Classification and Coding of Adverse Drug Reactions

We will develop new software tools for recording and classifying free-text descriptions of adversemedical therapies. A major challenge is finding ways to accommodate the conflicting requirements ofcoverage and uniformity of coding. A three-step model is proposed: extraction of linguistic terms, cintermediate language vocabulary, and selection of codes from a codelist. The extraction step applietechniques to assist the medical coder in the selection of relevant terms. Term subsets are classifilanguage based upon the Unified Medical Language System (UMLS) Metathesaurus of the National LibraryCustomizable coding modules can then be used to map intermediate language terms into output codes. Iexperts in drug development and thesaurus construction, Phase I will evaluate the utility of this moupon the divergent goals of universality and uniformity. Phase II will produce a full software protointegration with new document-retrieval-based approaches for increased automation.