Mapping clinical notes to medical terminology at point of care

Abstract

Clinicians write the reports in natural language which contains a large amount of informal medical term. Automating conversion of text into clinical terminologies allows reliable retrieval and analysis of the clinical notes. We have created an algorithm that maps medical expressions in clinical notes into a medical terminology. This algorithm indexes medical terms into an augmented lexicon. It performs lexical searches in text and finds the longest possible matches in the target terminology, SNOMED CT. The mapping system was run on a collection of 470, 000 clinical notes from an Intensive Care Service (ICS). The evaluation on a small part of the corpus shows the precision is 70.4%.