UNIFIED MEDICAL LANGUAGE SYSTEMS UMLS The Unified

UNIFIED MEDICAL LANGUAGE SYSTEMS (UMLS) § The Unified Medical Language System (UMLS) is a long term research and development project that started in 1986 by the U. S. National Library of Medicine (NLM) § The UMLS is not a gigantic and comprehensive medical vocabulary § The UMLS is a relational database connecting “by concept” over 60 vocabularies, thesauri, medical problem lists etc.

Purpose § To aid the development of systems that help health professionals and researchers retrieve and integrate electronic biomedical information form a variety of sources, such as: q q q Computer-based Patient Records Bibliographic databases Factual (full text) databases Administrative health data Expert systems

UMLS Uses § Electronic patient records § Natural language processing § Information retrieval § Thesaurus construction § Automated indexing

UMLS COMPONENTS Metathesaurus Semantic Network Lexicon

UMLS Source “Vocabularies” § Widely varying purposes, structures, properties that do not add up to single ontology or view of the world: Ø Ø Ø Thesauri, e. g. , Me. SH (Medical Subject Headings) Statistical Classifications, e. g. , ICD Billing Codes, e. g. , CPT Clinical coding systems, e. g. , SNOMED Lists of controlled terms, e. g. , HL 7 valid values

How to combine them? Not reallly. . .

METATHESAURUS Contains more than 60 vocabularies and classifications. u 776. 940 concepts u 2, 1 millions of concept names u 11 millions of relationships between concepts u

Metathesaurus - Relations u u Preserves the structure of the original sources. Add news relationships between the concepts

METATHESAURUS Organization Synonymous terms CUI Preferred term

Metathesaurus structure CONCEPTs TERMs STRING CUI’s LUI’s STRING Is organized by concept or meaning; its purpose is to link alternative names and views of the same concept together and to identify useful relationships between different concepts. . STRING

Metathesaurus structure example CONCEPTS (CUIs) TERMS (LUIs) STRING (SUIs) C 0004238 L 0004238 S 0016668 (preferred) Atrial Fibrillations Auricular Fibrillations (preferred) Atrial Fibrillation S 0016669 Atrial Fibrillations L 0004327 S 0016899 (synonym) Auricular Fibrillation(preferred) Auricular Fibrillation S 0016900 (plural variant) Auricular Fibrillations

Semantic Network § All information about specific concepts is found in the Metathesaurus § The Network provides information about the basic semantic types that are assigned to these concepts, and it defines the relationships that may hold between the semantic types § It defines these types, both with textual descriptions and by means of the information inherent in its hierarchies

Semantic Network Example “BIOLOGIC FUNTION” HIERARCHY LINK “ISA” BIOLOGIC FUNCTION LINK PHYSIOLOGIC FUNCTION ORGANISM FUNCTION MENTAL PROCESS ORGAN OR TISSUE FUNCTION CELL FUNCTION “ISA” PATHOLOGIC FUNCTION MOLECULAR FUNCTION GENETIC FUNCTION DISEASE OR SYNDROME MENTAL OR BEHAVIORAL DYSFUNCTION CELL OR MOLECULAR DYSFUNCTION NEOPLASTIC PROCESS EXPERIMENTAL MODEL OF DISEASE

Relationship between Metathesaurus and Semantic Network

LEXICON § It provide the lexical information needed for the SPECIALIST Natural Language Processing System § It is a general English lexicon that includes many biomedical terms (commonly occurring English words and biomedical vocabulary) § The lexicon entry for each word (or term) records the § syntactic § morphological § orthographic information needed by the SPECIALIST natural language processing system

UNIFIED MEDICAL LANGUAGE SYSTEM - Summary u u Standard source of concepts and synonyms. Multilingual Broad extension. Allow integration between applications

REFERENCES u http: //www. nlm. nih. gov/pubs/factsheets/umls. html u http: //www. nlm. nih. gov/research/umls/META 2. HTML u http: //www. nlm. nih. gov/research/umls/META 3. HTML u http: //www. nlm. nih. gov/research/umls/META 4. HTML u http: //www. nlm. nih. gov/pubs/cbm/umlscbm. html#6