Patent Application Titled “A Method Of Evaluating Autoimmune Disease Risk And Treatment Selection” Published Online (USPTO 20220223293): Predicta Med Ltd.
2022 AUG 02 (NewsRx) -- By a
The assignee for this patent application is
Reporters obtained the following quote from the background information supplied by the inventors: “Autoimmune disease as a category affects 50 million Americans. It is one of the top ten causes of death in women under the age of 65, is the second highest cause of chronic illness, and is the top cause of morbidity in women in
“There are 100+ known autoimmune diseases, all caused by a common thread which is the autoimmunity process. The autoimmunity process is initiated when one’s immune system becomes overactive and, rather than destroy invader cells, such as infections and viruses, targets one’s own healthy cells and tissues causing various autoimmune diseases. Autoimmune diseases can affect any system in the body. Nearly any body part can be involved. The symptoms vary widely among the various types and in-between different subjects, making the autoimmune diseases difficult to diagnose. Common symptoms include low grade fever and feeling tired. Some autoimmune diseases have a hereditary component, and certain cases may be triggered by infections or other environmental factors. Common diseases that are generally considered autoimmune include celiac disease, diabetes mellitus type 1, Graves’ disease, inflammatory bowel disease, multiple sclerosis, psoriasis, rheumatoid arthritis, and systemic lupus erythematosus.
“Providing the correct treatment for an autoimmune disease is a complex puzzle. To obtain proper treatment, subjects must visit a wide variety of specialties within medicine. Because autoimmune diseases affect multiple organs and systems in the body, teams of physicians ranging from rheumatologist, ophthalmologist, neurologist, and gastroenterologist often are needed to treat symptoms of an individual subject. This method of treatment is time consuming and often fiscally wasteful as there is typically no model for proper coordinated care amongst medical systems and physicians, needed to enable adequate monitoring, diagnostic testing and prescription drug treatments. Also, the addition of new cutting edge biologic treatments for autoimmune patients requires an even higher level of coordination and expertise from physicians as these treatments, while revolutionary as lifesaving and quality of life-enhancing tools, must be heavily monitored for short-term and long-term adverse side effects and dosage issues.
“One of the most prevalent autoimmune diseases, which usually takes multiple years to diagnose is celiac disease (CD; also known as coeliac disease, celiac sprue, non-tropical sprue, and gluten-sensitive enteropathy). Celiac disease is a multifactorial, autoimmune enteropathy characterized by gluten sensitivity and diverse clinical features, which may develop over many years. Contributing factors to the development of a clinical diagnosis of celiac disease comprise genetic, immunological and environmental factors. The genetic influence is primarily derived from two of the many human leukocyte antigens (HLA), specifically alleles DQ2 and DQ8. CD damages the villi of the small intestine and interferes with absorption of nutrients from food. According to recent research, the worldwide prevalence of celiac disease is 1.4% based on serologic (blood) testing, while 83%-95% of these patients remain undiagnosed. An estimated 1 in 133 Americans, or almost 1% of the population, has celiac disease (affecting men and women of all ages and races). It is estimated that over 80% of Americans who have CD are undiagnosed or misdiagnosed with other conditions. This means that about 2.4 million individuals in the US suffer with signs and symptoms of CD without a diagnosis and thus without targeted treatment. The time a person with celiac waits to be correctly diagnosed is on average 6-10 years. A recent study found that the mean delay to diagnosis from the first symptoms was 9.7 years, and from the first doctor visit, 5.8 years. The celiac disease diagnosis rate by 2019 was estimated to reach only 50-60%. The cost reduction in early detection of celiac can potentially save billions of dollars to the American health care system.
“Delay in CD diagnosis can lead to a number of other disorders including infertility, reduced bone density, neurological disorders, some cancers, and other autoimmune diseases. A study published in 2009 yielded two major findings-first, undiagnosed CD was associated with a nearly 4-fold increased risk of death compared with subjects without serologic evidence of CD. Second, the prevalence of CD appears to have increased dramatically in
“Early detection can be challenging: Both diagnostic rates and diagnostic delays show that celiac disease has a low rate of suspicion on clinical grounds. Two contributory factors in the difficulty of CD diagnosis are that the gastrointestinal symptoms may overlap with those found in other disorders, and that in some individuals the gastrointestinal component is mild or even mostly absent. On the other hand, the implications of late/delayed diagnosis are significant. Untreated CD results in poor Health-Related Quality of Life (HRQoL), a score that is improved relative to that of the general population if an individual with CD is diagnosed and treated. By shortening the diagnostic delay, it is possible to reduce this unnecessary burden of disease. The mean quality-adjusted life year (QALY) score during the year prior to initiated treatment was 0.66; it improved after diagnosis and treatment to 0.86, which was then better than that of the general population (0.79).
“Currently, for most children and adults, the best way to screen for celiac disease is with the tissue transglutaminase IgA (TTG-IgA) antibody. In order to render the celiac disease test accurate, sometimes a gluten challenge is administered to ensure that the subject generates enough of the TTG-IgA antibody. Sensitivity rate for this test is 98% and specificity is 95%. Because of potential for false antibody test results, a biopsy of the small intestine is the only definite way to diagnose celiac disease.
“Markov modeling suggests that, given the mortality associated with untreated symptomatic celiac disease, targeted screening may be cost effective in areas of moderate to high prevalence. Screening would involve performing the blood test for TTG-IgA in any individual suspected of having CD. Whereas this effort would entail a significant cost and give false-negative results in 2% of cases, even despite increased awareness in society and in health care, many CD cases would be missed in a screening campaign due to vague or atypical symptoms. Another possible suggested option is mass screening for CD. CD mass screening fulfils most of the listed criteria for a medical mass screening adapted by WHO from the 1968 classic guidelines on disease screening by Wilson and Jungner. It was recently estimated in
“Aside from CD, other autoimmune related gastrointestinal disorders cause significant morbidity and also have a rate of delayed diagnosis in the general population. Inflammatory bowel disease (IBD) has two major forms: Crohn’ s disease (CD) and ulcerative colitis (UC). The incidence of CD in
“Currently, only serology and blood tests are being used to detect and predict CD, which, while acceptably effective, are inconvenient methods, such that potential sufferers may forego the tests, and not be diagnosed correctly. There also exist a number of prior patents and patent applications in the field of using algorithms for the diagnosis of celiac and other diseases as listed below:
“EP 2,367,561 Compositions and methods for treatment of celiac disease
“U.
“U.
“U.
“U.
“WO 2010/030929 Methods and systems for incorporating multiple environmental and genetic risk factors
“US 2010/094560 Methods for diagnosing irritable bowel syndrome
“US 2014/051594 Methods for diagnosing irritable bowel syndrome
“US 2019/0108912 Method for predicting and detecting disease
“US 2018/0321259 Pathway specific markers for diagnosing irritable bowel syndrome’
There is additional background information. Please visit full patent to read further.”
In addition to obtaining background information on this patent application, NewsRx editors also obtained the inventors’ summary information for this patent application: “The methods of the present disclosure are based on the ability to cluster individuals or groups of individuals based on defining characteristics, such as demographic, symptoms, lab test results, medications, procedures, biomarkers, or other measurable properties, while recognizing that individuals differ in an almost infinite number of characteristics representing their biologic individuality. The methods of the present disclosure collect, store, and analyze huge bodies of data to classify people according to their individual likelihood of acquiring symptoms of a specific autoimmune disease or having a specific autoimmune disease which is undiagnosed at the point of the data collection.
“Because most autoimmune diseases develop over time, during which affected individuals are clinically asymptomatic, and because genetic markers of heightened inherited susceptibility can be measured in genome-wide association studies long before symptoms are noticed, identifying potential patients at an asymptomatic stage provides an opportunity to initiate preventive measures and minimize late-phase interventions which are primarily ineffective after irreversible tissue damage has occurred. Taken together with immunologic and biochemical markers, genomic markers can indicate that a potentially damaging autoimmune process is in process long before symptoms occur, at a stage when intervention has a higher likelihood of preventing long-term damage.
“The present disclosure describes new exemplary methods for predicting the risk in potential or latent patients, of the presence or the evolution of an autoimmune disease, using CD as an exemplary disorder. The method provides a screening recommendation for the general population according to relative risk, enables early diagnosis, and assists in formulating a treatment plan and disease management. The present disclosure describes a decision support platform, using artificial intelligence (AI) techniques such as machine learning, deep learning, and natural language processing (NLP) to enable early detection and personalized treatment selection. Information may be collected from the internet of things (IoT), a system of interrelated computing devices, mechanical and digital machines, objects, animals or people that are provided with unique identifiers and the ability to transfer data over a network without requiring human-to-human or human-to-computer interaction.
“The novel algorithms of the present disclosure process a collection of subject data collected from sources comprising at least some of electronic medical records (EMR), electronic health records (EHR), insurance claims data, patient sensors data such as IoT sensors, or data from health application programs, and suggest a subject’s risk for having a common or uncommon autoimmune related disease, such as CD, IBD (Crohn’s disease/ulcerative colitis), multiple sclerosis (MS), rheumatoid arthritis (RA), systemic lupus erythematosus (SLE), and others. The method prioritizes subjects according to probability/risk and makes recommendations regarding the appropriate subsequent steps, such as related tests or prescription of a specific treatment. The system provides explanatory output regarding relevant symptoms and signs, and analyzes trends, symptom recurrence, symptom distribution and all relevant patient history, to determine the risk of the particular subject having or developing the specific disease under consideration by the system. The service enables providers to seamlessly integrate this solution into their current workflow by either integrating the algorithms and software into the existing EMR system or by providing a separate software interface.
“The present disclosure describes a method of evaluating risk for autoimmune disease risk, such as CD, inflammatory bowel disease, ulcerative colitis, MS, RA, SLE, and other autoimmune related disorders. One exemplary method comprises the steps of:
“i) collecting medical data of subjects in a target population, comprising a set of features such as symptoms, blood test results, other lab tests, diagnostics, medications, biomarkers and measurements as collected,
“ii) providing at least one classifier, which may be a multi-label classifier, that has been trained on a large population dataset to diagnose at least one specific autoimmune disease such as CD, these classifiers are trained and tested on a large set of sample subjects; a collection of symptoms; concurrent diagnoses; or other parameters, and includes some subjects with a diagnosis of CD or other autoimmune related diseases mentioned above who were previously diagnosed by traditional means, and
“iii) applying the algorithmic classifier to individual subjects’ data collection, resulting in the probability of the target individuals having CD (or any of the other autoimmune related diseases).
“In some embodiments of the present disclosure, imaging processing is used to correlate the small intestinal biopsy results to the predictive model. Intestinal biopsy provides tissue for microscopic analysis of the intestinal villi, revealing signs not only of current severe disease, but in subjects predicted by the model to have a high risk of developing or having CD, also about the potential and latent celiac population. These predictions are based on milder microscopic changes, such as inflammation, loss of villi height, or inflammatory cell infiltration, in the intestinal tissue.
“The method may also predict the risk of a given subject to develop CD or any other autoimmune related disease in the future. For example, given the genetic predisposition of individuals with specific white blood cell markers, i.e., human leukocyte antigens (HLA) alleles DQ2 and/or DQ8, to develop CD, first degree relatives of such individuals are at higher risk of developing the disease compared with the general population. Finally, the method provides an option for personalized treatment selection according to the target individual’s clinical presentation and data related characteristics. The method follows the subject’s medical data throughout therapy and classifies the individual response to each treatment. Over time, the algorithm classifies each individual according to other individuals with the same feature patterns and their responses to each treatment. This provides an opportunity for new subjects to be introduced into the appropriate classification, starting the optimal treatment immediately. Thus, the system allows for personalized care and treatment selection based on subjects’ clustering and similarities.
“The present disclosure reveals an AI-based decision support platform which analyzes subjects’ data from multiple sources such as EMR, EHR, claims data, sensor data, or health application data, and calculates a risk factor (probability) for having autoimmune related disease, examples of which may be CD, IBD, MS, RA, SLE and others. The method is focused on helping healthcare providers identify autoimmune related illnesses in undiagnosed subjects as early as possible and select the best treatment for these patients.
“The platform can be integrated into the EMR system and thus perform several functions. Firstly, it raises an alert through the EMR regarding subjects with a risk factor above a pre-selected or automatically determined threshold, and based on that alert the doctor can summon the individual for further examination or, using the system, send the individual for follow up tests. Another option is that the health insurance provider will use the system via the care manager, or other individual in a position of managing business operations and patient care, and send requests for the providers to further examine specific individuals or summon the individual for further examination at his doctor’s office or, using the system, send the individual for follow up tests. Secondly, the system provides the doctor with all the disease-relevant data and recommended actions to have a full clinical picture during visits of patients whose evaluations have superseded the threshold of probability for having CD. Thirdly, it provides the users with a customizable interface which tracks all subjects at risk, prioritizes them and includes information about their risk factor, symptoms, recommended future examinations, etc. The current method thus provides a solution for both symptomatic and atypically symptomatic subjects, of which the latter are especially hard to diagnose due to the non-gastrointestinal nature of their symptoms. The method has a built-in flexibility, such that HMO policy makers or health care providers can set a policy determining the desired ratio of false positive: false negative outcomes, affecting the cost-benefit ratio of the HMO. This policy is made by setting a threshold for the risk factor, above or below which subjects are called into the clinic to be further examined and diagnosed.”
There is additional summary information. Please visit full patent to read further.”
The claims supplied by the inventors are:
“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 classifier model is generated by: (iii) accessing a database comprising records of health related data of a large population; (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 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; (vi) training the classifier model iteratively to relate features of each target diagnosis vector with a previous diagnosis of an autoimmune disease by correlating parameters of the tagged records representing features of an autoimmune disease for the member associated with that record; and (vii) repeating the training until the correlation of parameters 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.
“2. A method according to claim 1, wherein an autoimmune disease may be at least one of a gastrointestinal autoimmune disease such as celiac disease, ulcerative colitis, or Crohn’s disease.
“3. A method according to either of the previous claims, wherein the classifier model is trained to predict a diagnosis of either a specific autoimmune disease or any autoimmune disease.
“4. A method according to any of the previous claims, wherein the machine learning method is developed using self-supervised representation learning.
“5. A method according to claim 4, wherein self-supervised representation learning uses a form of artificial intelligence.
“6. A method according to any of the previous claims, wherein the multi-class classifier model is developed using supervised learning.
“7. A method according to claim 6, wherein supervised learning uses a form of artificial intelligence.
“8. A method according to any of the previous claims, wherein the database comprises historical data on a subpopulation of subjects having a diagnosis of an autoimmune disease.
“9. A method according to any of the previous claims, wherein tagging the records is performed using expert medical logic.
“10. A method according to any of the previous claims, wherein a database comprising records of health related data of a large population is used to generate the machine learning method.
“11. A method according to any of the previous claims, wherein the same database is used for generating both the machine learning method and the classifier model.
“12. A method according to any of the previous claims wherein the predicted diagnosis of an autoimmune disease in the subject is validated by a health practitioner.
“13. A method according to any of the previous claims 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.
“14. A method according to claim 12 wherein feedback from the health practitioner is appended into the expert medical logic to improve accuracy of the predictive diagnostic method.
“15. A method according to any of the previous claims, 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.
“16. A method according to any of the previous claims, 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.
“17. A method according to any of the previous claims, 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.
“18. A method according to any of the previous claims, 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.
“19. A method according to any of the previous claims, 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.
“20. 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.
“21. A method according to any of the previous claims, wherein the subject belongs to a subpopulation of the large population whose records of health related data comprise the database.
“22. A method according to any of the previous claims, wherein the health related data of the large population database are pre-processed by standardizing, marking and filling missing data points, and normalizing inputs.
“23. A method according to claim 22, wherein the health related data of the large population database are used to create self-supervised training data.
“24. 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.
“25. A method according to any of the previous claims, wherein the health related data of the large population database are standardized by turning string-type data into categorical data.
“26. A method according to any of the previous claims, wherein missing data are handled by identification, marking, and filling in absent data points as actual data.
“27. A method according to claim 26, wherein absent data points are allocated a median value, and the statistical distribution of continuous data is normalized.
“28. A method according to any of the previous claims, wherein optimal hyper-parameters are chosen and exported based on model test results on validation data.
“29. A method according to any of the previous claims, wherein the machine learning method is a feature embedding transformation.
“30. A method according to any of the previous claims, wherein the tagging of the records is also performed with information indicating with which autoimmune disease the member has been diagnosed.
“31. A method according to any of the previous claims, 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.
“32. A method according to any of the previous claims, 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.”
There are additional claims. Please visit full patent to read further.
For more information, see this patent application: GETZ, BENJAMIN; STEINBERG-KOCH, Shlomit. A Method Of Evaluating Autoimmune Disease Risk And Treatment Selection. Filed
(Our reports deliver fact-based news of research and discoveries from around the world.)
Sun Yat-sen University Reports Findings in Science (Does direct settlement of intra-province medical reimbursements improve financial protection among middle-aged and elderly population in China? Evidence based on CHARLS data): Science
Patent Issued for Distribution of infusion pumps (USPTO 11386482): Bigfoot Biomedical Inc.
Advisor News
- Economy ‘in a sweet spot’ but some concerns ahead
- Trump, Capitol allies likely looking at quick cryptocurrency legislation
- SEC panel reviews mandatory arbitration clause in investment advisory agreements
- Financial shocks, caregiving, inflation and technology are top retirement concerns
- Proposal to raise Social Security age under fire
More Advisor NewsAnnuity News
Health/Employee Benefits News
- Luigi Mangione murder case draws scrutiny of health claim denial rates, with three of Maryland's top insurers higher than average
- 5 of the most frustrating health insurer tactics and why they exist
- Wisp Partners with Nourish to Offer Patients on GLP-1s Personalized Nutrition Counseling
- Act Fast and You Can Still Enroll In An ACA Healthcare Plan for 2025
- Vanderbilt Poll: Tennesseans support Medicare expansion, gun reform
More Health/Employee Benefits NewsLife Insurance News