Independent Research Paper for INFS796

1. CARE MAPS:
DISTRIBUTED SEMANTIC
HEALTHCARE
WORKFLOWS
Daniel Aronne ~ George Mason University ~
2011

2. Objective
 How to provide patients with a seamless
healthcare treatment environment?
 A holistic approach.

3. Healthcare Industry
 A highly dynamic industry in a very complex
environment.
 Multiple stakeholders spanning multiple
organizations and geographical locations:
 Laboratories
 Physicians
 Clinics
 Pharmacies
 Insurance Companies
 Federal Agencies
 The Patient Himself!

4. Healthcare Industry Stakeholders
Pharmaceutical Manufacturers Payers/
Medical Devices Regulators
Biotech Distributor/ Employer
Wholesaler
Other
Payer
Outpatient
LTC
Facilities
Hospitals
Regulatory Physicians
Agency
Integrate
d
Networks
Providers Patients
AHRQ 2007 Annual Conference Presentation: http://www.ahrq.gov/about/annualmtg07/0927slides/juhn/Juhn-contents.html

5. Current Challenges and Issues
 Interaction
 Intra-organizationaland Inter-organizational
 Orchestration vs. choreography
 Integration
 Service discovery and matching
 Adaptability
 Adaptive medical workflows
 Quality of Service (QoS)
 Reliability, availability, scalability, error handling

6. Current Challenges and Issues
 Localization
 Local jurisdiction requirements
 Usability
 How much user interaction?
 Behavioral
A human driven industry
 How much should we automate without human
intervention?

7. Care Maps
 A roadmap of a patient’s journey.
 Consists of a series of steps and decisions
points in the management of a condition.
 Is usually based on medical guidelines, recent
evidence and expert consensus.
 Patient centered.

8. Agent-based system
approach

9. Multi-Agent Systems
 Have been recognized as a technology to
efficiently build complex systems.
 Suitable for describing the coordinating and
negotiating nature of healthcare service
providers and consumers.

10. Multi-Agent Systems
 Previous works have demonstrated the added
values of agent-based systems in healthcare,
and specifically in healthcare workflows [9]:
 Reusability
 Reliability
 Flexibility
 Robustness
 Maintainability
 Adaptability

11. Multi-Agent Systems
 Added values (continued):
 Support the integration of legacy systems
 Tackle the shortcomings of centralized systems
such as:
 performance bottlenecks
 resource limitations
 other kinds of failures

12. Multi-Agent Systems
 Shortcomings:
 Most of the systems are only prototypes.
 Most are not widely deployed in real
environments.
 Further study is required.

13. Decentralized workflow
execution

14. Decentralized Workflow
Execution
 Supports the dynamic nature of the healthcare
industry
 Ad-hoc adaptation to changing conditions at
runtime.
 Run-time process fragmentation and process
migration.

15. Decentralized Workflow
Execution
• Process fragmentation vs process
migration.
Zaplata, Sonja, Kristof Hamann, Kristian Kottke, and Winfried Lamersdorf. "Flexible Execution of Distributed Business
Processes Based on Process Instance Migration." Journal of Systems Integration 1.3 (2010): 3-16.

16. Decentralized Workflow
Execution
 Enhance existing processes with non-intrusive
migration data.
 Non-modifying annotation of process descriptions:
migration meta-model.
 All potential participants have to provide a
compliant interface in order to receive process
descriptions from preceding process engines (e.g.
XPDL, WS-BPEL)
 Support encryption and decryption of process
fragments and/or migration data for security and
privacy purposes.

17. Distributed directory service
(DDS)

18. Distributed Directory Service
 Inspiration from:
 Domain Name System (DNS)
 Namespace hierarchy
 Authoritative servers
 Replication
 P2P protocols (i.e. Bit Torrent)
 Queryrouting
 Network overlays
 No single point of failure, better reliability
 Scalable

20. Semantic Matchmaking
 Match service providers and service
consumers.
 Compute syntactical and semantic similarity
among service capability descriptions.
 Requires use of a semantic model (e.g.
ontology) to describe service descriptions.

21. Proposed framework
A distributed semantic workflow
management, multi-agent system approach

23. Decentralized Directory
Service (DDS):
• Resource and service
discovery.
• Provides support for:
• Semantic querying.
• Federated query.
• Security.
• Solves JADE
centralized DF.

24. Healthcare Entity Agent (HEA):
• Storefront representative of any healthcare
service provider.
• Initiates execution of process instances.
• Allocates process fragments to other healthcare
entities .
• Executes process fragments.
• Can migrate process instances to other entities.
• Interacts with any BPM engine that supports a
standardized workflow definition format (i.e.
XPDL).

25. Broker Agent (BA):
• Semantic matchmaker:
Matches service requests with
service providers.
• Queries local Directory Service
Ontology which contains
semantic service descriptions.
• If no suitable match, requests
the Directory Service Agent to
route his query to other
Directory Services.

26. Directory Service Agent (DSA)
• Storefront for the Directory
Service.
• Handles new Service
Providers registration.
• Propagates newly registered
SPs to other Directory Service
nodes.
• Routes queries to other BA in
the Distributed Directory
Service.

27. User Agent (UA)
• Acts on behalf of a human person
• May be delegated atomic tasks.
• May reside in a desktop computer or in a
mobile device.

28. Future Work
 A prototype to test these concepts.
 Address security and privacy concerns.

29. References
 [1] D. Alexandrou and G. Mentzas. “Research Challenges for Achieving Healthcare Business Process
Interoperability”, in Proceedings of the 2009 International Conference on eHealth, Telemedicine, and
Social Medicine, ETELEMED '09, IEEE Computer Society.
 [2] J. Emanuele and L. Koetter, "Workflow Opportunities and Challenges in Healthcare", in 2007 BPM &
Workflow Handbook, 2007.
 [3] Song, X., Hwong, B., Matos, G., Rudorfer, A., Nelson, C., Han, M., Girenkov, A., “Understanding
Requirements for Computer-aided Healthcare Workflows: Experience and Challenges”, in Proceeding of
the 28th international conference on Software engineering, ICSE’06, ACM Press.
 [4] Wei Tan, Yushun Fan, "Decentralized Workflow Execution for Virtual Enterprises in Grid
Environment," Grid and Cooperative Computing Workshops, International Conference on, pp. 308-314,
Fifth International Conference on Grid and Cooperative Computing Workshops, 2006
 [5] J. Dang, A. Hedayati, K. Hampel, and C. Toklu. “An ontological knowledge framework for adaptive
medical workflow”. Journal of Biomedical Informatics, 41(5):829–836, October 2008.
 [6] Z. Maraikar. “Resource and service discovery for mobile agent platforms”. Master’s thesis,
Department of Computer Science, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands, August
2006
 [7] Zaplata, Sonja, Kristof Hamann, Kristian Kottke, and Winfried Lamersdorf. "Flexible Execution of
Distributed Business Processes Based on Process Instance Migration." Journal of Systems Integration
1.3 (2010): 3-16. Print.
 [8] Huser, Vojtech, Luke Rasmussen, and Justin Starren. "Representing Clinical Processes in XML
Process Definition Language (XPDL)." Web.
 [9] Isern, David, David Sanchez, and Antonio Moreno. "Agents Applied in Health Care: A Review."