Datasets › UMLS

UMLS (Unified Medical Language System)

Introduced by Bridget McInnes et al. in UMLS::Similarity: Measuring the Relatedness and Similarity of Biomedical Concepts1 Jun 2013 archive 2025-07-28

The Unified Medical Language System (UMLS) is a comprehensive resource that integrates and disseminates essential terminology, classification standards, and coding systems. Its purpose is to foster the creation of more effective and interoperable biomedical information systems and services, including electronic health records. Here are the key aspects of the UMLS:

  1. Integration of Vocabularies: The UMLS brings together various health and biomedical vocabularies and standards. It acts as a bridge, enabling interoperability between different computer systems by harmonizing terminology.

  2. Components:

    • Metathesaurus: This component contains terms and codes from multiple vocabularies, including CPT, ICD-10-CM, LOINC, MeSH, RxNorm, and SNOMED CT. It provides hierarchies, definitions, relationships, and other attributes.
    • Semantic Network: The Semantic Network defines broad categories (semantic types) and their relationships (semantic relations).
    • SPECIALIST Lexicon and Lexical Tools: These tools include a large syntactic lexicon for biomedical and general English. They assist in normalizing strings, generating lexical variants, and creating indexes.
  3. Use Cases:

    • Clinical Practice: Link terms and codes across healthcare entities (doctors, pharmacies, insurance companies).
    • Patient Care Coordination: Facilitate communication among hospital departments.
    • Text Processing: Extract concepts, relationships, or knowledge from medical texts.
    • Terminology Mapping: Map between different terminologies.
    • Local Terminology Development: Create and maintain local terminologies.
    • Research: Investigate terminologies or ontologies.
  4. Accessing the UMLS:

    • Web Browsers: You can search and explore UMLS data using UTS applications like the Metathesaurus Browser (retrieve concept information) and the Semantic Network Browser (view semantic types and relations).
    • Local Installation: Download UMLS files and use the MetamorphoSys tool to customize the UMLS for your specific needs. Load the customized data into your own database system or browse it using the MetamorphoSys RRF browser.

Source: Conversation with Bing, 3/18/2024 (1) Unified Medical Language System (UMLS) - National Library of Medicine. https://www.nlm.nih.gov/research/umls/index.html. (2) UMLS Metathesaurus Browser. https://uts.nlm.nih.gov/uts/umls/home. (3) GitHub - dongwookim-ml/kg-data: knowledge-graph datasets. https://github.com/dongwookim-ml/kg-data. (4) UMLS Dataset | Papers With Code. https://paperswithcode.com/dataset/umls.

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Link Prediction UMLS LP-BERT Hits@10 1.000 Multi-task Pre-training Language Model for Semantic... 763337092/LP-BERT 10 Compare

Papers archive 2025-07-28

10 shown of 10 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 19. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • UMLS

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections