International Business Machines Corporation

Joern Jaskolowski

Swapnil Chhabra

Peter Bak

Avi Yaeli

Adam Perer

Piyush Madan

Jeffrey B Beers

Terry Verne Taerum

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.

Generation of concept scores based on analysis of clinical data

A pathway for each entity in a cohort may be extracted from raw data comprising a plurality of events. A common graph structure may be created based the extracted pathways. For each cohort, a relative signature trait may be computed for each edge based on a number of appearances of the edge in the extracted pathways that are associated with the cohort. A relationship expression may be obtained. The relationship expression may be with respect to at least two cohorts for which relative signature traits were computed. The common graph structure may be processed based on the relationship expression to determine an output label for each edge. A visualization of the common graph structure may be displayed.

Relative signature traits of cohorts

Growing community of inventors

Copenhagen, Denmark

Joern Jaskolowski