Clinical Observations Interoperability: - Bridging Clinical Practice and Clinical Research

1
Clinical Observations Interoperability -
Bridging Clinical Practice and Clinical Research

• Helen Chen
• February 13, 2009

2
Motivation

• Pressing need for interoperability between
  clinical trials and clinical practice
• Bridge gaps between various standards to connect
  related fields
• Semantic Web technologies are maturing quickly
  and getting ready for prime time

3
Clinical Observation Interoperability Group

• W3C Semantic Web for Life Sciences and Healthcare
  Interest Group
• Members from CDISC, clinical trial researchers
  and healthcare IT researchers
• http//esw.w3.org/topic/HCLS/ClinicalObservationsI
  nteroperability

4
Goals

• Show that Semantic Web technologies can be used
  to bridge the gap between the two
• Map across formats
• Reuse existing data
• Develop a proof of concept application that
  demonstrates the feasibility of that approach

5
Use Case Step-Through

• (Textual) specification of the eligibility
  criteria for a given clinical trial
• Ontology-based translation of the eligibility
  criteria into SPARQL queries
• Translation of the SPARQL queries into
  database-specific queries
• Execution of the queries at the databases)
  results contain all eligible patients
• Return of a list of eligible patients to clinical
  trial administrator

6
Problems

• Data is not stored only in form of the CDISC SDTM
  but also in HL7 DCM form
• Concepts in SDTM domain do not always have
  one-one mapping to HL domain
• Drug prescription coded in different drug codes
  (RxNorm and NDC)
• Data is not stored as RDF but in conventional
  relational databases

7
Solution

• Transform references described in SDTM classes to
  references described to HL7 classes via N3 rules
• Obtain relavant concepts at different granularity
  via inferencing
• Class-gtsubclasses
• Derive new classes (weight loss drug) via
  ltmay-treatgt mechanism
• Transform either
• Relational data into RDF
• or SPARQL into SQL via N3 rules
• Second approach chosen

8
Ontology Modeling

• Develop ontologies for clinical trials and
  clinical practice based on CDISC SDTM and HL7
  DCM
• Write mapping rules
• Model patient and medication aspects
• Lab results and observations
• Patient vital signs
• Medications

9
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
  .

.
.
10
Exclusion Criteria

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

.
.
11
Medication

• M0271 a sdtmMedication splclassCode 6809
  metformin sdtmsubject P0006
  sdtmdosePerAdministration sdtmhasValue
  500 sdtmhasUnit "mg sdtmstartDateTime
  "20070101T000000"xsddateTime
  sdtmendDateTime "2008-0101T000000"xsddate
  Time .

12
Criteria in SPARQL

• ?medication1 sdtmsubject ?patient
  splactiveIngredient ?ingredient1 .
• ?ingredient1 splclassCode 6809 .
• OPTIONAL
• ?medication2 sdtmsubject ?patient
  splactiveIngredient ?ingredient2 .?ingredient2
  splclassCode 11289 .
• FILTER (!BOUND(?medication2))

13
Drug Class Information in CT 8

• 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

14
Prescription Information in Patient Database

• "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"

15
Drug Ontology By Stanford
from drug ontology documentation
16
Mapping Between CT and Patient Record
C1299007
C0050393
C0066535
C0025598
17
SDTM to HL7 Transformation
Clinical Trial Ontology
sdtmMedication sdtmdosePer- Administration


?x a sdtmMedication sdtmdosePer-
Administration ?y gt ?x hl7Substance-
Administration hl7doseQuantity ?y
hl7Substance- Administration hl7doseQuantity
Clinical Practice Ontology
18
HL7 to EMR Database Transformation
SPARQL in Clinical Practice Ontology


hl7substanceAdministration a
hl7SubstanceAdministration hl7consumable
hl7displayName ?takes
splactiveIngredient splclassCode ?ingred
gt ?indicItem Item_MedicationPatie
ntID ?person Item_MedicationPerfo
rmedDTTM ?indicDate
Item_MedicationEntryName ?takes . .
hl7Substance- Administration hl7doseQuantity
Item_MedicationEntryName ?takes
. MedicationItemID ?indicItem
SQL to EMR Database
19
Pushing Query to Database

• SPARQL in SDTM ontology to SPARQL in HL7 ontology
• SPARQL in HL7 ontology to SQL in EMR database

List of eligible patients
EMR
HL7 DCM/RIM
CT Eligibility
SPARQL
SQL
SPARQL
20
SPARQL in SDTM

• PREFIX sdtm lthttp//www.sdtm.org/vocabularygt
• PREFIX spl lthttp//www.hl7.org/v3ballot/xml/infra
  structure/vocabulary/vocabularygt
• SELECT ?patient ?dob ?sex ?takes
  ?indicDate?contra
• WHERE
• ?patient a sdtmPatient
• sdtmmiddleName ?middleName
• sdtmdateTimeOfBirth ?dob
• sdtmsex ?sex .
• sdtmsubject ?patient
• sdtmstandardizedMedicationName ?takes
• splactiveIngredient splclassCode ?code
• sdtmstartDateTimeOfMedication
  ?indicDate
• .
• OPTIONAL
• sdtmsubject ?patient
• sdtmstandardizedMedicationName ?contra
• splactiveIngredient splclassCode 11289
• sdtmeffectiveTime

21
SDTM-HL7 Mapping Rules

• CONSTRUCT
• ?patient a sdtmPatient
• sdtmmiddleName ?middleName
• sdtmdateTimeOfBirth ?dob
• sdtmsex ?sex .
• a sdtmConcomitantMedication
• sdtmsubject ?patient
• sdtmstandardizedMedicationName ?takes
• splactiveIngredient splclassCode ?ingred
  
• sdtmstartDateTimeOfMedication ?start
• . WHERE
• ?patient a hl7Person
• hl7entityName ?middleName
• hl7livingSubjectBirthTime ?dob
• hl7administrativeGenderCodePrintName ?sex
  
• hl7substanceAdministration
• a hl7SubstanceAdministration
• hl7consumable
• hl7displayName ?takes

22
SPARQL in HL7 Via SWtranformer

• PREFIX hl7 lthttp//www.hl7.org/v3ballot/xml/infra
  structure/vocabulary/vocabularygt
• SELECT ?patient ?dob ?sex ?takes ?indicDate
• WHERE
• ?patient hl7entityName ?middleName .
• ?patient hl7livingSubjectBirthTime ?dob .
• ?patient hl7administrativeGenderCodePrintName
  ?sex .
• ?patient a hl7Person .
• ?patient hl7substanceAdministration
  ?b0035D918_gen0 .
• ?b0035D918_gen0 hl7consumable
  ?b0035C798_gen1 .
• ?b0035D918_gen0 a hl7SubstanceAdministrationgt
  .
• ?b0035D918_gen0 hl7effectiveTime ?b0035C5E8_ge
  n3 .
• ?b0035C798_gen1 hl7displayName ?takes .
• ?b0035C798_gen1 hl7activeIngredient
  ?b0035C848_gen2 .
• ?b0035C848_gen2 hl7classCode ?code .
• ?b0035C5E8_gen3 hl7start ?indicDate .
• FILTER ( ?code 6809 )

23
HL Database Mapping Rules Tables

• PREFIX xsd lthttp//www.w3.org/2001/XMLSchemagt
• PREFIX Person lthttp//hospital.example/DB/Person
  gt
• PREFIX Sex_DE lthttp//hospital.example/DB/Sex_DE
  gt
• PREFIX Item_Medication lthttp//hospital.example/D
  B/Item_Medicationgt
• PREFIX Medication lthttp//hospital.example/DB/Med
  icationgt
• PREFIX Medication_DE lthttp//hospital.example/DB/
  Medication_DEgt
• PREFIX NDCcodes lthttp//hospital.example/DB/NDCco
  desgt

24
HL Database Mapping Rules Schema

• CONSTRUCT
• ?person a hl7Person
• hl7entityName ?middleName
• hl7livingSubjectBirthTime ?dob
• hl7administrativeGenderCodePrintName ?sex
  
• hl7substanceAdministration a
  hl7SubstanceAdministration
• hl7consumable
• hl7displayName ?takes
• splactiveIngredient splclassCode
  ?ingred
• hl7effectiveTime hl7start
  ?indicDate
• .
• WHERE
• ?person PersonMiddleName ?middleName
• PersonDateOfBirth ?dob
• PersonSexDE ?sexEntry .
• OPTIONAL ?indicItem Item_MedicationPatientID
  ?person
• Item_MedicationPerformedDTTM
  ?indicDate
• Item_MedicationEntryName ?takes
  .

25
SQL to Database

• SELECT patient.id AS patient, patient.DateOfBirth
  AS dob, sexEntry_gen0.EntryName AS sex,
  indicItem_gen1.EntryName AS takes,
  indicItem_gen1.PerformedDTTM AS indicDate
• FROM Person AS patient
• INNER JOIN Sex_DE AS sexEntry_gen0 ON
  sexEntry_gen0.idpatient.SexDE
• INNER JOIN Item_Medication AS indicItem_gen1 ON
  indicItem_gen1.PatientIDpatient.id
• INNER JOIN Medication AS indicMed_gen2 ON
  indicMed_gen2.ItemIDindicItem_gen1.id
• INNER JOIN Medication_DE AS indicDE_gen5 ON
  indicDE_gen5.idindicMed_gen2.MedDictD
  E
• INNER JOIN NDCcodes AS indicCode_gen6 ON
  indicCode_gen4.ingredient6809 AND
  indicCode_gen6.NDCindicDE_gen5.NDC

26
COI Demo

• coi svn
• http//code.google.com/p/coi/source/checkout
• Public access (working in progress)
• http//hcls.deri.org/coi/demo/

27
COI Demo Clinical Trial Eligibility Criteria
28
COI Demo Selecting Inclusion Criteria
Inclusion in SDTM ontology
SDTM clinical trial ontology
29
COI Demo Drug Ontology Inference
Subclasses of anticoagulant
Drug ontology
Exclusion in Drug ontology
30
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.
31
COI Demo Getting Right Patients
32
Benefits of Semantic Web Apporach

• Unambiguious conceptual model for seperate
  doamins without early commitment to a common
  ontology
• Reusable mapping rules from clinical research
  domain to Healthcare domain
• Late bining of coding systems and database schema
• Transform SPARQL to SQL in real time, reflecting
  real time discovery and integration needs

33
Challenges Ahead

• Large Tree Structure Navigation
• Reasoning on Large Data
• SWTranformer, url processing and filter clause
  implementation
• Portability Issues on DERI Server
• More patient data to test all proposed scenarios

34
Questions and Suggestions?

• Thank You!