Transcript Practical Applications of Ontologies in Clinical Systems

Panel: Problems with Existing EHR
Paradigms and How Ontology
Can Solve Them
Roberto A. Rocha, MD, PhD, FACMI
Sr. Corporate Manager
Clinical Knowledge Management and Decision Support,
Clinical Informatics Research and Development, Partners Healthcare
System
Lecturer in Medicine
Division of General Internal Medicine and Primary Care, Department of
Medicine, Brigham and Women’s Hospital, Harvard Medical School
International Conference on Biomedical Ontology
July 28-30, 2011
Buffalo, New York, USA
Panel: Problems with Existing EHR
Paradigms and How Ontology
Can Solve Them
Roberto A. Rocha, MD, PhD, FACMI
Sr. Corporate Manager
Clinical Knowledge Management and Decision Support,
Clinical Informatics Research and Development, Partners Healthcare
System
Lecturer in Medicine
Division of General Internal Medicine and Primary Care, Department of
Medicine, Brigham and Women’s Hospital, Harvard Medical School
International Conference on Biomedical Ontology
July 28-30, 2011
Buffalo, New York, USA
Opportunity
• New generation of clinical systems beyond efficient
record storage and communication
– New paradigm with pervasive computerized data analysis
and decision support
– Widespread use of interoperable services and data, with
advanced functions that enable team-based care
Example: Simple ‘If - Then’ rule
Example: Simple ‘If - Then’ rule
Lab results?
Patient data
Medications?
Concepts
Coded values?
LOINC?
Problem list?
Bedside measurements?
Knowledge
Rules?
SNOMED CT?
Classifications?
Formulas?
Availability of data
• Availability of structured and coded clinical data determines
the feasibility of CDS interventions
– Data is expensive to generate at the point-of-care (systematically)
– Benefits frequently not tangible to data “producers” (extra incentives)
• Dissemination and exchange of knowledge assets depends on
data standardization (structure & semantics)
Natural language processing?
Voice recognition?
Mobile devices?
Knowledge-driven documentation?
Semantic expressivity (adaptive)?
Health IT Data Standards!
Efficient dissemination strategy
Subscribes to
literature alerts
Similar model for a
Personal Health Records
(individuals)
CDS rules, order
sets, dashboards
are updated
Notices a guideline
updated with a
new drug
Creates ‘action
flowcharts’ using
workflow models
Decides to
implement new
guideline
Downloads
guideline into EHR
Stead WW and Lin HS, editors. Computational
Technology for Effective Health Care: Immediate
Steps and Strategic Directions. National Research
Council, 2009.
Current dissemination barriers
Large scale CDS
Development
of CDS
content
CDS content
in standard
format
CDS content
available for
download
What will differentiate clinical systems?
Process automation?
Ease of use?
Advanced CDS functions?
EHRs with
end-user
configurable
CDS
How ontologies can help?
• Shared concepts and logical models (data &
knowledge)
– Proper domain coverage, but without compromising
extensibility and innovation
– More accessible methods and tools to enable widespread
adoption
– Training and demonstration projects
• Cost-effective semantic interoperability
– Lower the cost and overhead of the data & knowledge
‘translation’ every time exchange is necessary
• Clinical systems that can seamlessly represent and
process a complete electronic patient care record
– Move beyond interoperability space and start
influencing/guiding transactional data and knowledge
representation models
Thank you!
Roberto A. Rocha, MD, PhD
[email protected]