GENERATION OF CONCEPT SCORES BASED ON ANALYSIS OF CLINICAL DATA

Techniques for clinical concept score generation are provided. A set of keywords related to a clinical concept are determined, and a plurality of attributes is identified by searching a plurality of electronic health records (EHRs) based on the set of keywords. A plurality of attribute groups is generated, where each of the attribute groups is statistically orthogonal and includes at least one of the plurality of attributes, based on occurrence data extracted from the plurality of EHRs. For a patient, a plurality of attribute scores is determined for the plurality of attributes based on occurrence data extracted from one or more EHRs corresponding to the patient. A plurality of attribute group scores is determined, for the patient, for the plurality of attribute groups, based on the plurality of attribute scores. A clinical concept score is generated for the patient based on the plurality of attribute group scores.