# US 12,224,070 B2 · Method of evaluating autoimmune disease risk and treatment selection > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,224,070 B2 - Document ID: US12224070B2 - Status: Granted - Kind: B2 - Application number: 17/596,015 - Filed: 2020-06-02 - Published: 2022-07-14 - Granted: 2025-02-11 - Earliest claimed: 2019-06-02 - Assignees: Predicta Med LTD - Applicants: Predicta Med LTD; Shlomit Steinberg-Koch; Benjamin Getz - Inventors: Shlomit Steinberg-Koch; Benjamin Getz - Web page: https://patentgrep.com/patent/US12224070B2 ## CPC - G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] - G16H 50/30: for calculating health indices; for individual health risk assessment - G06N 3/0499: Feedforward networks - G06N 3/08: Learning methods - G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning - G06N 3/09: Supervised learning - G06N 3/091: Active learning - G06N 3/092: Reinforcement learning - G06N 3/0985: Hyperparameter optimisation; Meta-learning; Learning-to-learn - G16H 20/00: ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - G16H 70/60: relating to pathologies - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G16H 20/10: relating to drugs or medications, e.g. for ensuring correct administration to patients - G16H 20/30: relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising - G16H 20/60: relating to nutrition control, e.g. diets - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract Methods enabling prediction, screening, early diagnosis, and recommended intervention or treatment selection of autoimmune conditions using artificial intelligence operating in conjunction with large medical datasets. Logic is applied to historic population data to extract medical features and identify subjects with diagnosed autoimmune conditions, and the pre-diagnosis medical data is used to train a diagnosis classification algorithm. A self-supervised learning mechanism is separately used to generate a feature embedding transformation of the patients medical history into representational feature vectors. These patient feature vectors together with their expected diagnoses are used to train a multi-label classifier model using supervised learning. The embedding transformation and the multi-label classifier are then applied to a current subjects data to generate a patient diagnosis probability vector, predicting the existence of autoimmune conditions. These methods are applied to diagnose gastrointestinal autoimmune disorders using celiac disease as example. ## Claims ### Claim 1 A method for predictive diagnosis of at least one autoimmune disease in a subject, comprising: (i) applying to health related data of the subject, a machine learning method adapted to convert parameters of the health related data, some of which may be indicative of a diagnosis of an autoimmune disease, into a vector that provides a compact representation of the health related data that reflects a medical condition of the subject; and (ii) applying a classifier model to the vector generated in step (i) to identify whether the medical condition of the subject indicates a likelihood of the subject having or developing an autoimmune disease, wherein the method comprises identifying the subject as having the likelihood of developing an autoimmune condition even when the subject is clinically asymptomatic; wherein the classifier model is generated by: (iii) accessing databases comprising records of health related data of a large population; wherein the records of health comprise electronic medical records (EMR), electronic heath records (EHR), insurance claims data and patient sensor data; wherein records of heath comprise structured data that is formatted to be searchable in relational databases, and unstructured data that lacks a pre-defined format or organization; (iv) tagging at least most of the records with information indicating if a member of the large population with whom a record is associated, has been diagnosed with an autoimmune disease; (v) performing the machine learning method, using self-supervised representation learning, on at least some of the tagged health related records, to convert tagged records into target diagnosis vectors indicating that the member associated with the tagged record has been diagnosed with an autoimmune disease; wherein the machine learning process is applied on tagged health related records that convey information about members only before the members were diagnosed with the autoimmune disease; (vi) training the classifier model iteratively to relate features of each target diagnosis vector with a previous diagnosis of an autoimmune disease by associating features of the target diagnosis vector representing the tagged records with the previous diagnosis of an autoimmune disease; and (vii) repeating the training until the associating features of the target diagnosis vector with the diagnosis of an autoimmune disease shows a desired level of accuracy, such that application of the classifier model to the vector generated in step (i) predicts with the desired level of accuracy, the likelihood that the subject has an autoimmune disease. ### Claim 2 (depends on 1) A method according to claim 1, wherein an autoimmune disease is at least one of a gastrointestinal autoimmune disease such as celiac disease, ulcerative colitis, or Crohn's disease. ### Claim 3 (depends on 1) A method according to claim 1, wherein the tagging comprises retroactively identifying and labeling each member medical history prior to the diagnosis of the member with autoimmune conditions that the member has been later positively diagnosed with. ### Claim 4 (depends on 1) A method according to claim 1, wherein the machine learning method is developed using self-supervised representation learning. ### Claim 5 (depends on 4) A method according to claim 4, wherein self-supervised representation learning uses a form of artificial intelligence. ### Claim 6 (depends on 1) A method according to claim 1, wherein the multi-class classifier model is developed using supervised learning. ### Claim 7 (depends on 6) A method according to claim 6, wherein supervised learning uses a form of artificial intelligence. ### Claim 8 (depends on 1) A method according to claim 1, wherein the accessing comprises using EMR-specific modular computer plugins for accessing the EMR, and providing access to doctors and policy makers to an output of step (ii) using an EMR's application programming interface. ### Claim 9 (depends on 1) A method according to claim 1, wherein tagging the records is performed using expert medical logic. ### Claim 10 (depends on 1) A method according to claim 1, wherein a database comprising records of health related data of a large population is used to generate the machine learning method. ### Claim 11 (depends on 1) A method according to claim 1, wherein the same database is used for generating both the machine learning method and the classifier model. ### Claim 12 (depends on 1) A method according to claim 1 further comprising generating an alert through electronic medical records regarding subjects with a risk factor above a pre-selected or automatically determined threshold. ### Claim 13 (depends on 1) A method according to claim 1 wherein the health related data of the subject is tagged and added to the database comprising records of health related data of the large population. ### Claim 14 (depends on 9) A method according to claim 9 wherein feedback from the health practitioner is appended into the expert medical logic to improve accuracy of the predictive diagnostic method. ### Claim 15 (depends on 1) A method according to claim 1, wherein the parameters are defined by current legacy methods based on a least one of published medical literature, diseases registries, medical practice guidelines and said medical data. ### Claim 16 (depends on 1) A method according to claim 1, wherein the health-related data comprises at least some of electronic medical or health records, the internet of things or other sensor data, health application data, and data from medical claims. ### Claim 17 (depends on 1) A method according to claim 1, wherein training the classifier model is performed using at least one of artificial intelligence, machine learning, deep learning, natural language processing, reinforcement learning, and big data analytics techniques. ### Claim 18 (depends on 1) A method according to claim 1, wherein the classifier model is a multi-label classifier model that outputs multiple results associated with the likelihood of the subject having more than one specific type of autoimmune disease or autoimmune related disease. ### Claim 19 (depends on 1) A method according to claim 1, further comprising: using supervised learning, training an intervention recommendation model to provide at least one of recommended intervention, treatment selection, disease management recommendations, and decision support guidelines. ### Claim 20 (depends on 19) A method according to claim 19, wherein the intervention recommendation model is trained by supervised learning from at least one of either the success or the effectiveness of interventions and treatments in the database comprising records of health related data of a large population. ### Claim 21 (depends on 1) A method according to claim 1, wherein the subject belongs to a subpopulation of the large population whose records of health related data comprise the database. ### Claim 22 (depends on 1) A method according to claim 1, wherein the health related data of the large population database are pre-processed by standardizing, marking and filling missing data points, and normalizing inputs. ### Claim 23 (depends on 22) A method according to claim 22, wherein the health related data of the large population database are used to create self-supervised training data. ### Claim 24 (depends on 23) A method according to claim 23, wherein the training data are used to train the machine learning method used to create embedding vectors that are a compact representation of the input semantics and context. ### Claim 25 (depends on 1) A method according to claim 1, wherein the health related data of the large population database are standardized by turning string-type data into categorical data. ### Claim 26 (depends on 1) A method according to claim 1, wherein missing data are handled by identification, marking, and filling in absent data points as actual data. ### Claim 27 (depends on 26) A method according to claim 26, wherein absent data points are allocated a median value, and the statistical distribution of continuous data is normalized. ### Claim 28 (depends on 1) A method according to claim 1, wherein optimal hyper-parameters are chosen and exported based on model test results on validation data. ### Claim 29 (depends on 1) A method according to claim 1, wherein the machine learning method is a feature embedding transformation. ### Claim 30 (depends on 1) A method according to claim 1, wherein the tagging of the records is also performed with information indicating with which autoimmune disease the member has been diagnosed. ### Claim 31 (depends on 1) A method according to claim 1, wherein application of the classifier model to the vector generated in step (i) predicts with the desired level of accuracy, the likelihood that the subject has a specific autoimmune disease. ### Claim 32 (depends on 1) A method according to claim 1, further comprising: applying an intervention recommendation model to the patient diagnosis probability vector, if the subject is identified as having greater than a pre-defined likelihood of having or developing an autoimmune disease, wherein the intervention recommendation model is generated by: a) accessing a database comprising records of health related data of members of a large population; b) using expert medical logic to determine most effective treatment and follow up parameters of members of the large population who have been previously diagnosed with and treated for an autoimmune disease; and c) training the intervention recommendation model iteratively to provide model parameters that meet accuracy requirements on test inputs, the model parameters provided by the intervention recommendation model being applied to the health related data of the subject and the patient diagnosis probability vector, to generate recommended interventions. ### Claim 33 A system for predictive diagnosis of at least one autoimmune disease in a subject, comprising: at least one processor, a memory and at least one type of data storage; wherein the at least one processor is configured to: (i) apply to health related data of the subject, a machine learning method adapted to convert parameters of the health related data, some of which may be indicative of a diagnosis of an autoimmune disease, into a vector that provides a compact representation of the health related data that reflects a medical condition of the subject; and ii) apply a classifier model to the vector generated in step (i) to identify whether the medical condition of the subject indicates a likelihood of the subject having or developing an autoimmune disease, wherein the at least one processor is further configured to generate the classifier model by: (iii) accessing databases comprising records of health related data of a large population; wherein the records of health comprise electronic medical records (EMR), electronic heath records (EHR), insurance claims data and patient sensor data; wherein records of heath comprise structured data that is formatted to be searchable in relational databases, and unstructured data that lacks a pre-defined format or organization; (iv) tagging at least most of the records with information indicating if a member of the large population with whom a record is associated, has been diagnosed with an autoimmune disease; (v) performing the machine learning method, using self-supervised representation learning, on at least some of the tagged health related records, to convert tagged records into target diagnosis vectors indicating that the member associated with the tagged record has been diagnosed with an autoimmune disease; wherein the machine learning process is applied on tagged health related records that convey information about members only before the members were diagnosed with the autoimmune disease; (vi) training the classifier model iteratively to relate features of each target diagnosis vector with a previous diagnosis of an autoimmune disease by associating features of the target diagnosis vector representing the tagged records with the previous diagnosis of an autoimmune disease; and (vii) repeating the training until the associating features of the target diagnosis vector with the diagnosis of an autoimmune disease shows a desired level of accuracy, such that application of the classifier model to the vector generated in step (i) predicts with the desired level of accuracy, the likelihood that the subject has an autoimmune disease; wherein the at least one processor is configured to identify the subject as having the likelihood of developing an autoimmune condition even when the subject is clinically asymptomatic. ### Claim 34 (depends on 33) The system according to claim 33, wherein the at least one processor is further configured to provide at least one of recommended interventions, referrals to specialists, schedule of follow up testing, and a ranked list of treatment recommendations. ### Claim 35 (depends on 33) The system according to claim 33, wherein the artificial intelligence algorithms comprise a machine learning algorithm that was applied on tagged health related records that convey information about members only before the members were diagnosed with the autoimmune disease. ### Claim 36 (depends on 33) The system according to claim 33, further comprising a user interface that provides to a human operator at least one of recommended interventions, referrals to specialists, schedule of follow up testing, and ranked list of treatment recommendations. ### Claim 37 (depends on 34) The system according to claim 34, wherein recommended interventions include health-promoting activities such as diet or exercise, and treatment recommendations include drugs or other chemical therapies.