Abstract
Clinical decision analysis seeks to identify the optimal management strategy by modelling the uncertainty and risks entailed in the diagnosis, natural history, and treatment of a particular problem or disorder. Decision trees are the most frequently used model in clinical decision analysis, but can be tedious to construct, cumbersome to use, and computationally prohibitive, especially with large, complex decision problems. We present a new method for clinical decision analysis that combines the techniques of decision theory and artificial intelligence. Our model uses a modular representation of knowledge that simplifies model building and enables more fully automated decision making. Moreover, the model exploits problem structures to yield better computational efficiency. As an example we apply our techniques to the problem of management of acute deep venous thrombosis.
Full text
PDF
Selected References
These references are in PubMed. This may not be the complete list of references from this article.
- Hillner B. E., Philbrick J. T., Becker D. M. Optimal management of suspected lower-extremity deep vein thrombosis. An evaluation with cost assessment of 24 management strategies. Arch Intern Med. 1992 Jan;152(1):165–175. [PubMed] [Google Scholar]
- Kahn C. E., Jr, Haddawy P. Management of suspected lower-extremity deep venous thrombosis. Arch Intern Med. 1995 Feb 27;155(4):426–426. [PubMed] [Google Scholar]
- Landefeld C. S., McGuire E., Cohen A. M. Clinical findings associated with acute proximal deep vein thrombosis: a basis for quantifying clinical judgment. Am J Med. 1990 Apr;88(4):382–388. doi: 10.1016/0002-9343(90)90493-w. [DOI] [PubMed] [Google Scholar]
- Pauker S. G., Kassirer J. P. Decision analysis. N Engl J Med. 1987 Jan 29;316(5):250–258. doi: 10.1056/NEJM198701293160505. [DOI] [PubMed] [Google Scholar]