![Page 1: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/1.jpg)
A.I. in health informatics lecture 5 standards &
ontolologies kevin small & byron wallace
*Slides reuse material from Kleinsorge, Willis, and Emrick; 2007.
![Page 2: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/2.jpg)
today
• standards – facilitates interoperability if well designed – stifles creativity if poorly designed
• ontologies – standardization of knowledge
• UMLS
![Page 3: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/3.jpg)
standards
• set of rules and definitions regarding completion of a process
• permits disassociated entities to cooperate
• important for medicine
![Page 4: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/4.jpg)
standards
• required when excessive diversity impedes effectiveness
• standards can impede innovation
• effective and timely standards can also focus innovation
![Page 5: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/5.jpg)
health care standards
• portability of patient records – accuracy – security, privacy
• uniformity in billing
• standardization of clinical information
• electronic communication standards
![Page 6: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/6.jpg)
origination of standards
• ad hoc – mutual agreement of participating entities
• de facto – incidentally generated by dominant entity
• government mandate – HCFA UB92 insurance-claim form
• consensus – open process by interested parties
![Page 7: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/7.jpg)
developing standards
• identification stage – need and technological maturity
• conceptualization stage – purpose, scope, format, etc.
• discussion stage – identification of critical issues, timelines
• early implementation • conformance and certification
![Page 8: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/8.jpg)
the fruit of standards
![Page 9: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/9.jpg)
…and
• ANSI, CEN, ISO, ASTM • Health Care Informatics Standards
Board (HISB) – electronic health care records – data exchange – health care codes and terminology – communication with devices and
instrumentation – Knowledge and model representation – privacy, confidentiality, security
• HIMSS, CPRI, IHE, NQF, WEDI
![Page 10: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/10.jpg)
why do we care?
• in many (most) ways, we (I) don’t
• standardized information is easier to reason with (less ambiguity) – ontologies
• research science should have a role in determining standards
![Page 11: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/11.jpg)
ontologies
“An ontology may take a variety of forms, but necessarily it will include a vocabulary of terms, and some specifica3on
of their meaning. This includes definiFons and an indicaFon of how concepts are inter-‐related which collecFvely impose a structure on the domain and constrain the possible interpretaFon of terms”
-‐Uschold et al., 1998
![Page 12: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/12.jpg)
ontologies
Burgun et al., 2001
![Page 13: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/13.jpg)
UMLS semantic network
Kleonsorge et al., 2007
Organism process of
Embryonic Structure
Anatomical Abnormality
Congenital Abnormality
Acquired Abnormality
Fully Formed Anatomical Structure
Anatomical Structure
part of
Organism Attribute
property of
Body Substance
contains,produces conceptual
part of
evaluation of
Body System conceptual part of
part of
Body Part, Organ or Organ Component
part of
Tissue
part of
Cell
part of
Cell Component
Gene or Genome
Body Space or Junction
adjacent to
location of
location of
evaluation of Finding
Laboratory or Test Result
Sign or Symptom
Biologic Function
Physiologic Function
Pathologic Function
Body Location or Region
conceptual part of
conceptual part of
Injury or Poisoning
disrupts
disrupts
co-occurs with
![Page 14: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/14.jpg)
ontologies
• frames knowledge within a domain – structured representation – universal encoding
• reduces ambiguity
gene “the coding region of DNA”
“DNA fragment that can be transcribed and translated in to a protein”
“DNA region of biological interest with a name and that carries a geneFc trait or phenotype”
![Page 15: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/15.jpg)
ontologies
• scientific knowledge desires precision – decomposes into entities and relationships – logical reasoning
• allows storing information in databases – requires hand encoding or information
extraction from natural language – efficient storage of volumes of knowledge – human/machine interface
![Page 16: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/16.jpg)
ontological components
• concepts – entities within a domain
• relations – interactions between concepts
• instances – named entities
• axioms – constraints between (named) entities
conceptualizaFon
concrete
![Page 17: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/17.jpg)
concepts
• primitive concepts – globular protein hydrophobic core
• defined concepts – nucleus containing Eukaryotic
![Page 18: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/18.jpg)
relations
• taxonomic – specialization (“is a kind of”) – partitive (“is a component of”)
• associative – nominative – locative – causative – many others…
![Page 19: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/19.jpg)
ontology use
• domain-oriented – encodes domain knowledge
• task-oriented – encodes methods of completing tasks
• generic – open frameworks (e.g., Cyc)
![Page 20: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/20.jpg)
ontology benefits
• community reference
• schema specification
• ontology-based search
• input to NLP systems
![Page 21: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/21.jpg)
ontology life-cycle
Stevens et al., 2000
![Page 22: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/22.jpg)
knowledge representation
• natural-language vocabularies – hand-crafted tree inheritance structures
• frame-based systems – similar to object-based modeling
• description logics – primacy of relationship inference
![Page 23: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/23.jpg)
evaluating ontologies
• expressivity – can the domain be encoded?
• rigor – satisfiable and consistent
• semantics – captures intended meaning?
![Page 24: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/24.jpg)
Unified Medical Language System (UMLS®)
• more than just an ontology • ostensibly rich knowledge source for AI
research • http://umls.nlm.nih.gov
“The UMLS, or Unified Medical Language System, is a set of files and soRware that brings together many health and biomedical vocabularies and standards to enable interoperability between computer systems.
You can use the UMLS to enhance or develop applicaFons, such as electronic health records, classificaFon tools, dicFonaries and language translators.”
![Page 25: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/25.jpg)
NLM strategy
• designating U.S. standards – starting point and maintenance
• coordinate development of standards into interlocking set – broaden participation – promote usage
![Page 26: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/26.jpg)
standards
• CHI (clinical) LOINC • E.g., lab test results, problems, diagnoses, history, physical • Electronic exchange of clinical health informaFon in U.S. Government
systems
• HIPAA (administraFve) CPT • e.g., health insurance claims, billing, ordering • HIPAA AdministraFve SimplificaFon provisions • Designated DHHS naFonal standards for electronic healthcare
transacFons
• PHIN (public health) ICD-‐9-‐CM • e.g., disease surveillance, immunizaFon rates, environmental
monitoring • CDC designated standards for public health reporFng
![Page 27: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/27.jpg)
UMLS objectives
• intellectual middleware • for developers (not end users)
• knowledge sources to ameliorate: – disparities in language and format (e.g.,
atrial fibrillation, auricular fibrillation, af)
– disparities in granularity and perspective (e.g., contusions, hematoma, bruise)
![Page 28: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/28.jpg)
knowledge sources
Metathesaurus SemanFc Network SPECIALIST
Lexicon & Tools
135 broad categories and 54 relaFonships between categories
1 million+ biomedical concepts from over 100 sources
lexical informaFon and programs for language processing
3 knowledge sources (used separately or together)
![Page 29: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/29.jpg)
Metathesaurus
• very large • multipurpose • multi-lingual
• information regarding – biomedical/health concepts – names and associated codes – relationships amongst concepts
![Page 30: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/30.jpg)
source vocabularies
• derived from clinical, research, administrative, public health, etc.
• valid values – thesauri: MeSH, CRISP, NCI – statistical classifications: ICD-9-CM – billing codes: CPT, ABC codes – clinical coding: SNOMED CT
![Page 31: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/31.jpg)
source vocabularies
• intended to coordinate, not derive a single vocabulary – Diagnosis/signs and symptoms: ICD9CM,
ICD10, ICD10CM, ICD10AM, ICD-O, ICPC, ICF, SNOMED CT, Read Codes, MedDRA, MEDCIN, DSM
– Procedures: CPT, CDT, HCPCS, OCPS, SNOMED CT, ICD9CM, ICD10-PCS
– Nursing: NANDA, NIC, NOC, OMS, HHC – Diagnostic tests: LOINC, UltraSTAR – Drugs: VANDF, NDC, RXNORM, NDDF – Medical devices: SPN, UMD – Genomics: GO, HUGO, NCBI Taxonomy
![Page 32: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/32.jpg)
term clusters
• concepts contain synonymous terms • preferred term is indicated
– unique identifier (CUI) is assigned term source term type source ID Addison’s disease Metathesaurus PN Addison’s disease SNOMED CT PT 363732003 Addison’s Disease MedlinePlus PT T1233 Addison Disease MeSH PT D000224 Bronzed disease SNOMED Intl SY DB-‐70620 Primary Adrenal Insufficiency MeSH EN D000224 Primary hypoadrenalism MedDRA LT 10036696 syndrome, Addison
C0001403 Addison’s disease
![Page 33: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/33.jpg)
concept organization
Concept C0001621
[…] Term
L0001621
S0011231 Adrenal Gland Disease A0020266 MeSH A7568579 NCI Thesaurus
S0000441 Disease of adrenal gland A0001264 SNOMED 1982 A6917004 SNOMED Clinical Terms
S0481705 Diseases of Adrenal Gland A0014499 SNOMED 1982
S0220090 Diseases, adrenal gland A0049924 MeSH
Term L0181041
S0632950 Disorder of adrenal gland A0688820 Read Codes A4778687 SNOMED Clinical Terms
S0354509 Adrenal Gland Disorders A6996540 MedlinePlus A7576253 NCI Thesaurus A7561794 Psychological Index Terms
Term L1279026 S1520972 Nebennierenkrankheiten
A7500884
![Page 34: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/34.jpg)
concepts
• ~1.5M CUI – synonymous sets
• ~5.5M LUI – normalized names
• ~6.1M SUI – concept strings
• ~7.4M AUI – source-specific
L0018681
L0380797
C0018681
S0046855
A0066007 Headaches (MedDRA) A12003304 Headaches (OMIM)
S0046854
A0066000 Headache (MeSH) A0065992 Headache (ICD-10)
S0475647 A0540936 Cephalodynia (MeSH)
2007 numbers
![Page 35: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/35.jpg)
concept categories
• high-level – semantic types
• NLM derived – source independent
Disease or Syndrome
Endocrine Diseases
Adrenal Gland Diseases
Addison’s Disease
Diseases
Adrenal Gland Hypofunction
![Page 36: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/36.jpg)
concept relationships
• symbolic relationships – ~8M pairs of concepts
• co-occurrence relationships – ~6M pairs of concepts
• mapping relationships – ~150k mappings
![Page 37: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/37.jpg)
symbolic relationships
• Hierarchical – Parent / Child – Broader / Narrower than
• Derived from hierarchies – Siblings (children of parents)
• AssociaFve – Other
• Various flavors of near-‐synonymy – Similar – Source asserted synonymy
– Possible synonymy
PAR/CHD RB/RN
SIB
RO
RL
SY
RQ
![Page 38: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/38.jpg)
Anatomical Structure
Fully Formed Anatomical Structure
Embryonic Structure
Body Part, Organ or Organ Component Pharmacologic
Substance
Disease or Syndrome
Population Group
Semantic Types
Semantic Network
Heart
Concepts
Metathesaurus
38
237
49
5
16
13 22
Esophagus
Left Phrenic Nerve
Heart Valves
Fetal Heart
Medias- tinum
Saccular Viscus
Angina Pectoris
Cardiotonic Agents
Tissue Donors
![Page 39: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/39.jpg)
semantic network
• 135 semantic types – broad categories (drug, virus, etc.)
• 54 semantic relationships – links categories (is-a, causes, treats)
• types + relationships – broad categorization of biomedicine
![Page 40: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/40.jpg)
UMLS semantic network
Kleonsorge et al., 2007
Organism process of
Embryonic Structure
Anatomical Abnormality
Congenital Abnormality
Acquired Abnormality
Fully Formed Anatomical Structure
Anatomical Structure
part of
Organism Attribute
property of
Body Substance
contains,produces conceptual
part of
evaluation of
Body System conceptual part of
part of
Body Part, Organ or Organ Component
part of
Tissue
part of
Cell
part of
Cell Component
Gene or Genome
Body Space or Junction
adjacent to
location of
location of
evaluation of Finding
Laboratory or Test Result
Sign or Symptom
Biologic Function
Physiologic Function
Pathologic Function
Body Location or Region
conceptual part of
conceptual part of
Injury or Poisoning
disrupts
disrupts
co-occurs with
![Page 41: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/41.jpg)
SPECIALIST lexicon
• Over 330k entries – syntax – morphology – orthography
• natural language interface
![Page 42: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/42.jpg)
orthography
• Spelling variants – oe/e – ae/e – ise/ize – geniFve mark
– BriFsh-‐American variants
Addison's disease Addison disease Addisons disease
oesophagus -‐ esophagus
anaemia -‐ anemia
cauterise -‐ cauterize
criFcise -‐-‐ criFcize centre -‐-‐ center foetus -‐-‐ fetus
![Page 43: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/43.jpg)
normalization Hodgkin’s diseases, NOS
Hodgkin diseases, NOS Remove genitive
Hodgkin diseases, Remove stop words
hodgkin diseases, Lowercase
hodgkin diseases Strip punctuation
hodgkin disease Uninflect
Sort words disease hodgkin
![Page 44: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/44.jpg)
SPECIALIST lexicon {base=Kaposi's sarcoma spelling_variant=Kaposi sarcoma entry=E0003576
cat=noun variants=uncount variants=reg variants=
}
{base=chronic entry=E0016869
cat=adj variants=inv posiFon=aurib(1) posiFon=pred
}
{base=aspirate entry=E0010803 cat=verb variants=reg tran=np nominalizaFon=aspiraFon|noun|E0010804 }
{base=in entry=E0033870 cat=prep }
![Page 45: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/45.jpg)
subdomain integration
Biomedical literature
MeSH
Genome annotations
GO Model organisms
NCBI Taxonomy
Genetic knowledge bases
OMIM
Clinical repositories
SNOMED CT Other subdomains
…
Anatomy
FMA
UMLS
![Page 46: A.I. in health informatics - Tufts University · A.I. in health informatics lecture 5 standards & ontolologies kevin small & byron wallace *Slides(reuse(material(from(Kleinsorge,(Willis,(and(Emrick;2007](https://reader031.vdocuments.net/reader031/viewer/2022022807/5d0093a988c993df548ba6d9/html5/thumbnails/46.jpg)
why do we care?
• actionable intelligence requires knowledge about the universe – medicine very knowledge intensive – very rich information source
• machine learning requires appropriate representation – models uncertainty