Brought to you by EarthWeb
IT Library Logo

Click Here!
Click Here!

Search the site:
 
EXPERT SEARCH -----
Programming Languages
Databases
Security
Web Services
Network Services
Middleware
Components
Operating Systems
User Interfaces
Groupware & Collaboration
Content Management
Productivity Applications
Hardware
Fun & Games

EarthWeb Direct EarthWeb Direct Fatbrain Auctions Support Source Answers

EarthWeb sites
Crossnodes
Datamation
Developer.com
DICE
EarthWeb.com
EarthWeb Direct
ERP Hub
Gamelan
GoCertify.com
HTMLGoodies
Intranet Journal
IT Knowledge
IT Library
JavaGoodies
JARS
JavaScripts.com
open source IT
RoadCoders
Y2K Info

Previous Table of Contents Next


Chapter 32
Expert Systems in Medicine

Young Moon Chae


CONTENTS

1. Introduction
2. Historical Account
3. Methodologies
3.1. Bayesian Statistical Approaches
  3.2. Rule-Based Reasoning
  3.3. Neural Network
  3.4. Case-Based Reasoning
  3.5. Object-Oriented Programming
4. The Status of Applications Research
4.1. INTERNIST/CADUCEUS: An Expert System in Internal Medicine
  4.2. MYCIN: An Expert System in Blood Infections
  4.3. PUFF: An Expert System in Pulmonary Disorders
  4.4. QMR: A Medical Diagnostic Expert System
  4.5. EEG Analysis System
  4.6. Other Expert Systems Developed in the 1990s
5. Research Issues
5.1. Selecting a Medical Domain
  5.2. Knowledge Acquisition and Representation
  5.3. Validation and Verification
  5.4. Ethical and Legal Considerations
  5.5. Acceptability Issues
6. Future Trends
6.1. Processing of Temporal Knowledge
  6.2. System Integration
  6.3. System Evaluation
References
Appendix: Medical Expert Systems Developed from 1992 to 1996

I. INTRODUCTION

This chapter reviews the research on expert systems designed as aids to medical decision-making. Because complex medical decisions are often made when major uncertainties are present and when the stakes are extremely high, expert systems are ideally suited for decision analysis. Over the last 30 years, many medical expert systems have been developed. Motivations for the development of expert systems in medicine have been numerous. Assisting physicians in making diagnoses and treatment recommendations is the most commonly found application of expert systems in medicine. A physician may have knowledge of most diseases, but, due to the extensive number of diseases, a physician could benefit from the support provided by an expert system to quickly isolate the disease. Specifically, the goals of developing expert systems for medicine are as follows (Shortliffe et al., 1979):

  1. To improve the accuracy of clinical diagnosis through approaches that are systematic, complete, and able to integrate data from diverse sources
  2. To improve the reliability of clinical decisions by avoiding unwarranted influences of similar but not identical cases
  3. To improve the cost efficiency of tests and therapies by balancing the expenses of time, inconvenience against benefits, and risks of definitive actions
  4. To improve our understanding of the structure of medical knowledge, with the associated development of techniques for identifying inconsistencies and inadequacies in that knowledge
  5. To improve our understanding of clinical decision-making, in order to improve medical teaching and to make the system more effective and easier to understand

In medical diagnosis, the exhaustive nature of problem-solving in expert systems to ensure that remote possibilities are not overlooked is important (Barr and Feigenbaum, 1982). Often, the very codification of expertise in suitable form for an expert systems is an illuminating and valuable part of the expert systems development. Furthermore, since the nature of the problem in medicine is not sufficiently understood, large amounts of domain-specific knowledge have to be represented and reasoned with.

Medical treatment decisions are another prime area for applying expert systems. This is so because such decisions must typically be made by patients and their physicians at a point in the diagnostic process that has produced a relatively stable determination of the patient's problem and where specific treatment or more invasive testing options are being considered.

An expert system should be used in medical practice only if it improves the quality of care at an acceptable cost in time or money, or if it maintains the existing standard of care at a reduced cost in time or money. Miller et al. (1985) defined improved quality of care by one or more of the following criteria: improved diagnositc accuracy; improved therapeutic results; an improved sense of the patients well-being; easier and more rapid access to patient information via better record-keeping systems; and a better representation of facts in medical records and better documentation of the reasons for the physicians' actions. These criteria may be used in evaluating medical expert systems when they are applied in a clinical setting.

The development of medical expert systems brings with it many formidable technical, behavioral, legal, and ethical problems that must be addressed by the researchers in this field. These include acquiring and representing medical knowledge, validating the systems, getting physicians and patients to accept them, and deciding the responsibility for clinical decisions made with the help of these systems. This chapter reviews historical accounts of expert systems in medicine, key techniques, applications, research issues, and future trends of medical expert systems.


Previous Table of Contents Next

footer nav
Use of this site is subject certain Terms & Conditions.
Copyright (c) 1996-1999 EarthWeb, Inc.. All rights reserved. Reproduction in whole or in part in any form or medium without express written permission of EarthWeb is prohibited. Please read our privacy policy for details.