using ontologies in clinical decision support applications

13
1 Using Ontologies in Clinical Decision Support Applications Samson W. Tu Stanford Medical Informatics Stanford University

Upload: sabin

Post on 30-Jan-2016

40 views

Category:

Documents


0 download

DESCRIPTION

Using Ontologies in Clinical Decision Support Applications. Samson W. Tu Stanford Medical Informatics Stanford University. Main points. Information technology has the potential to advance patient care by improving clinician adherence to clinical practice guidelines - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Using Ontologies in Clinical Decision Support Applications

1

Using Ontologies in Clinical Decision Support Applications

Samson W. Tu

Stanford Medical Informatics

Stanford University

Page 2: Using Ontologies in Clinical Decision Support Applications

2

Main points

Information technology has the potential to advance patient care by improving clinician adherence to clinical practice guidelines

Principled architecture that separates ontologies, knowledge bases, and problem-solving components allows development and deployment of maintainable complex software systems

EON and ATHENA projects demonstrate use of ontologies in clinical decision support applications

Page 3: Using Ontologies in Clinical Decision Support Applications

3

EON project NLM-funded project at Stanford (PI: Dr. Musen) Develop methodology, ontologies, and software

components for creating decision-support system for guideline-based care

Use Protégé knowledge-acquisition methodology and tool for construction of Domain concept ontologies Patient information model Guideline knowledge bases

Develop software components that assist clinicians in specific tasks Therapy-advisory and eligibility-determination servers Database mediator for time-oriented queries Explanation and visualization facilities

Page 4: Using Ontologies in Clinical Decision Support Applications

4

EON architecture

ClientsServers

ProtocolEligibilityChecker

TherapyAdvisory

Server

Protégé

TemporalMediator

YentaYentaEligibilityClient

YentaYentaAdvisoryClient

ClientsPatient

Database

ProtégéKnowledge

BaseEON

GuidelineOntology

Medical DomainOntology

PatientData Model

Guidelines

Page 5: Using Ontologies in Clinical Decision Support Applications

5

ATHENA project

Funded by VA Research Service HSR&D (PIs: Drs. Hoffman and Goldstein, VA clinicians and Stanford faculties)

Hypothesized that guideline-based interventions in management of hypertension can Change physicians’ prescribing behavior Change patient outcome

Deployed and evaluated at primary care VA clinics in 9 geographically diverse cities over a 15-month clinical trial

Results Expert clinicians maintain hypertension knowledge base

using Protégé Clinicians interacted with the ATHENA Hypertension

Advisory at 54% of all patient visits Impact on prescribing behavior and change patient outcome

being analyzed

Page 6: Using Ontologies in Clinical Decision Support Applications

6

ATHENA Clients

AdvisoryClient

EventMonitor

Building ATHENA system from EON components

PatientDatabase

ATHENA Clients

EON Servers

GuidelineInterpreter Advisory

Client

EventMonitor

TemporalMediator

VA CPRS

VA DHCP

Data Converter

nightly data extraction Guideline

KnowledgeBase

Protégé

ATHENA GUI

Page 7: Using Ontologies in Clinical Decision Support Applications

7

What the Clinician Sees…

Page 8: Using Ontologies in Clinical Decision Support Applications

8

ATHENA HTN Advisory

BP targets

Primaryrecommendation

Drugrecommendation

Page 9: Using Ontologies in Clinical Decision Support Applications

9

ATHENA HTN Advisory: More Info

Page 10: Using Ontologies in Clinical Decision Support Applications

10

ATHENA HTN Advisory: Link to evidence base

Page 11: Using Ontologies in Clinical Decision Support Applications

11

EON ontologies

Guideline ontology

Patient information model (generalizes to HL7 RIM)

Generic data types (generalize to HL7 data types)

Medical concept ontology (generalizes to standard terminologies)

Page 12: Using Ontologies in Clinical Decision Support Applications

12

Physician-maintained hypertension knowledge base

Page 13: Using Ontologies in Clinical Decision Support Applications

13

Benefits of ontology-based clinical information systems Separation of declarative domain knowledge and

procedural problem-solving knowledge allow Content experts to maintain knowledge bases Standardization of ontologies that leads to sharing

and interoperability Semantically rich ontologies allow sophisticated

reasoning and decision support e.g., automatic concept classification based on

description logic e.g., detailed drug recommendations based on

computable model of clinical practice guidelines