Your SlideShare is downloading. ×
The Unified Medical Language System What is it and how to use it?
Upcoming SlideShare
Loading in...5
×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

×

Saving this for later?

Get the SlideShare app to save on your phone or tablet. Read anywhere, anytime - even offline.

Text the download link to your phone

Standard text messaging rates apply

The Unified Medical Language System What is it and how to use it?

468
views

Published on

Published in: Health & Medicine, Technology

0 Comments
1 Like
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total Views
468
On Slideshare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
Downloads
16
Comments
0
Likes
1
Embeds 0
No embeds

Report content
Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
No notes for slide

Transcript

  • 1. Korea Advanced Institute of Science and Technology December 4, 2007 The Unified Medical Language System What is it and how to use it? Olivier Bodenreider, MD, PhD Lister Hill National Center for Biomedical Communications Bethesda, Maryland - USA
  • 2. Outline Part I: What is the UMLS? Introduction Overview through an example The three UMLS Knowledge Sources UMLS Metathesaurus UMLS Semantic Network SPECIALIST Lexicon and lexical tools Part II: How to use the UMLS? A UMLS-based algorithm 2
  • 3. Part I What is the UMLS? (1) Introduction
  • 4. What does UMLS stand for? Unified Medical Language System UMLS® Unified Medical Language System® UMLS Metathesaurus® 4
  • 5. Motivation Started in 1986 National Library of Medicine “Long-term R&D project” (Integrated Academic Complementary to IAIMS Information Management Systems) «[…] the UMLS project is an effort to overcome two significant barriers to effective retrieval of machine-readable 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.» 5
  • 6. The UMLS in practice Database Series of relational files Interfaces Web interface: Knowledge Source Server (UMLSKS) Application programming interfaces (Java and XML-based) Applications lvg (lexical programs) MetamorphoSys (installation and customization) RRF browser (browsing subsets) The UMLS is not an end-user application 6
  • 7. Part I What is the UMLS? (2) Overview through an example
  • 8. Addison’s disease Addison's disease is a rare endocrine disorder Addison's disease occurs when the adrenal glands do not produce enough of the hormone cortisol For this reason, the disease is sometimes called chronic adrenal insufficiency, or hypocortisolism 8
  • 9. Adrenal insufficiency Clinical variants Primary / Secondary Primary: lesion of the ACTH adrenal glands themselves Secondary: inadequate secretion of ACTH by the pituitary gland Acute / Chronic Isolated / Polyendocrine deficiency syndrome 9
  • 10. Addison’s disease: Symptoms Fatigue Weakness Low blood pressure Pigmentation of the skin (exposed and non- exposed parts of the body) … 10
  • 11. AD in medical vocabularies Synonyms: different terms Addisonian syndrome eponym Bronzed disease Melasma addisonii symptoms Asthenia pigmentosa Primary adrenal deficiency Primary adrenal insufficiency clinical Primary adrenocortical insufficiency variants Chronic adrenocortical insufficiency Contexts: different hierarchies 11
  • 12. Organize terms Synonymous terms clustered into a concept Preferred term Unique identifier (CUI) Addison Disease MeSH D000224 Primary hypoadrenalism MedDRA 10036696 Primary adrenocortical insufficiency ICD-10 E27.1 Addison's disease (disorder) SNOMED CT 363732003 C0001403 Addison's disease 12
  • 13. MeSH Disease Endocrine system diseases Adrenal gland diseases Adrenal Insufficiency Addison Disease
  • 14. MedDRA Endocrine disorders Adrenal gland disorders Adrenal cortical hypofunctions Addison’s Disease
  • 15. SNOMED International Disease/Diagnoses Diseases of the endocrine system Diseases of the adrenal glands Addison’s Disease
  • 16. SNOMED CT (native) Disorder of endocrine system Disorder of adrenal gland Hypoadrenalism Disorder of Adrenal hypofunction adrenal cortex Adrenal cortical hypofunction Addison’s Disease
  • 17. SNOMED CT (UMLS view) Disorder of endocrine system Disorder of adrenal gland Adrenal gland Disorder of hypofunction adrenal cortex Adrenal cortical hypofunction Addison’s Disease
  • 18. NCI Thesaurus Endocrine Disorder Non-neoplastic endocrine disorder Adrenal gland disorder Non-neoplastic adrenal gland disorder Adrenal gland insufficiency Adrenal cortical insufficiency Addison’s Disease
  • 19. ICD-10 Endocrine, nutritional and metabolic diseases Disorders of other endocrine glands Other disorders of adrenal gland Primary adrenocortical insufficiency
  • 20. Organize concepts Inter-concept A C B relationships: hierarchies B D E H E F H D E from the source vocabularies G H Redundancy: multiple paths One graph instead of A multiple trees B C (multiple inheritance) D E F G H 20
  • 21. organize concepts Disease Endocrine system diseases Adrenal gland diseases Adrenal gland Adrenal cortex hypofunction diseases SNOMED CT SNOMED Intl Adrenal cortical hypofunction MeSH MedDRA Addison’s Disease
  • 22. UMLS view Disease Endocrine / nutritional / metabolic disorder Endocrine system diseases Non-neoplastic Disorders of other endocrine disorder endocrine glands Adrenal gland diseases Non-neoplastic adrenal gland disorder Adrenal gland Adrenal cortex Other disorders of hypofunction diseases adrenal gland Adrenal cortical hypofunction Addison’s Disease
  • 23. UMLS view Disease Endocrine / nutritional / metabolic disorder Immune system diseases Endocrine system diseases Non-neoplastic Disorders of other endocrine disorder endocrine glands Adrenal gland diseases Non-neoplastic adrenal gland disorder Autoimmune diseases Adrenal gland Adrenal cortex Other disorders of hypofunction diseases adrenal gland Adrenal cortical hypofunction Addison’s Disease Tuberculous Addison’s disease Addison's disease due to autoimmunity
  • 24. Relate to other concepts Additional hierarchical relationships link to other trees make relationships explicit Non-hierarchical relationships Co-occurring concepts Mapping relationships 24
  • 25. Categorize concepts High-level categories Disease or Syndrome (semantic types) Assigned by the Diseases Metathesaurus editors Independently of the Endocrine Diseases hierarchies in which these concepts are located Adrenal Gland Diseases Adrenal Gland Hypofunction Addison’s Disease 25
  • 26. How do they do that? Lexical knowledge Semantic pre-processing UMLS editors 26
  • 27. Lexical knowledge Adrenal gland diseases Adrenal disorder Disorder of adrenal gland Diseases of the adrenal glands C0001621 27
  • 28. Semantic pre-processing Metadata in the source vocabularies Tentative categorization Positive (or negative) evidence for tentative synonymy relations based on lexical features 28
  • 29. Additional knowledge: UMLS editors Adrenal gland diseases Adrenal gland Adrenal cortex Other disorders of hypofunction diseases adrenal gland Adrenal cortical hypofunction Addison’s Disease 29
  • 30. UMLS Summary Synonymous terms clustered into concepts Unique identifier Finer granularity Broader scope Additional hierarchical relationships Semantic categorization 30
  • 31. Part I What is the UMLS? (3) UMLS Metathesaurus
  • 32. Unified Medical Language System SPECIALIST Lexicon 360,000 lexical items Lexical Part of speech and variant information resources Metathesaurus 6M names from over 100 terminologies Terminological 1.5M concepts resources 8M relations Semantic Network Ontological 135 high-level categories resources 7000 relations among them 32
  • 33. Metathesaurus Basic organization Concepts Synonymous terms are clustered into a concept Properties are attached to concepts, e.g., Unique identifier Definition Relations Concepts are related to other concepts Properties are attached to relations, e.g., Type of relationship Source 33
  • 34. Source Vocabularies (2007AC) 141 source vocabularies 17 languages Broad coverage of biomedicine 6.1M names 1.5M concepts 8M relations Common presentation 34
  • 35. Biomedical terminologies General vocabularies anatomy (UWDA, Neuronames) drugs (RxNorm, First DataBank, Micromedex) medical devices (UMD, SPN) Several perspectives clinical terms (SNOMED CT) information sciences (MeSH, CRISP) administrative terminologies (ICD-9-CM, CPT-4) data exchange terminologies (HL7, LOINC) 35
  • 36. Biomedical terminologies (cont’d) Specialized vocabularies nursing (NIC, NOC, NANDA, Omaha, PCDS) dentistry (CDT) oncology (PDQ) psychiatry (DSM, APA) adverse reactions (COSTART, WHO ART) primary care (ICPC) Terminology of knowledge bases (AI/Rheum, DXplain, QMR) The UMLS serves as a vehicle for the regulatory standards (HIPAA, CHI) 36
  • 37. Integrating subdomains Clinical Clinical repositories repositories Genetic Genetic knowledge bases knowledge bases Other Other SNOMED CT subdomains subdomains OMIM … MeSH Biomedical Biomedical UMLS literature literature NCBI Taxonomy Model GO Model organisms FMA organisms Genome Genome Anatomy Anatomy annotations annotations 37
  • 38. Integrating subdomains Clinical Clinical repositories repositories Genetic Genetic knowledge bases knowledge bases Other Other subdomains subdomains Biomedical Biomedical literature literature Model Model organisms organisms Genome Genome Anatomy Anatomy annotations annotations 38
  • 39. Trans-namespace integration Addison's disease Clinical Clinical (363732003) repositories repositories Genetic Genetic knowledge bases knowledge bases Other Other SNOMED CT subdomains subdomains OMIM … MeSH Biomedical Biomedical UMLS literature literature NCBI C0001403 Taxonomy Addison Disease (D000224) Model GO Model organisms FMA organisms Genome Genome Anatomy Anatomy annotations annotations 39
  • 40. Addison’s Disease: Concept ADRENAL INSUFFICIENCY (ADDISON'S DISEASE) ADRENOCORTICAL INSUFFICIENCY, PRIMARY FAILURE Disease or Syndrome Hypoadrenalisms, Primary Melasma addisonii Primary adrenal deficiency Asthenia pigmentosa Bronzed disease Insufficiency, adrenal primary Primary adrenocortical insufficiency Addison's, disease Maladie d'Addison - French Addison’s Disease Addison-Krankheit - German Morbo di Addison - Italian Doença de Addison - Portuguese АДДИСОНОВА БОЛЕЗНЬ - Russian アジソン病 - Japanese SNOMED CT SNOMED Intl An adrenal disease characterized by the progressive destruction of the adrenal cortex, resulting in insufficient production of MeSH aldosterone and hydrocortisone. Clinical symptoms include MedDRA C0001403 anorexia; nausea; weight loss; muscle ewakness; and hyperpigmentation of the skin due to increase in circulating … levels of ACTH precursor hormone which stimulates melanocytes. 40
  • 41. Semantic Types Anatomical Structure Fully Formed Anatomical Embryonic Structure Structure Disease or Syndrome Body Part, Organ or Organ Component Pharmacologic Population Semantic Substance Group Network Metathesaurus Medias- Saccular 5 tinum Viscus Angina 49 Pectoris Esophagus 16 Cardiotonic Heart 237 Agents Left Phrenic Nerve Tissue Heart Fetal 38 Donors 13 Valves 22 Heart Concepts
  • 42. Part II How to use the UMLS? A UMLS-based algorithm
  • 43. Indexing Initiative [Aronson & al., AMIA, 2000] For noun phrases extracted from medical texts, map to UMLS concepts Then, select from the MeSH vocabulary the concepts that are the most closely related to the original concepts MeSH descriptor Medical text Noun phrase UMLS 43
  • 44. Restrict to MeSH [Bodenreider & al., AMIA, 1998] Based on the principle of semantic locality Use different components of the UMLS 4 techniques of increasing aggressiveness Use Synonymy MRCONSO Use Associated expressions (ATXs) MRATX + MRREL Explore the Ancestors MRREL + SN Explore the Other related concepts MRREL + SN 44
  • 45. Restrict to MeSH Synonymy Term mapped to Source concept For this concept, is there a synonym term that comes from MeSH? (MRCONSO) 45
  • 46. Restrict to MeSH Assoc. expressions If not, Is there an associated expression (ATX) that describes this concept using a combination of MeSH descriptors? (MRATX/MRMAP + MRREL) AND Endoscopic removal of intraluminal foreign body MH/SH from oesophagus without incision Esophagus surgery Foreign Bodies 46
  • 47. Restrict to MeSH Ancestors If not, let us build the graph of the ancestors of this concept using parents and broader concepts (MRREL) all the way to the top excluding ancestors whose semantic types are not compatible with those of the source concept (MRSTY) From the graph, select the concepts that come from MeSH (MRCONSO) Remove those that are ancestors of another concept coming from MeSH 47
  • 48. Restrict to MeSH Other related concepts If not, explore the other related concepts (MRREL) whose semantic types are compatible with those of the source concept (MRSTY) From those, select the concepts that come from MeSH (MRCONSO) 48
  • 49. Restrict to MeSH Example Vein of neck, NOS There is a MeSH term in the synonyms of SC SC is described by a combination of MeSH terms (ATX) The ancestors of SC contain MeSH terms MeSH terms from non-hierarchically related concepts Vein + Neck 49
  • 50. Restrict to MeSH Example Head and neck, NOS Body part, NOS Blood Vessels Vascular structure Head Veins Neck Systemic veins Vein of head and neck, NOS Vein of neck, NOS 50
  • 51. Restrict to MeSH Quantitative results 86% of UMLS concepts mapped to MeSH (2007) Other related concepts Synonymy 12% 23% 11% Graph of Built-in ancestors 54% mappings 51
  • 52. Restrict to MeSH Qualitative results Qualitative evaluation 1,036 concepts extracted from 200 MEDLINE citations manual review of every mapping or failure 61% Relevant Subtotal Gastrectomy Gastrectomy Encephalopathy, NOS Brain Diseases 28% More or less relevant Vitamin A measurement Laboratory Procedure Swelling, NOS Symptoms 11% Non relevant 52
  • 53. Medical Ontology Research Contact: olivier@nlm.nih.gov Web: mor.nlm.nih.gov Olivier Bodenreider Lister Hill National Center for Biomedical Communications Bethesda, Maryland - USA
  • 54. Bibliography
  • 55. References: UMLS home page UMLS home page http:// www.nlm.nih.gov/research/umls/ UMLS documentation Formerly know as the “Green Book” Now online documentation http://www.nlm.nih.gov/research/umls/UMLSDOC.HTML 55
  • 56. References Short presentation Bodenreider, O. (2004) The Unified Medical Language System (UMLS): integrating biomedical terminology. Nucleic Acids Res, 32(Database issue), D267-70. UMLS as a research project Lindberg, D. A., Humphreys, B. L., & McCray, A. T. (1993). The Unified Medical Language System. Methods Inf Med, 32(4), 281-91. Humphreys, B. L., Lindberg, D. A., Schoolman, H. M., & Barnett, G. O. (1998). The Unified Medical Language System: an informatics research collaboration. J Am Med Inform Assoc, 5(1), 1-11. 56
  • 57. References Technical papers McCray, A. T., & Nelson, S. J. (1995). The representation of meaning in the UMLS. Methods Inf Med, 34(1-2), 193-201. Comprehensive bibliography 1986-96 http://www.nlm.nih.gov/pubs/cbm/umlscbm.html 57
  • 58. Documentation and Support
  • 59. UMLS documentation and support UMLS homepage links to various UMLS resources http://www.nlm.nih.gov/research/umls/ UMLSKS homepage links to the User’s and Developer’s guides http://umlsks.nlm.nih.gov/ UMLS mailing list UMLSUSERS-L@LIST.NIH.GOV Email address for support custserv@nlm.nih.gov 59