Abstract
The paper describes the heuristic approach to risk analysis taken by ATTENDING, an Artificial Intelligence system designed to critique a physician’s plan of anesthetic management. To critique a physician’s plan, the system must know about the different risks and risk tradeoffs involved in a patient’s management. It must also be able to manipulate this knowledge in a flexible way. The paper discusses the three principles on which ATTENDING’s heuristic approach to risk is based, and also describes how each principle is currently implemented.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Miller PL : ATTENDING: A system which critiques an anesthetic management plan. Proc. Am. Med. Informatics Assoc. Congress 82, San Francisco, May 1982.
Weinstein MC, et al.: Clinical Decision Analysis. Philadelphia: W. B. Saunders, 1980.
Kulikowski C : Artificial intelligence methods and systems for medical consultation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1980, Vo., PAMI-2, No. 5.
Shortliffe EH, Buchanan BG, Feigenbaum EA: Knowledge engineering for medical decision making. A review of computer-based clinical decision aids. Proc. IEEE 1979; 67: 1207–1224.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1982 Electrical and Electronics Engineers, Inc.
About this chapter
Cite this chapter
Miller, P.L. (1982). A Heuristic Approach to Risk Analysis in Computer-Assisted Medical Management. In: Reggia, J.A., Tuhrim, S. (eds) Computer-Assisted Medical Decision Making. Computers and Medicine. Springer, New York, NY. https://doi.org/10.1007/978-1-4612-5108-8_5
Download citation
DOI: https://doi.org/10.1007/978-1-4612-5108-8_5
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4612-9567-9
Online ISBN: 978-1-4612-5108-8
eBook Packages: Springer Book Archive