Intention-based Expressions in GASTINE

Summary

Objectives: 1) To evaluate the design of the framework for computerized intention-based clinical practice guidelines; 2) to implement runtime features such as plan recognition and backtracking.

Method: To evaluate the design, we implemented the heart failure guideline into GASTINE, a tool for representing and executing intention-based clinical guidelines.

Result: Description of the current implementation of intention-based expressions in GASTINE and analysis of some generic shortcomings. Explanation of how these shortcomings are addressed. Presentation of how plan recognition and backtracking work and how they improve the system.

Conclusion: The improved guideline system is rather flexible, i.e., it allows deviations from the guideline as long as they are in the spirit of the guideline. The recognition of actions as intended by the users facilitates a flexible decision support system. The intentions are used to explain why certain actions were suggested. Therefore it is assumed that showing the intention behind suggested actions provides a better insight into why these actions are advised.

Keywords

Decision support system - computerized guidelines - intention - goal

• References

• 1 Woolf SH. et al. Clinical guidelines: potential benefits, limitations, and harms of clinical guidelines. BMJ 1999; 318 7182 527-530.
• 2 Martens JD, Werkhoven MJ, Severens JL, Winkens RA. Effects of a behaviour independent financial incentive on prescribing behaviour of general practitioners. J Eval Clin Pract 2007; 13 (Suppl. 03) 369-373.
• 3 Cabana MD. et al. Why don’t physicians follow clinical practice guidelines? A framework for improvement. JAMA 1999; 282 (Suppl. 15) 1458-1465.
• 4 Burgers JS. et al. Characteristics of high-quality guidelines: evaluation of 86 clinical guidelines developed in ten European countries and Canada. Int J Technol Assess Health Care 2003; 19 (Suppl. 01) 148-157.
• 5 Patel VL. et al. Representing clinical guidelines in GLIF: individual and collaborative expertise. J Am Med Inform Assoc 1998; 5 (Suppl. 05) 467-483.
• 6 Gillois P. et al. From paper-based to electronic guidelines: application to French guidelines. Medinfo 2001; 10 Pt 1 196-200.
• 7 Shahar Y. Automated Support to Clinical Guidelines and Care Plans: The Intention-Oriented View. 2002 (cited 2008, Feb 27). Available from: openclinical.org/docs/int/briefingpapers/shahar.pdf
• 8 de Clercq PA. et al. Design and implementation of a framework to support the development of clinical guidelines. Int J Med Inform 2001; 64 2–3 285-318.
• 9 Latoszek-Berendsen A. et al. With good intentions. Int J Med Inform 2007; 76 (Suppl. 03) 440-446.
• 10 Dictionary (cited 2008, Feb 27). Available from: www.dictionary.com
• 11 de Clercq PA, Hasman A, Blom JA, Korsten HH. The application of ontologies and problem-solving methods for the development of shareable guidelines. Artif Intell Med 2001; 22 (Suppl. 01) 1-22.
• 12 Winikoff M. et al. Declarative and Procedural Goals in Intelligent Agent Systems. 2002 Toulouse. France: April 22-25 2002
• 13 Musen MA, Gennari JH, Eriksson H, Tu SW, Puerta AR. PROTEGE-II: computer support for development of intelligent systems from libraries of components. Medinfo 1995; 8 Pt 1: 766-770.
• 14 Shahar Y. et al. A Task-Specific Ontology for the Application and Critiquing of Time-Oriented Clinical Guidelines. Lecture Notes In Computer Science Proceedings of the 6th Conference on Artificial Intelligence in Medicine in Europe. 1997; 1211: 51-61.
• 15 Sips RJ, Braun L, Roos N. Enabling protocol-based medical critiquing. Stud Health Technol Inform 2006; 124: 471-476.
• 16 Johnson PD, Tu S, Booth N, Sugden B, Purves IN. Using scenarios in chronic disease management guidelines for primary care. Proc AMIA Symp 2000; pp 389-393.
• 17 Marcos M, Berger G, van Harmelen F, ten Teije A, Roomans H, Miksch S. Using critiquing for improving medical protocols: harder than it seems. In: Proc of the 8th European Conference on Artificial Intelligence in Medicine (AIME-2001) 2001. pp 431-441.
• 18 Shahar Y, Musen M. Plan recognition and revision in support of guideline-based care. Working notes of the AAAI Spring Symposium on Representing Mental States and Mechanisms 1995 pp 118-126.