Drug name recognition and classification in biomedical texts: A case study outlining approaches underpinning automated systems

This article presents a system for drug name recognition and classification in biomedical texts. The system combines information obtained by the Unified Medical Language System (UMLS) MetaMap Transfer (MMTx) program and nomenclature rules recommended by the World Health Organization (WHO) International Nonproprietary Names (INNs) Program to identify and classify pharmaceutical substances. Moreover, the system is able to detect possible candidates for drug names that have not been detected by MMTx program by applying these rules, achieving, in this way, a broader coverage. This work is the first step in a method for automatic detection of drug interactions from biomedical texts, a specific type of adverse drug event of special interest in patient safety.