Role of Semantic Web Technologies in Managing Knowledge Change and Provenance
Vipul Kashyap1, Alfredo Morales2
[email protected] ; [email protected] 1Clinical Informatics R&D, Partners Healthcare System
2 Cerebra, Inc.
HCLSIG Face to Face Meeting, Cambridge MAJanuary 25, 2006
Outline
• Some definitions
• The Business Problem:— Structured Clinical Documentation in HealthCare
• Example
• Semantics-based approach for Clinical Documentation
• Dependency Propagation and Management
• Conclusions
What does it mean to manage Knowledge Change and Provenance
• There is a close interrelationship between knowledge change and provenance
— What has changed? – Change— Why did it change? – Provenance
• Did someone change it? – Provenance• Did its components change? – Change
— Who changed it? – Provenance
• Significance:— Rapid Knowledge Discovery and Evolution in Healthcare and
Life Sciences
The Business Problem• Difficulty of identifying targeted templates for particular
conditions and diseases
• Inflexibility for documenting unforeseen findings
• Lack of consistency and maintenance of documentation templates as clinical knowledge and content evolves over time.
• Inefficiency, complexity and slow pace of navigating through user interfaces
— leads to decreased overall efficiency for generating complex documents
Example:
Example Instrument
1. Do you know if there any contraindications to fibric acid for this patient? __ Yes __ No
2. Does this patient suffer from gallstones?__ Yes__ No
3. What is the AST Value for this patient? ______ mg/ml?
4. Which of the following range of values does the AST values for this patient apply to? _ < 10 _ [10,20] _ [20,40]
5. Are the liver panel values more than the normal values for this patient? __ Yes __ No
6. If the answer to Question 5 is Yes, then the liver panel values are: __ 2 x Normal __ 3 x Normal
Documentation Ontology
• A Data Collection Item consists of: - A domain (Patient) - A question - An attribute (has_contraindication_to) - A value
• A Data Collection Item can depend on the results of other data collection items
Domain Ontology
Suppose AST values change from 0 AST 40 to 20 AST 40
Bridge – Composition Ontology
Knowledge Change and Provenance
• At each stage, Knowledge Engineer gets notified of:— What has changed?
• The definition of Fibric Acid Contraindication
— Why did it change? • Fibric Acid Contraindication Patient with Abnormal Liver Panel
Abnormal Liver Panel Abnormal AST Change in AST Values
— Who was responsible for the change?• Knowledge Engineer who entered the changed AST values?
• Change in a Clinical Guideline?
The Value Proposition of Semantics
• Managing change and provenance is a very difficult problem
• Semantics can play a crucial role in it:— A reasoner can navigate a semantic model of knowledge
and propagate change
— One can declaratively change the model at any time…
— The reasoner will compute the new changes!
• Configuration v/s coding…. Could lead to huge ROI!