Semantic Tagging of Medical Narratives with Top Level Concepts from SNOMED CT Healthcare Data Standard

Abstract

Medical narratives written by clinicians constitute critical information in healthcare domain and are required to be correct with respect to contextual meaning. SNOMED CT (Systematized Nomenclature of Medicine - Clinical Terms) is a standardized reference terminology that consists of 390023 SNOMED CT concepts with SNOMED CT codes. This paper describes the extraction of SNOMED CT concepts from free text discharge summary reports. For the evaluation of the medical concepts, we used 300 discharge summaries corpus provided by University of Pittsburgh Medical Centre, and compared it with the SNOMED CT concept file which is a preprocessed and cleaned file listing SNOMED CT concepts. In this paper we present the ongoing research on SNOMED CT concept extraction from discharge summaries using natural language processing and introducing SNOMED CT core concepts as a single gazetteer list for concept extraction. Out of 390023 concepts, 21563 concepts were found in the test set of discharge summaries from the SNOMED CT core concepts gazetteer list. A modified approach extracted the 23 top level concept tags which will be useful for linguist analysis research.