Graph-based signal integration for high-throughput phenotyping

By Jorge R. Herskovic, Devika Subramanian, Trevor A. Cohen, Pamela A. Bozzo-Silva, Charles F. Bearden, Elmer Victor Bernstam. 2012

7 citations recorded by the source corpus.

Electronic Health Records aggregated in Clinical Data Warehouses (CDWs) promise to revolutionize Comparative Effectiveness Research and suggest new avenues of research. However, the effectiveness of CDWs is diminished by the lack of properly labeled data. We present a novel approach that integrates knowledge from the CDW, the biomedical literature, and the Unified Medical Language System (UMLS) to perform high-throughput phenotyping. In this paper, we automatically construct a graphical knowledge model and then use it to phenotype breast cancer patients. We compare the performance of this approach to using MetaMap when labeling records. MetaMap's overall accuracy at identifying breast cancer patients was 51.1% (n=428); recall=85.4%, precision=26.2%, and F1=40.1%. Our unsupervised graph-based high-throughput phenotyping had accuracy of 84.1%; recall=46.3%, precision=61.2%, and F1=52.8%. We conclude that our approach is a promising alternative for unsupervised high-throughput phenotyping.

Subfields: Artificial Intelligence, Health Information Management, Molecular Biology

Citations in the corpus

• Natural Language Processing for EHR-Based Computational Phenotyping (2018, neutral): “[105] NA MetaMap, SemRep Narrative, biomedical literature UMLS concept and UMLS relationship, semantic predication from biomedical literature Lehman et al.”