Unified Medical Language System UMLS NLM Presentation Theater

Unified Medical Language System® (UMLS®) NLM Presentation Theater MLA 2006 Rachel Kleinsorge Jan Willis

What does UMLS stand for? u Unified u Medical u Language u System UMLS® Unified Medical Language System®

The UMLS consists of Metathesaurus 1 million+ biomedical concepts from over 130 sources Semantic Network 135 broad categories and 54 relationships between categories SPECIALIST Lexicon & Tools lexical information and programs for language processing 3 Knowledge Sources used separately or together

UMLS 3 Knowledge Sources u Metathesaurus l Over 100 source vocabularies l Over 1 million concepts l Inter-concept relationships u Semantic Network l 135 Semantic types (broad categories) l 54 Semantic relations (between categories) u Lexical resources l SPECIALIST Lexicon l Lexical tools (programs and databases)

History of the UMLS [Lindberg & al. , Methods, 1993] [Humphreys & al. , JAMIA, 1998] Started at National Library of Medicine, 1986 u “Long-term R&D project” u «[…] the UMLS project is an effort to overcome two significant barriers to effective retrieval of machinereadable information. • The first is the variety of ways the same concepts are expressed in different machine-readable sources and by different people. • The second is the distribution of useful information among many disparate databases and systems. »

UMLS Objectives l Intellectual “middleware” l A set of multi-purpose tools for system developers l Knowledge Sources used to overcome: l l disparities in language format Ex: atrial fibrillation, auricular fibrillation, af disparities in granularity and perspective Ex: Contusions, hematoma, bruise Ex: Instruct patient to promptly report nosebleeds and excessive bruising (NIC), Epistaxis (Me. SH)

UMLS in Practice u Databases: 3 separate sets of relational files u Tools: l l l Metamorpho. Sys (installation and customization) Web interface Knowledge Source Server (UMLSKS) Application programming interfaces lvg (lexical programs) RRF Subset Browser u Distributed on DVD; downloaded from UMLSKS The UMLS is not an end-user application

UMLS Uses u Information retrieval u Thesaurus construction u Natural language processing u Automated indexing u Electronic health records (EHR) u Distribution mechanism for HIPAA, CHI, PHIN regulatory standards

License Agreements u Semantic Network, SPECIALIST Lexicon & Lexical Tools l u terms and conditions of use online Metathesaurus l l license agreement process some restrictions n n 2. No charges, usage fees or royalties will be paid to NLM. 5. Within 30 days of the end of any calendar year … provide NLM with a brief report 11. c. required to include … identifiers from … the original source vocabularies 12. For material … from some sources additional restrictions … may apply.

What is the UMLS? Overview through an example

Metathesaurus: clusters terms by meaning u Synonymous terms clustered into a concept u Preferred term is chosen u Unique identifier (CUI) is assigned Addison’s disease Addison’s Disease Addison Disease Bronzed disease Deficiency; corticorenal, primary Primary Adrenal Insufficiency Primary hypoadreanlism syndrome, Addison C 0001403 Metathesaurus PN SNOMED CT PT 363732003 Medline. Plus PT T 1233 Me. SH PT D 000224 SNOMED Intl 1998 SY DB-70620 ICPC 2 -ICD 10 PT MTHU 021575 Thesaurus Me. SH EN D 000224 Med. DRA LT 10036696 Addison’s disease

Cluster of synonymous terms Term L 0001621 Term L 0041793 Concept C 0001621 Term L 0161347 Term L 0181041 Term L 0368399 Term L 1279026 Term L 0162317 S 0011232 Adrenal Gland Diseases S 0011231 Adrenal Gland Disease S 0000441 Disease of adrenal gland S 0481705 Disease of adrenal gland, S 0220090 Disease, adrenal gland S 0044801 Gland Disease, Adrenal NOS […] S 0860744 Disorder of adrenal gland, unspecified S 0217833 Unspecified disorder of adrenal glands S 0225481 ADRENAL DISORDER S 0627685 DISORDER ADRENAL (NOS) […] S 0632950 Disorder of adrenal gland S 0354509 Adrenal Gland Disorders […] S 0586222 Adrenal disease S 0466921 ADRENAL DISEASE, […] NOS S 1520972 Nebennierenkrankheiten GER S 0226798 SURRENALE, FRE MALADIES […]

Semantic Network u 135 Semantic Types l l Broad subject categories (Clinical Drug, Virus) Ex: Addison’s Disease n u 54 Semantic Relationships l l u Semantic Type: Disease or Syndrome Links between categories (isa, causes, treats) Ex: Virus causes Disease or Syndrome Together l l Form the structure of the semantic network Broadly categorize the biomedical domain

A portion of the Semantic Network

SPECIALIST Lexicon u General English lexicon of common words, biomedical terms u Used by SPECIALIST Natural Language Processing System u Lexical records contain encoded information: l l l u u syntactic (how words are put together), morphological (inflection, derivation, and compounding), and orthographic (spelling) information Lexical tools process terms Used in Metathesaurus production Adrenal gland diseases Adrenal disorder Disorder of adrenal gland Diseases of the adrenal glands C 0001621

SPECIALIST Lexicon {base=disease entry=E 0023270 cat=noun variants=reg variants=uncount compl=pphr(of, np|bone|) compl=pphr(of, np|breast|) compl=pphr(of, np|liver|) compl=pphr(of, np|ovary|) }

Summary Metathesaurus: u clusters terms into concepts – assigns unique identifier Semantic Network: u defines relationships between concepts, organizes concepts into categories Lexicon and Lexical Tools: u process terms for entry into the Metathesaurus