Identification of adverse drug events in chinese clinical narrative text

Abstract

Drug is an effective measure of alleviating pain and treating diseases. Whereas medication-related harms due to both adverse drug effects and drug errors have become the leading iatrogenic injury. However, such medication-related harms often remain unrecognized and unreported. The purpose of this study is to automatically identify adverse drug events (ADEs) in routine clinical documents. Firstly, ADE related Chinese lexical resource was collected and maintained. Then, a natural language processing (NLP) application which could automatically extract ADE symptom from drug manuals was developed and applied for building an ADE knowledge base for 3,733 drugs. Finally, based on these resources, an ADE detection algorithm was proposed to identify ADEs in the clinical free-text. Results revealed that the precision of the ADE detection algorithm was 80.8 %.