公开(公告)号：US12224070B2

公开(公告)日：2025-02-11

申请号：US17596015

申请日：2020-06-02

Applicant: Predicta Med LTD ,  Shlomit Steinberg-Koch ,  Benjamin Getz

Inventor： Shlomit Steinberg-Koch ,  Benjamin Getz

IPC: G16H50/30 ,  G16H20/00 ,  G16H50/70

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.

公开(公告)号：US20220223293A1

公开(公告)日：2022-07-14

申请号：US17596015

申请日：2020-06-02

Applicant: SHLOMIT STEINBERG-KOCH ,  BENJAMIN GETZ ,  Predicta Med LTD

Inventor： Shlomit STEINBERG-KOCH ,  BENJAMIN GETZ

IPC: G16H50/30 ,  G16H50/70 ,  G16H20/00

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.