The solution is based on the mathematic models of patient representation.

The platform uses a combination of three main technologies: deep learning technologies for processing medical images and combining heterogeneous medical data into a vector that encodes all medical data about the patient; medical ontologies for the preparation of mathematical models and interpretation of the results of using artificial intelligence technologies; presentation of results for automatic annotation of recognizable medical images and mechanism of “attention”, which makes it possible to simplify the evaluation of the reliability of the mathematical model’s performance by a physician.