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.

Abstract: A method for normalizing health related events (HREs) count variables, the method includes (i) storing, in a storage unit, the HREs count variables, the HRE count variables represent an occurrence of HREs of different types in relation to a group of patients; (ii) granting, to a plurality of users, a remote access to the storage unit via one or more man machine interfaces, thereby facilitating an update of the HREs count variables by one or more users of the plurality of users; (iii) converting the HREs count variables to normalized HRE information items; wherein a HRE count variable represents a number of occurrences of a HER of a given type of the different types during a defined period in relation to a patient of the group; wherein a normalized HRE information item related to the HRE count variable is normalized to the patients of the group and is normalized to the HREs of the different types that are related to the patient; wherein the converting comprises applying a term frequency and inverse document fr

Abstract: A method for reducing dependency of non-discrete laboratory measurements results on personal parameters, the method includes (i) storing, in a storage unit, health related events (HREs) count variables that represent an occurrence of HREs of different types in relation to a group of patients; (ii) granting, to a plurality of users, a remote access; (iii) converting the HREs count variables to normalized HRE information items; wherein a normalized HRE information item related to the HRE count variable is normalized to the patients of the group and is normalized to the HREs of the different types that are related to the patient; wherein the converting comprises applying a term frequency and inverse document frequency (TF-IDF) process; and (iv) storing the normalized HRE information items in the storage unit; wherein the storing of the normalized HRE information items make available to at least one user of the plurality of users the normalized HRE information items.

Abstract: A method for predictive diagnosis of a disease in a person, the method includes (i) obtaining, by a machine learning process hosted by a first processing circuit, a health related data of the person that is stored in a first data structure; (ii) applying by the first processing circuit, the machine learning process, on the health related data to convert the health related data into a vector that provides a compact representation of the health related data, the vector comprises disease predicting information of the health related data; (iii) storing the vector in a second data structure; (iii) obtaining the vector by a classifier model hosted by a second processing circuit; (iv) applying, by the second processing circuit, the classifier model to the vector to identify whether there is a likelihood of the person having or developing the disease; and (v) storing an outcome of the applying of the classifier model in a third data structure; wherein the storing of the outcome makes available the outcome to one or m

Abstract: A method for early diagnosis of an autoimmune or chronic disease in subject. The method includes (i) selecting, out of missing existing health related data of the subject (HRDS) items, a subject-specific subset; (ii) obtaining at least one missing existing HRDS item; (iii) adding the at least one obtained HRDS item to an existing HRDS to provide an updated HRDS; (iv) applying to the updated HRDS, a second machine learning model adapted to convert parameters of the updated HRDS, some of which may be indicative of the early development stages of the disease, into a second vector that provides a compact representation of the updated HRDS that reflects on the medical condition of the subject; and (v) applying a second classifier model to the second vector to provide a second classification result that is indicative of a second likelihood of the subject having or developing the disease.

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.

Abstract: Methods enabling prediction, screening, early diagnosis, and recommended intervention or treatment selection of chronic medical 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 chronic 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 patient's 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 subject's data to generate a patient diagnosis probability vector, predicting the existence of chronic conditions.