FIELD: physics.
SUBSTANCE: invention relates to the field of artificial intelligence. Processing data contained in patient's medical history selected from pre-formed training sample; converting said data into a sequence of medical facts for each patient using medical ontologies; performing the obtained sequence of medical facts automatic marking for each patient using the diagnoses or other facts of interest extracted from the patient's medical history; training primary representations independently for each of the modalities; training of joint representations; final model and aggregation parameters training; patient's medical history not included in the training sample is obtained, and preliminary data processing is performed; converting processed data into a sequence of medical facts using medical ontologies; obtained set of facts is sent to input to trained final models; diagnosis is determined, analysis and prognosis of patient's diseases development is performed with highest probability corresponding to presented set of facts.
EFFECT: technical result is higher accuracy of diagnosis, analysis and prediction of developing disease for the patient.
3 cl, 11 dwg
