| CPC G16H 50/30 (2018.01) [G16H 20/00 (2018.01); G16H 50/70 (2018.01)] | 37 Claims |
|
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.
|