event associated with at least one autoimmune disorder.

7. The computer-implemented method of any one of claims 1 to 6, wherein said prognostic assessment comprises at least one clinical recommendation of pharmaceutical intervention for said patient-user.

8. The computer-implemented method of any one of claims 1 to 7, wherein the prognostic assessment comprises a clinical recommendation of at least one blood biomarker test for the patient-user.

9. The computer-implemented method of any one of claims 1 to 8, wherein the biometric data includes data from at least one body-worn sensor of the patient-user.

10. 10. The computer-implemented method of claim 2, further comprising modifying the plurality of clinical dialogue prompts according to the one or more prognostic values ​​for the one or more text segments via the dialogue AI model.

11. 11. A computer-implemented system for assessing the prognosis of an autoimmune disease, comprising: a processing unit; and a non-transitory computer-readable medium communicatively associated with the processing unit, the non-transitory computer-readable medium comprising stored processor-executable instructions that, when executed by the processing unit, cause the processing unit to perform one or more operations comprising the computer-implemented method of any one of claims 1 to 10.

12. 11. A computer program product embodied in a non-transitory computer-readable medium, the computer program product comprising processor-executable instructions that, when executed by a processing unit, cause the processing unit to perform one or more operations comprising the computer-implemented method of any one of claims 1 to 10.

13. 1. A computer-implemented method for patient phenotyping for autoimmune disease, comprising: presenting, by a dialogue AI agent communicatively engaged with the first server, a first set of clinical dialogue prompts to the patient-user according to the generative AI model; receiving, by the dialogue AI agent, a first set of responses to the first set of clinical dialogue prompts from the patient-user; receiving, by the first server, a first set of patient diagnostic record data, the first set of diagnostic record data including at least one of blood biomarker test data and biometric data of the patient-user; receiving, by at least one server, a first set of text data including a first set of responses to the first set of clinical dialogue prompts from the patient-user; processing, by the at least one server, the first set of text data and the first set of diagnostic record data according to a natural language processing model; the natural language processing model is configured to extract one or more features from the first set of text data and the first set of diagnostic record data; the natural language processing model is configured to cluster one or more text segments from the first set of text data and the first set of diagnostic record data according to the one or more features; analyzing the one or more text segments according to the natural language processing model to determine one or more temporal or contextual associations between the one or more text segments and blood biomarker test data and / or biometric data; establishing a patient phenotype for the patient-user according to one or more temporal or contextual associations between the one or more text segments and blood biomarker test data and / or biometric data according to at least one output of the natural language processing model; the patient phenotype comprising one or more symptoms, markers, and pathological triggers for an autoimmune disease of the patient-user; providing, by the at least one server, the patient phenotype for the patient-user to a practitioner-user via a graphical user interface on a client device; 1. A computer-implemented method comprising:

14. 14. The computer-implemented method of claim 13, further comprising configuring, by the at least one server, the generative AI model according to the patient phenotype.

15. 15. The computer-implemented method of claim 13, further comprising presenting, by the dialogue AI agent, a second set of clinical dialogue prompts to the patient-user in accordance with the generative AI model.

16. The computer-implemented method of claim 15 , wherein the second set of clinical dialogue prompts is configured according to the patient phenotype.

17. The computer-implemented method of any one of claims 15 to 16, wherein at least one clinical prompt of the second set of clinical dialogue prompts is different from the first set of clinical dialogue prompts.

18. 18. The computer-implemented method of any one of claims 15 to 17, further comprising receiving, by the dialogue AI agent, a second set of responses to the second set of clinical dialogue prompts from the patient-user.

19. 19. The computer-implemented method of any one of claims 15 to 18, further comprising receiving, by the first server, a second set of diagnostic record data for a patient, the second set of diagnostic record data including a second set of blood biomarker test data and / or a second set of biometric data for the patient-user.

20. 20. The computer-implemented method of any one of claims 15 to 19, further comprising receiving, by the at least one server, a second set of text data comprising a second set of responses from the patient-user to the second set of clinical dialogue prompts.

21. 21. The computer-implemented method of claim 20, further comprising processing, by the at least one server, the second set of text data according to the natural language processing model.

22. 22. The computer-implemented method of claim 21, wherein the natural language processing model is configured to extract one or more features from the second set of text data according to the patient phenotype.

23. 23. The computer-implemented method of claim 22, wherein the natural language processing model is configured to cluster one or more text segments from the second set of text data according to the one or more features.

24. 21. The computer-implemented method of claim 20, further comprising processing, by the at least one server, the second set of text data and the second set of diagnostic record data according to the natural language processing model.

25. 25. The computer-implemented method of claim 24, wherein the natural language processing model is configured to extract one or more features from the second set of text data and the second set of diagnostic record data according to the patient phenotype.

26. 26. The computer-implemented method of claim 25, wherein the natural language processing model is configured to cluster one or more text segments from the second set of text data and the second set of diagnostic record data according to the one or more features.

27. 24. The computer-implemented method of any one of claims 21 to 23, further comprising analyzing the one or more text segments according to a machine learning model to generate an autoimmune disease prognosis assessment for the patient-user.

28. 27. The computer-implemented method of any one of claims 24 to 26, further comprising analyzing the one or more text segments according to a machine learning model to generate an autoimmune disease prognosis assessment for the patient-user.

29. 29. The computer-implemented method of claim 27 or 28, further comprising providing, by said at least one server, said prognosis assessment to said subject-user via a graphical user interface of an end-user device associated with said subject-user.

30. 29. The computer-implemented method of claim 27 or 28, further comprising providing, by said at least one server, a prognosis assessment to said practitioner-user via a graphical user interface of said client device.

31. 24. The computer-implemented method of any one of claims 21 to 23, further comprising updating or modifying the patient phenotype according to at least one output of the natural language processing model.

32. 27. The computer-implemented method of any one of claims 24 to 26, further comprising updating or modifying the patient phenotype according to at least one output of the natural language processing model.

33. 31. The computer-implemented method of claim 29 or 30, wherein the prognostic assessment comprises one or more recommended actions for the management of the autoimmune disorder for the patient-user.

34. 34. A computer-implemented system for assessing the prognosis of an autoimmune disease, comprising: a processing unit; and a non-transitory computer-readable medium communicatively associated with the processing unit, the non-transitory computer-readable medium comprising stored processor-executable instructions that, when executed by the processing unit, cause the processing unit to perform one or more operations comprising the computer-implemented method of any one of claims 13 to 33.

35. 34. A computer program product embodied in a non-transitory computer-readable medium, the computer program product comprising processor-executable instructions that, when executed by a processing unit, cause the processing unit to perform one or more operations comprising the computer-implemented method of any one of claims 13 to 33.

36. 1. A computer-implemented method for identifying diagnostic triggers for autoimmune disease from clinical interaction data, comprising: presenting, by at least one server communicatively associated with a first client device, a plurality of clinical interaction prompts to a patient-user at a user interface of the first client device; receiving, by the at least one server, a plurality of user-generated responses to the plurality of clinical dialogue prompts from the patient-user via the first client device, the plurality of user-generated responses to the plurality of clinical dialogue prompts including a first set of clinical dialogue data; receiving, by the at least one server, a first set of diagnostic record data for the patient-user, the first set of diagnostic record data including at least one of blood biomarker test data and biometric data for the patient-user; processing, by the at least one server, the first set of clinical dialogue data and the first set of diagnostic record data according to a natural language processing model; the natural language processing model is configured to extract one or more features from the first set of clinical dialogue data and the first set of diagnostic record data; the natural language processing model is configured to cluster one or more text segments from the first set of clinical dialogue data and the first set of diagnostic record data according to the one or more features; analyzing the one or more text segments according to at least one output of the natural language processing model to determine one or more temporal or contextual associations between the one or more text segments and blood biomarker test data and / or biometric data; setting one or more diagnostic triggers for the patient-user according to one or more temporal or contextual associations between the one or more text segments and blood biomarker test data and / or biometric data according to at least one output of the natural language processing model; communicating, by the at least one server via a network interface, the one or more diagnostic triggers for the patient-user to a practitioner-user via a graphical user interface of a second client device; 1. A computer-implemented method comprising:

37. 37. The computer-implemented method of claim 36, wherein the plurality of clinical dialogue prompts are configured according to a generative AI model.

38. 38. The computer-implemented method of claim 37, wherein the generative AI model comprises a large-scale language model.

39. 38. The computer-implemented method of any one of claims 36-37, further comprising configuring, by the at least one server, the natural language processing model according to the one or more diagnostic triggers.

40. 39. The computer-implemented method of any one of claims 37-38, further comprising configuring, by the at least one server, the generative AI model according to the one or more diagnostic triggers.

41. 41. The computer-implemented method of claim 40, further comprising presenting, by the at least one server communicatively involved with the first client device, a second or next plurality of clinical interaction prompts to the patient-user in a user interface of the first client device.

42. 42. The computer-implemented method of claim 41, further comprising receiving, by the at least one server via the first client device, second or next plurality of user-generated responses to second or next plurality of clinical dialogue prompts from the patient-user, wherein the second or next plurality of user-generated responses to the second or next plurality of clinical dialogue prompts include the second or next set of clinical dialogue data.

43. 43. The computer-implemented method of claim 42, further comprising processing, by the at least one server, the second or subsequent set of clinical dialogue data according to the natural language processing model to extract one or more features from the second or subsequent set of clinical dialogue data according to the one or more diagnostic triggers.

44. 44. The computer-implemented method of claim 43, further comprising analyzing an output of at least one of the natural language processing models according to a machine learning model to identify at least one diagnostic trigger from the second or subsequent set of clinical interaction data.

45. 45. The computer-implemented method of claim 44, further comprising communicating, by the at least one server, the at least one diagnostic trigger from the second or subsequent set of clinical interaction data to the practitioner-user via a graphical user interface of the second client device.

46. 45. The computer-implemented method of claim 44, further comprising communicating, by the at least one server, the at least one diagnostic trigger from the second or subsequent set of clinical interaction data to the patient-user in a user interface of a first client device.

47. 45. The computer-implemented method of claim 44, further comprising generating, according to the machine learning model, at least one clinical recommendation for management of the autoimmune disease according to the at least one diagnostic trigger from a second or subsequent plurality of user-generated responses.

48. 48. The computer-implemented method of claim 47, further comprising communicating, by the at least one server, via a graphical user interface of the second client device to the practitioner-user, at least one clinical recommendation for management of the autoimmune disease.

49. 48. The computer-implemented method of claim 47, further comprising communicating, by the at least one server, at a user interface of the first client device to the patient-user, at least one clinical recommendation for management of the autoimmune disease.

50. 50. A computer-implemented system for assessing the prognosis of an autoimmune disease, comprising a processing unit and a non-transitory computer-readable medium communicatively associated with the processing unit, the non-transitory computer-readable medium comprising stored processor-executable instructions that, when executed by the processing unit, cause the processing unit to perform one or more operations comprising the computer-implemented method of any one of claims 36 to 49.

51. 50. A computer program product embodied in a non-transitory computer readable medium, the computer program product comprising processor-executable instructions that, when executed by a processing unit, cause the processing unit to perform one or more operations comprising the computer-implemented method of any one of claims 36 to 49.

52. A system for evaluating the prognosis of an autoimmune disease, comprising: a first client device associated with a patient-user, said first client device comprising a first graphical display and a first input / output device; a second client device associated with the practitioner user, said second client device comprising a second graphical display and a second input / output device; an application server communicatively participating with the first client device and the second client device via a network communication interface, the application server comprising a generative AI engine and a natural language processing engine; the application server comprising at least one processor and a non-transitory computer-readable medium, the non-transitory computer-readable medium, when executed by the at least one processor, presenting a plurality of clinical dialogue prompts at the first client device according to a generative AI model that executes the generative AI engine; receiving a plurality of dialogue responses from the patient-user in response to the plurality of clinical dialogue prompts, the plurality of dialogue responses including a first set of text data; receiving, via at least one application program interface, a first set of diagnostic record data for the patient-user; the first set of diagnostic record data for the subject-user includes at least one of blood biomarker test data and biometric data; processing the first set of text data and the first set of diagnostic record data for the patient-user according to a natural language processing model implementing a natural language processing engine; the natural language processing model is configured to extract one or more features from the first set of text data and the first set of diagnostic record data; the natural language processing model is configured to cluster one or more text segments from the first set of text data and the first set of diagnostic record data according to the one or more features; analyzing the one or more text segments according to the natural language processing model to determine one or more temporal or contextual associations between the one or more text segments and blood biomarker test data and / or biometric data; assigning one or more prognostic values ​​to the one or more text segments according to the natural language processing model; analyzing the one or more prognostic values ​​for the one or more text segments to generate at least one autoimmune disease prognostic assessment for the patient-user; providing the prognostic assessment to the first client device and / or a second client device via the network communications interface; 1. A system comprising: stored processor-executable instructions that cause the processor to perform one or more operations comprising:

53. 53. The system of claim 52, further comprising at least one biometric sensor configured to collect biometric data of the subject-user.

54. 54. The system of claim 53, wherein the at least one biometric sensor comprises a body-worn sensor configured to continuously collect the biometric data when worn by the patient-user.

55. 55. The system of claim 54, wherein the at least one biometric sensor is communicatively coupled to the first client device for real-time communication of multiple sensor inputs including the biometric data to the first client device.

56. 56. The system of claim 55, wherein the first client device is configured to communicate the biometric data to the application server via the network communication interface.

57. 57. The system of any one of claims 52 to 56, wherein the generative AI model comprises a large-scale language model.

58. 58. The system of any one of claims 52 to 57, wherein the biometric data includes at least one data type selected from the group consisting of electrocardiogram data, heart rate data, heart rate variability data, sleep data, and activity data.

59. The system of any one of claims 52 to 58, wherein the prognostic evaluation comprises a diagnostic evaluation of at least one autoimmune disease.

60. The system of any one of claims 52 to 59, wherein the prognostic evaluation comprises a predictive evaluation of at least one pathophysiological event associated with at least one autoimmune disorder.

61. 61. The system of any one of claims 52 to 60, wherein the prognostic assessment includes at least one clinical recommendation of pharmaceutical intervention for the patient-user.

62. 62. The system of any one of claims 52-61, wherein the prognostic assessment comprises a clinical recommendation of at least one blood biomarker test for the patient-user.

63. 1. A system for patient phenotyping for autoimmune diseases, comprising: a first client device associated with a patient-user, said first client device comprising a first graphical display and a first input / output device; a second client device associated with the practitioner user, said second client device comprising a second graphical display and a second input / output device; an application server communicatively participating with the first client device and the second client device via a network communication interface, the application server comprising a generative AI engine and a natural language processing engine; the application server comprising at least one processor and a non-transitory computer-readable medium, the non-transitory computer-readable medium, when executed by the at least one processor, presenting a first set of clinical dialogue prompts at the first client device according to a generative AI model that executes the generative AI engine; receiving a first set of dialogue responses from the patient-user in response to the first set of clinical dialogue prompts, the first set of dialogue responses including a first set of text data; receiving a first set of diagnostic record data for the subject-user, the first set of diagnostic record data including at least one of blood biomarker test data and biometric data for the subject-user; processing the first set of text data and the first set of diagnostic record data according to a natural language processing model implementing a natural language processing engine; the natural language processing model is configured to extract one or more features from the first set of text data and the first set of diagnostic record data; the natural language processing model is configured to cluster one or more text segments from the first set of text data and the first set of diagnostic record data according to the one or more features; analyzing the one or more text segments according to a machine learning model to determine one or more temporal or contextual associations between the one or more text segments and blood biomarker test data and / or biometric data; establishing a patient phenotype for the patient-user according to one or more temporal or contextual associations between the one or more text segments and blood biomarker test data and / or biometric data according to the machine learning model; the patient phenotype comprising one or more symptoms, markers, and pathological triggers for an autoimmune disease of the patient-user; providing the patient phenotype for the subject-user to the first client device and / or a second client device via the network communications interface; 1. A system comprising: stored processor-executable instructions that cause the processor to perform one or more operations comprising:

64. 64. The system of claim 63, further comprising at least one biometric sensor configured to collect biometric data of the subject-user.

65. 65. The system of claim 64, wherein the at least one biometric sensor comprises a body-worn sensor configured to continuously collect the biometric data when worn by the patient-user.

66. 66. The system of claim 65, wherein the at least one biometric sensor is communicatively coupled to the first client device for real-time communication of multiple sensor inputs including the biometric data to the first client device.

67. 67. The system of claim 66, wherein the first client device is configured to communicate the biometric data to the application server via the network communication interface.

68. 68. The system of any one of claims 63 to 67, wherein the generative AI model comprises a large-scale language model.

69. 69. The system of any one of claims 63 to 68, wherein the biometric data includes at least one data type selected from the group consisting of electrocardiogram data, heart rate data, heart rate variability data, sleep data, and activity data.

70. 70. The system of any one of claims 63 to 69, wherein the one or more operations further comprise configuring the generative AI model according to the patient phenotype.

71. 71. The system of any one of claims 63 to 70, wherein the one or more actions further include presenting a second set of clinical dialogue prompts at the first client device in accordance with the generative AI model.

72. 72. The system of claim 71, wherein the second set of clinical dialogue prompts is configured according to the patient phenotype.

73. 73. The system of any one of claims 71 to 72, wherein at least one clinical prompt in the second set of clinical dialogue prompts is different from the first set of clinical dialogue prompts.

74. 74. The system of any one of claims 71 to 73, wherein the one or more actions further comprise receiving a second set of dialogue responses from the patient-user in response to the second set of clinical dialogue prompts, the second set of dialogue responses including a second set of text data.

75. 75. The system of any one of claims 71-74, wherein the one or more operations further comprise receiving a second set of diagnostic record data for the patient, the second set of diagnostic record data including a second set of blood biomarker test data and / or a second set of biometric data for the patient-user.

76. 76. The system of any one of claims 71 to 75, wherein the one or more operations further comprise processing the second set of text data according to the natural language processing model.

77. 77. The system of claim 76, wherein the natural language processing model is configured to extract one or more features from the second set of text data according to the patient phenotype.

78. 78. The system of claim 77, wherein the natural language processing model is configured to cluster one or more text segments from the second set of text data according to the one or more features.

79. 79. The system of any one of claims 76 to 78, wherein the one or more actions further comprise updating or modifying the patient phenotype according to at least one output of the natural language processing model.

80. 80. The system of any one of claims 76-79, wherein the one or more operations further comprise analyzing the one or more text segments to generate an autoimmune disease prognosis assessment for the patient-user.

81. 81. The system of claim 80, wherein the one or more actions further comprise providing the prognosis assessment to the first client device and / or the second client device via the network communications interface.

82. 82. The system of claim 81, wherein the prognostic assessment includes one or more recommended actions for management of the autoimmune disorder for the patient-user.

83. 1. A system for identifying diagnostic triggers for autoimmune disease from clinical interaction data, comprising: a first client device associated with a patient-user, said first client device comprising a first graphical display and a first input / output device; a second client device associated with the practitioner user, said second client device comprising a second graphical display and a second input / output device; an application server communicatively participating with the first client device and the second client device via a network communication interface, the application server comprising a generative AI engine and a natural language processing engine; the application server comprising at least one processor and a non-transitory computer-readable medium, the non-transitory computer-readable medium, when executed by the at least one processor, presenting a plurality of clinical dialogue prompts to a patient-user at the first client device according to a generative AI model executing the generative AI engine; receiving a plurality of user-generated responses to the plurality of clinical dialogue prompts from the patient-user, the plurality of user-generated responses to the plurality of clinical dialogue prompts including a first set of clinical dialogue data; receiving a first set of diagnostic record data for the subject-user, the first set of diagnostic record data including at least one of blood biomarker test data and biometric data for the subject-user; processing the first set of clinical dialogue data and the first set of diagnostic record data according to a natural language processing model implementing a natural language processing engine; the natural language processing model is configured to extract one or more features from the first set of clinical dialogue data and the first set of diagnostic record data; the natural language processing model is configured to cluster one or more text segments from the first set of clinical dialogue data and the first set of diagnostic record data according to the one or more features; analyzing the one or more text segments according to at least one output of the natural language processing model to determine one or more temporal or contextual associations between the one or more text segments and blood biomarker test data and / or biometric data; setting one or more diagnostic triggers for the patient-user according to one or more temporal or contextual associations between the one or more text segments and blood biomarker test data and / or biometric data according to at least one output of the natural language processing model; communicating the one or more diagnostic triggers to the first client device and / or a second client device via the network communications interface; 1. A system comprising: stored processor-executable instructions that cause the processor to perform one or more operations comprising:

84. 84. The system of claim 83, further comprising at least one biometric sensor configured to collect biometric data of the subject-user.

85. 85. The system of claim 84, wherein the at least one biometric sensor comprises a body-worn sensor configured to continuously collect the biometric data when worn by the patient-user.

86. 86. The system of claim 85, wherein the at least one biometric sensor is communicatively coupled to the first client device for real-time communication of multiple sensor inputs including the biometric data to the first client device.

87. 87. The system of claim 86, wherein the first client device is configured to communicate the biometric data to the application server via the network communication interface.

88. 88. The system of any one of claims 83 to 87, wherein the generative AI model comprises a large-scale language model.

89. 89. The system of any one of claims 83 to 88, wherein the biometric data includes at least one data type selected from the group consisting of electrocardiogram data, heart rate data, heart rate variability data, sleep data, and activity data.

90. 90. The system of any one of claims 83 to 89, wherein the one or more actions further comprise configuring or modifying the natural language processing model according to the one or more diagnostic triggers.

91. 91. The system of any one of claims 83 to 90, wherein the one or more actions further comprise configuring or modifying the generative AI model according to the one or more diagnostic triggers.

92. 92. The system of claim 91 , wherein the one or more actions further comprise presenting a second or next plurality of clinical dialogue prompts to the patient-user at the first client device in accordance with the generative AI model.

93. 93. The system of claim 92, wherein the one or more operations further comprise receiving second or next plurality of user-generated responses to second or next plurality of clinical dialogue prompts from the patient-user, the second or next plurality of user-generated responses to the second or next plurality of clinical dialogue prompts including the second or next set of clinical dialogue data.

94. 94. The system of claim 93, wherein the one or more operations further comprise processing the second or subsequent set of clinical dialogue data according to the natural language processing model to extract one or more features from the second or subsequent set of clinical dialogue data according to the one or more diagnostic triggers.

95. 95. The system of claim 94, wherein the one or more operations further comprise analyzing at least one output of the natural language processing model to identify at least one diagnostic trigger from a second or subsequent set of the clinical interaction data.

96. 96. The system of claim 95, wherein the one or more operations further comprise communicating at least one diagnostic trigger from a second or subsequent set of clinical interaction data to the first client device and / or the second client device via the network communication interface.

97. 97. The system of any one of claims 94 to 96, wherein the one or more operations further comprise generating, according to a machine learning model, at least one clinical recommendation for management of an autoimmune disease according to at least one diagnostic trigger from the second or subsequent set of clinical interaction data.

98. 98. The system of claim 97, wherein the one or more operations further comprise communicating the at least one clinical recommendation for management of the autoimmune disease to the first client device and / or the second client device via the network communication interface.

Images