MetaMap

MetaMap is a highly configurable software tool developed by the National Library of Medicine (NLM) to map biomedical text to the Unified Medical Language System (UMLS) Metathesaurus or, equivalently, to discover Metathesaurus concepts referred to in text.

Key Capabilities

• Semantic Mapping: Uses a knowledge-intensive approach based on computational linguistics and the UMLS to accurately map text strings to distinct medical concepts (CUIs).
• Extensive Vocabulary Support: Leverages the vast UMLS Metathesaurus, integrating over 200 different biomedical vocabularies including SNOMED CT, RxNorm, ICD-10, and LOINC.
• Word Sense Disambiguation (WSD): Includes built-in mechanisms to resolve ambiguous terms based on context (e.g., “cold” as a temperature vs. “cold” as a viral infection).

Usage in Healthcare

MetaMap has been a foundational tool for decades in clinical natural language processing. It is widely used to index massive corpuses of medical literature (like MEDLINE), abstract data from electronic health records, and build sophisticated clinical decision support systems that require standardized semantic understanding of unstructured text.