Clinical Observations Interoperability: A Semantic Web Approach to Eligibility Screening for Clinical Trials

1
Clinical Observations InteroperabilityA
Semantic Web Approachto Eligibility Screening
for Clinical Trials
Vipul Kashyap Eric Prudhommeau Helen Chen
Holger Stenzhorn Jyotishman Pathak Rachel
Richesson

• AMIA Spring Symposium, Orlando
• May 29, 2009

2
Outline

• COI and HCLS Group (W3C)
• What is Semantic Web?
• Motivating problem
• Methods for development of demonstration
• How do we use SW to address problem?
• Challenges
• Future
• Benefits

3
Developers of this demonstration..

• Clinical Observation Interoperability (COI) Task
  Force http//esw.w3.org/topic/HCLS/ClinicalObserva
  tionsInteroperability
• Members from CDISC, clinical trial researchers
  and healthcare IT researchers

4
What is the Semantic Web?

• Factors Influencing the Scaling of the WWW
• URL
• Lack of centralization
• Simple standards
• Human-readable
• Tools

• Technologies
• SWRL, RIF
• OWL
• SPARQL
• RDF/ RDF Schema
• XML/XML Schema
• HTML

Adapted from Berners-Lee, Hendler. Nature 2001.
5
The Core of the Semantic WebRDF Statements
Has- Diagnosis
http//Hospital_A_Admissions_Patient 123456
Diabetes
Object (literal)
Subject
Predicate
http//trusted_source_Diabetes_definition
http//trusted_source_ Has-Dx_definition
http//Hospital_A_Admissions_Patient 123456
Object (resource)
Subject
Predicate
6
Other technologies

• OWL (Web Ontology Language)
• RIF (Rule Interchange Format)
• N3 (Notation 3)
• SPARQL (Query Language for RDF)

7
Problem...Clinical Trials Recruitment
8
Use Case Patient Screening
PROBLEM Same construct in 2 different
representations.
9
Clinical Observations Interoperability
Clinical Trial Eligibility
Patient Characteristics
construct
Research Protocols
EMR
data source
DCM/RIM
SDTM
semantic model
HL7
CDISC
Standards Development Organization
10
Methods

• Use case scope
• Developed semantic models for
• clinical trial based upon SDTM
• clinical practice based upon HL7 DCM
• Selected clinical trials
• SDTM ? RDF
• Received patient data (relational database)
• HL7 DCM ? RDF
• Mapping between SDTM DCM (SPARQL)
• Used Drug Ontology to facilitate mapping on drug
  concepts at different granularities (ingredients
  to class)
• Mapping of DCM ontology to relational database
  schema
• Developed query interface

11
Mechanics

• Eligibility expressed in SPARQL queries in SDTM
  language
• Translated the SDTM SPARQL query into an HL7 DCM
  SPARQL statement
• HL7 DCM SPARQL statement transformed to SQL
• Execute SQL and list eligible patient data

12
Inclusion Criteria

• Type 2 diabetes on diet and exercise therapy or
  monotherapy
• with metformin, insulin secretagogue, or
  alpha-glucosidase inhibitors, or a low-dose
  combination of these at 50 maximal dose. Dosing
  is stable for 8 weeks prior to randomization.
• ?patient takes metformin
  .

13
Exclusion Criteria

• Use of warfarin (Coumadin), clopidogrel (Plavix)
  or other anticoagulants.
• ?patient doesNotTake anticoagulant .

14
Examples Drug Class in Research Protocols

• monotherapy with metformin, insulin secretagogue,
  or alpha-glucosidase inhibitors and a low dose
  combination of all
• Long term insulin therapy
• Therapy with rosiglitazone (Avandia) or
  pioglitazone (Actos), or extendin-4 (Byetta),
  alone or in combination
• corticosteroids
• weightloss drugs e.g., Xenical (orlistat),
  Meridia (sibutramine), Acutrim (phenylpropanol-ami
  ne), or similar medications
• nonsteroidal anti-inflammatory drugs
• Use of warfarin (Coumadin), clopidogrel (Plavix)
  or other anticoagulants
• Use of probenecid (Benemid, Probalan),
  sulfinpyrazone (Anturane) or other uricosuric
  agents

15
Prescription Information in EMR

• "132139","131933","98630 ","GlipiZIDE-Metformi
  n HCl 2.5-250 MG Tablet","54868079500
  ",98630,"2.5-250 ","TABS","","MG
  "," ","15","GlipiZIDE-Metformin HCl
  ","","GlipiZIDE-Metformin HCl 2.5-250 MG Tablet
• "132152","131946","98629 ","GlipiZIDE-Metformi
  n HCl 2.5-500 MG Tablet","54868518802
  ",98629,"2.5-500 ","TABS","","MG
  "," ","15","GlipiZIDE-Metformin HCl
  ","","GlipiZIDE-Metformin HCl 2.5-500 MG Tablet
• "132407","132201","98628 ","GlipiZIDE-Metformi
  n HCl 5-500 MG Tablet","54868546702
  ",98628,"5-500 ","TABS","","MG
  "," ","15","GlipiZIDE-Metformin HCl
  ","","GlipiZIDE-Metformin HCl 5-500 MG Tablet
• "132642","132436","C98630 ","GlipiZIDE-Metformi
  n HCl TABS","54868079500 ",98630,"","TABS","","
  "," ","15","GlipiZIDE-Metformin HCl
  ","","GlipiZIDE-Metformin HCl TABS"

16
Drug Ontology Bridging Drug Names and Classes
17
Use Case Patient Screening
18
COI Demo Clinical Trial Eligibility Criteria
19
COI Demo Selecting Inclusion Criteria
Inclusion in SDTM ontology
SDTM clinical trial ontology
20
COI Demo Drug Ontology Inference
Subclasses of anticoagulant
Drug ontology
Exclusion in Drug ontology
21
COI Demo Selecting Mapping Rules
check all drugs that "may_treat obese" ?A
rdfssubClassOf ?B rdfslabel ?D. ?B a
owlRestriction owlonProperty may_treat
owlsomeValuesFrom C0028754 gt ?D a
WeightLoseDrug.
22
COI Demo Getting Right Patients
23
COI Demo Evolving

• coi svn
• http//code.google.com/p/coi/source/checkout
• Public access
• http//hcls.deri.org/coi/demo/

24
Challenges

• Lack of robust standards for Eligibility Criteria
  
• Standards in all areas evolving
• Finding appropriate mappings (e.g., case
  definitions)
• Regulations of data re-use
• Reasoning on large amount of data
• Large tree structure navigation
• More patient data to test all proposed scenarios
• More domain experts

25
Future

• Respond to new CDISC standards
• Respond to Protocol Representation standards
• Respond to various interpretations of DCM
  standard
• Add additional eligibility constructs
• Need real patient data for testing
• Improve interface
• Demonstrate re-use and scalability

26
Benefits of Semantic Web Approach

• Explicit Unambiguious conceptual models
• Flexible No commitment to a common ontology
• Collaborative All ontologies are external can
  be refined
• Scalable The brains (i.e., mapping rules) of
  the system are external
• Extensible Can add additional entities or
  mapping rules
• Re-usable Once get experience in one system,
  technology is the same in different settings
• Real-time Automatic translation (to query
  languages) reflecting real time integration
  needs.

27
Acknowledgements

• Major developers
• Helen Chen
• Holger Stenzhorn
• Eric Prudhommeau
• Other supporters
• Jennifer Fostel
• Bo Anderssen
• Kerstin Forsberg
• M. Scott Marshall
• Tom Oniki

• Dr. Parsa Mirhaji, University of Texas Health
  Science Center at Houston, Center for Biosecurity
  and Public Health Informatics Research (sample
  data)
• W3C Interest Group on the Semantics for the
  Healthcare and Life Sciences (HCLS)

Questions Rachel.Richesson_at_epi.usf.edu