![One definition…
Explicit specification of a conceptualization
[Gruber, 1993]](https://image.slidesharecdn.com/sle2012storeyslideshare-121114043946-phpapp02/85/SLE-2012-Keynote-Cognitive-and-Social-Challenges-of-Ontology-Use-in-the-Biomedical-Domain-10-320.jpg)
![Drug Safety: Detecting Risk Signals
ROR of 1.5, CI of [1.11, 2.13]
The X2 p-value <10-7
MI No MI
Vioxx a b
No Vioxx c d
Slide by Nigam Shah.](https://image.slidesharecdn.com/sle2012storeyslideshare-121114043946-phpapp02/85/SLE-2012-Keynote-Cognitive-and-Social-Challenges-of-Ontology-Use-in-the-Biomedical-Domain-60-320.jpg)
SLE 2012 Keynote: Cognitive and Social Challenges of Ontology Use in the Biomedical Domain
- 1. Cognitive and Social Challenges of Ontology use in the Biomedical Domain SLE 2012: 5th International Conference on Software Language Engineering Dresden, Germany Margaret-Anne Storey The CHISEL Group, University of Victoria
- 2. Studying and addressing human aspects in software engineering and knowledge engineering
- 3. Research methods used: – Mixed methods (analysis of archival data, interviews, grounded theory, surveys etc.) Technologies explored: – Visualization techniques – Collaboration support – Social media
- 4. Focus of this talk: Providing cognitive support for ontology developers and users throughcollaborative visual user interfaces
- 5. Ontology Ontology Ontology Creation Library Applications Background BioPortal Annotation Examples Services Search Tools Mappings
- 6. Ontology Ontology Ontology Creation Library Applications Background BioPortal Annotation Examples Services Search Tools Mappings
- 8. The study of being
- 9. Co-opted by computer science to enable the explicit specification of Entities Propertiesand attributes of entities Relationsbetween entities
- 10. One definition… Explicit specification of a conceptualization [Gruber, 1993]
- 12. Ontology languages Choice of language and choice of reasoning engine Tradeoff between expressiveness, reasoning power, tractability and human understanding May need inference engine to give real-time feedback while authoring an ontology
- 13. Why ontologies?
- 14. Awash in data….
- 17. How are ontologies used?
- 18. Challenges? Cognitive issues: – Complexity, scale – Evolution – Inclusion of “upper ontologies”, or parts of other ontologies Social issues: – One size does not fit all – Multiple authors – Input from broader set of stakeholders
- 19. Ontology Ontology Ontology Creation Library Applications Background BioPortal Annotation Examples Services Search Tools Mappings FMA, GO, ICD
- 20. Foundational Model of Anatomy (FMA) Comprehensive ontology of human anatomy Over 120K terms, 2.1M relationship instances (168 relationship types) One of the largest and best developed ontologies in biomedicine, multi-purpose Slide by Mark Musen.
- 21. Slide by Mark Musen.
- 22. Gene Ontology (GO) To unify representation of gene and gene product attributes across all species For annotating genes and gene products, assimilate and disseminate annotation data Contains over 24,500 terms applicable to a wide variety of biological organisms A standard tool in bioinformatics
- 24. International Classification of Diseases (ICD) • An enumeration of diseasesthat forms the basis for medical claims and reimbursements • A “legacy” terminology that has its roots in 19th century epidemiology • Created initially by biostatisticians with a pressing need to compare death statistics in different European countries Slide by Mark Musen.
- 25. ICD is used for lots of (too many?) things! • ICD is used to code all patient encounters with the health-care system for: – Billing and reimbursement – Institutional planning – Disease surveillance and public health – Quality assurance – Economic modeling • ICD was never intended to make the distinctions relevant to all these tasks! • Nevertheless it is widely used! Slide by Mark Musen.
- 26. ICD: An excerpt… 724 Unspecified disorders of the back 724.0 Spinal stenosis, other than cervical 724.00 Spinal stenosis, unspecified region 724.01 Spinal stenosis, thoracic region 724.02 Spinal stenosis, lumbar region 724.09 Spinal stenosis, other 724.1 Pain in thoracic spine 724.2 Lumbago 724.3 Sciatica 724.4 Thoracic or lumbosacral neuritis 724.5 Backache, unspecified 724.6 Disorders of sacrum 724.7 Disorders of coccyx 724.70 Unspecified disorder of coccyx 724.71 Hypermobility of coccyx 724.71 Coccygodynia 724.8 Other symptoms referable to back 724.9 Other unspecified back disorders Slide by Mark Musen.
- 27. ICD9 (1977): A handful of codes for traffic accidents Slide by Mark Musen.
- 28. ICD10 (1999): 587 codes for such accidents V31.22 Occupant of three-wheeled motor vehicle injured in collision with pedal cycle, person on outside of vehicle, nontraffic accident, while working for income W65.40 Drowning and submersion while in bath-tub, street and highway, while engaged in sports activity X35.44 Victim of volcanic eruption, street and highway, while resting, sleeping, eating or engaging in other vital activities Slide by Mark Musen.
- 29. ICD revision process in the 20th Century… • International and National Revision conferences • 1-5 person delegations in International conferences, multi-disciplinary • Manual curation • Output: paper copy • Negotiation process: decibel method of discussion • ICD drafts translated into 27 languages See http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2950305/
- 30. ICD-11 revision: key aspects • Content model • Topic Advisory Groups – vertical and horizontal • Classification experts (ontology development) • iCAT: web based collaborative authoring tool • Use cases – evaluating ICD-11 in use
- 31. Deliverables • Print versions –fit for purposein multiple languages • Web portal to access, browse and maintain it – Input from the crowd • Classification in formalized language
- 32. Ontology Ontology Ontology Creation Library Applications Background BioPortal Annotation Examples Services Search Tools Mappings FMA-Explorer, Protégé, iCAT
- 33. Foundational Model Explorer University of Victoria 33
- 34. Protégé ontology authoring environment Ontology contents need to be processed and interpreted by computers Interactive tools can assist developers in ontology authoring (e.g. Protégé)
- 37. iCAT web based authoring tool for ICD-11
- 38. Ontology Ontology Ontology Creation Library Applications Background BioPortal Annotation Examples Services Search Tools Mappings
- 39. National Center for Biomedical Ontology Goal: develop innovative technology and methods that allow scientists to record, manage, and disseminate biomedical information and knowledge in both human readable and machine-processableform
- 43. Ontology Ontology Ontology Creation Library Applications Background BioPor Annotation Examples Services Search Tools Mappings
- 44. BioPortal services • Ontology recommender • Ontology widgets • Annotator • API access through REST services • Virtual appliance (custom installs, can be proprietary)
- 47. Ontology Widgets
- 50. Ontology Ontology Ontology Creation Acquisition Applications Background Library Annotation Examples Services Search Tools Mappings
- 52. Visualizing multiple ontologies and mappings
- 54. Mappings between terms - Matrix
- 55. Mappings between ontologies -- Graph
- 56. Ontology Ontology Ontology Creation Acquisition Applications Background Library Annotation Examples Services Search Tools Mappings
- 57. Data from STRIDE • 1.8 million pediatric and adult patients with clinical and demographic data (1994 - present) • 19 million Clinical Encounters (1994 - present) 35 million 22 million 2.9 million 1.2 million 7 million 137 million 10 million Slide by Nigam Shah.
- 58. Making EMRs Unreasonably Effective Text clinical note BioPortal – knowledge graph Creating clean lexicons Diseases Frequency Term – 1 : Term recognition tool : NCBO Annotator Procedures : Annotation Workflow Syntactic types Term – n Drugs Terms Recognized P1 ICD9 ICD9 ICD9 ICD9 ICD9 ICD9 P1 T1, … T5, … T4, T8, … T6, T1, Further Analysis T2, T4, T3, T9, T8, T2, no T4 T3 T1 T4 T10 no T4 P2 P2 P3 Negation detection Cohort of Interest P3 : : Pn Pn Terms form a temporal series of tags Slide by Nigam Shah.
- 59. P1 ICD9 ICD9 ICD9 ICD9 ICD9 ICD9 P1 T1, … T5, … T4, T8, … T6, T1, T1 … … Tn T2, T4, T3, T9, T8, T2, no T4 T3 T1 T4 T10 no T4 P1 1 0 1 1 P2 P2 : 0 1 1 0 P3 P3 : 0 0 0 1 : : Pn 0 1 0 1 Pn Pn T1 … … Tn P1 … … Pn T1 1 0.6 0.5 0.6 P1 1 0.1 0.7 0.8 : 1 0.2 0.3 : 1 0.5 0.8 : 1 0.1 : 1 0.4 Who is getting Tn 1 Pn 1 What is special these drugs, about these conditions, etc? patients? Comparative cephalexin cane Drug Safety doppler ultrasonography ultrasound imaging Effectiveness amoxicillin doppler studies angioplasty atherectomy revascularization wheelchair cilostazol vascular surgical bypass graft Learning hydralazine congestive heart diagnostic procedures Predictions from Data pneumonia imaging surgical revision failure bypass heart failure nifedipine testosterone amiodarone pravastatin vascular diseases carotid pantoprazole insulin glargine endarterectomy obesity transplantation ramipril fentanyl zolpidem trimethoprim decompressive incision coronary sulfamethoxazole diazepam angiography fluoroscopic heart angiography transplantation tacrolimus temazepam Slide by Nigam Shah.
- 60. Drug Safety: Detecting Risk Signals ROR of 1.5, CI of [1.11, 2.13] The X2 p-value <10-7 MI No MI Vioxx a b No Vioxx c d Slide by Nigam Shah.
- 61. Ontology uses See http://research.microsoft.com/en-us/projects/ontology/
- 65. Ontology Ontology Ontology Creation Acquisition Applications Background Library Annotation Examples Services Search Tools Mappings
- 66. GoPubmed
- 72. Ontology Ontology Ontology Creation Acquisition Applications Background Library Annotation Examples Services Search Tools Mappings What’s next?
- 73. Towards collaborative ontology visualization as a service • Preserve easy-to-use visualizations of ontologies • Enable flexible visual exploration and analysis of biomedical ontologies and data • Support collaboration in visual exploration and analysis of biomedical ontologies and data • Enable presentation of analysis artifacts on the web
- 74. BioMixer An online platform for the visual exploration of multiple biomedical ontologies
- 77. Demo
- 81. University of Victoria 81
- 83. Ontology Ontology Ontology Creation Library Applications Background BioPortal Annotation Examples Services Search Tools Mappings Summary
- 84. Concluding remarks • Ontologies finally coming of age(D. McGuinness) • With adoption, novel tools will emerge • Users now savvy with search, visualization and analytics • Anticipated benefits for translational research “Developers do not innovate tools, users do”
- 85. Selected References Gruber T., A Translation Approach to Portable Ontologies. Knowledge Acquisition 5(2):199-220, 1993 ICD11: http://www.youtube.com/user/whoicd11 Ernst, N.A., Storey, M.A., Allen, P.: Cognitive support for ontology modeling. International Journal of Human-Computer Studies 62(5), 553–577 (2005) Fu, B., Grammel, L., Storey, M.A.: BioMixer: A Web-based Collaborative Ontology Visualization Tool. 3rd International Conference on Biomedical Ontology (ICBO 2012) (2012) Gruber, T.R.: Towards Principles for the Design of Ontologies Used for Knowledge Sharing. In: Guarino, N., Poli, R. (eds.) Formal Ontology in Conceptual Analysis and Knowledge Representation. vol. 43, pp. 907–928. Kluwer Academic Publishers (1993) Katifori, A., Halatsis, C., Lepouras, G., Vassilakis, C., Giannopoulou, E.: Ontology visualization methods— a survey. ACM Computing Surveys 39(4) (2007) Musen, M.A., Noy, N.F., Shah, N.H., Chute, C.G., Storey, M.A., Smith, B., Team, the NCBO: The National Center for Biomedical Ontology. Journal of the American Medical Informatics Association (In press.) (2012), http://bmir.stanford.edu/file_asset/index.php/1729/BMIR-2011-1468.pdf Noy, N.F., Shah, N.H., Whetzel, P.L., Dai, B., Dorf, M., Griffith, N., Jonquet, C., Rubin, D.L., Storey, M.A., Chute, C.G., Musen, M.A.: BioPortal: ontologies and integrated data resources at the click of a mouse. Nucleic acids research 37(Web Server issue) (Jul 2009) Smith, B.: Ontology (Science). Nature Precedings (i) (Jul 2008) Tudorache, T., Falconer, S., Noy, N., Nyulas, C., ¨Ust¨un, T., Storey,M.A., Musen, M.: Ontology development for the masses: creating ICD-11 in WebProt´eg´e. In: Knowledge Engineering and Management by the Masses, EKAW2010. pp. 74–89. Springer (2010)
Editor's Notes
- #76: Useful for independent explorations and comparisonsCould include video of demo here.
- #77: Couldlabel the data graph (make it clear that it is our internal datastructure, which runs on the client (and the actual data can be different on each client), and we build it by calling the REST services)