From billing codes to expertise: mining, representing and sharing
clinical research profiles in the Linked Data Cloud
Carlo Torniai
Shahim Essaid, Chris Barnes, Stephen Williams, Janos HajagosNicole Vasilevsky, Melissa Haendel
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
CTSAConnect ProjectNeeds:
– Identify potential collaborators, relevant resources, and expertise across scientific disciplines
– Assemble translational teams of scientists to address specific research questions
Approach:
Create a semantic representation of clinician and basic science researcher expertise to enable
– more effective linking of information about clinicians and basic science researchers
– publication of expertise data as Linked Data (LD) for use in other applications
8/23/2012 3www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
Integrating VIVO and eagle-i
VIVO is an ontology-driven application . . . for collecting anddisplaying information about people
eagle-i is an ontology-driven application . . . for collecting and searching research resources
Both publish Linked Data. Neither addresses clinical expertise
eagle-i
VIVO
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
Extending eagle-i and VIVO to represent clinical expertise
eagle-i
VIVO
Semantic
Clinical activities
• Organizational affiliations
• Grant and project participation
• Activities
– Teaching courses
– Mentoring students
– (Co)-authoring publications
Researcher Characterization
• Research resources
– Reagents
– Biospecimens
– Animal models
– Instruments
– Techinque
• Training and credentials• Clinical research topic• Specialization inferred from EHR
– Procedures
– Diagnosis
– Prescriptions
Clinician Characterization
CTSAconnect will produce a single Integrated Semantic Framework that includes clinical expertise
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
ISF Clinical module
ARG: Agents, Resources, Grants ontologyCM: Clinical moduleIAO: Information Artifact OntologyOBI: Ontology for Biomedical InvestigationsOGMS: Ontology for General Medical ScienceFOAF: Friend of a Friend vocabularyBFO: Basic Formal Ontology
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
ISF Clinical module: encounter
ARG: Agents, Resources, Grants ontologyCM: Clinical moduleOGMS: Ontology for General Medical ScienceFOAF: Friend of a Friend vocabulary
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
ISF Clinical module: encounter output
CM: Clinical moduleOBI: Ontology for Biomedical InvestigationsOGMS: Ontology for General Medical Science
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
Collecting and publishing clinical expertise as represented by encounter
Step 1Aggregate
Clinical Data
Step 2Map Data to
ISF
Step 4Publish Linked
Data
Step 3Compute Expertise
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
Aggregate clinical data
Step 1Aggregate
Clinical Data
Step 2Map Data to
ISF
Step 4Publish Linked
Data
Step 3Compute Expertise
Provider ID
ICD Code Value
Code Count
Unique Patient Count Code Label
1234567 552.00 1 1Unilateral or unspecified femoral hernia
with obstruction (ICD9CM 552.00)
1234567 553.02 8 6Bilateral femoral hernia without mention
of obstruction or gangrene (ICD9CM 553.02)
1234567 555.1 4 1Regional enteritis of large intestine
(ICD9CM 555.1)
1234568 745.12 10 5Corrected transposition of great vessels
(ICD9CM 745.12)
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
Map data to ISF
Step 1Aggregate
Clinical Data
Step 2Map Data to
ISF
Step 4Publish Linked
Data
Step 3Compute Expertise
Provider ID ICD Code Value Code Count
UniquePatient Count Code Label
1234567 552.00 1 1
Unilateral or unspecified femoral hernia with
obstruction (ICD9CM 552.00)
1234567 553.02 8 6
Bilateral femoral hernia without mention of
obstruction or gangrene (ICD9CM 553.02)
1234567 555.1 4 1Regional enteritis of large intestine (ICD9CM 555.1)
1234568 745.12 10 5Corrected transposition of
great vessels (ICD9CM 745.12)
AggregatedClinical Data
ISF
RDFtriples
Java scriptsOWL API
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
Compute Expertise
Step 1Aggregate
Clinical Data
Step 2Map Data to
ISF
Step 4Publish Linked
Data
Step 3Compute Expertise
• Unified Medical Language System (UMLS) aggregates Medical Subjects Heading (MeSH) and other terminologies by linking them to UMLS concept unique identifiers (CUI)
• UMLS CUIs will be used to map ICD9 and CPT codes to MeSH
• Expertise indexed by MeSH will enable meaningful connections between clinicians, basic researchers, and biomedical knowledge
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
Compute Expertise: Mapping ICD9 to MeSH
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
Compute Expertise: weighting
Step 1Aggregate
Clinical Data
Step 2Map Data to
ISF
Step 4Publish Linked
Data
Step 3Compute Expertise
• Provider X has 500 patients
• S/he has used Syndactyly(ICD9: 755.12) for 30 unique patients 75 times
Percentage of patients with code: 30/500*100 = 6%
Code frequency: 75/30 = 2.5
Code weight: 6 * 2.5 = 15
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
Publish Linked Data
Step 1Aggregate
Clinical Data
Step 2Map Data to
ISF
Step 4Publish Linked
Data
Step 3Compute Expertise
Linked Data cloud
SPA
RQ
LEn
dp
oin
tsO
the
r A
PIs
…
Triple StoresSeveral means to access and
query data
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
Sample encounter data published as LOD
Inferred Types
Annotations and Properties
Health care encounter Instance URI
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
Querying the data
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
Beyond expertise
• Encounter data represented using ISF and published as Linked Data, in addition to enhance linkage between clinical and basic expertise, will enable integration with multiple datasets which could be used in a variety of ways to discover useful clinical associations and patterns
www.ctsaconnect.org CTSAconnectReveal Connections. Realize Potential.
Information CTSAconnect project
ctsaconnect.org
CTSAconnect ontology source
http://code.google.com/p/connect-isf/
The clinical module can be directed accessed at http://bit.ly/clinical-isf
Linked Data generation code http://bit.ly/isf-lod-code
eagle-i federated search
eagle-i.net
VIVO integrated search
vivosearch.org
CTSA ShareCenter
ctsasharecenter.org
CTSA 10-001: 100928SB23PROJECT #: 00921-0001
Carlo [email protected]
Shahim [email protected]
Chris [email protected]
Janos [email protected]
Stephen V [email protected]
Nicole [email protected]
Melissa [email protected]
Top Related