Artificial intelligence. Expert systems for clinical diagnosis: are they worth the effort?

Modeling the decision-making processes of human experts has been studied by scientists who call themselves psychologists and by scientists who say they are students of artificial intelligence (Al). The psychological research literature suggests that experts' decision-making processes can be adequately captured by simple mathematical models. On the other hand, those in Al who are preoccupied with human expertise maintain that complex computer models, in the form of expert systems, are required to do justice to those same processes. The resultant paradox of simple versus complex decision-making models is investigated here. The relevant literatures in psychology and Al are reviewed and, based on these findings, a resolution of the paradox is offered.

[1]  Paul E. Meehl,et al.  Clinical vs. Statistical Prediction. , 1955 .

[2]  K. R. Hammond.  Probabilistic functioning and the clinical method. , 1955, Psychological review.

[3]  L. R. Goldberg,et al.  The effectiveness of clinicians' judgments; the diagnosis of organic brain damage from the Bender-Gestalt test. , 1959, Journal of consulting psychology.

[4]  P. Hoffman.  The paramorphic representation of clinical judgment. , 1960, Psychological bulletin.

[5]  George S. Sebestyen,et al.  Decision-making processes in pattern recognition , 1962 .

[6]  E. H. Bowman.  Consistency and Optimality in Managerial Decision Making , 1963 .

[7]  K. R. Hammond,et al.  ANALYZING THE COMPONENTS OF CLINICAL INFERENCE. , 1964, Psychological review.

[8]  K. R. Hammond,et al.  SOME METHODOLOGICAL CONSIDERATIONS IN MULTIPLE-CUE PROBABILITY STUDIES. , 1964, Psychological review.

[9]  S. Oskamp.  OVERCONFIDENCE IN CASE-STUDY JUDGMENTS. , 1965, Journal of consulting psychology.

[10]  Nils J. Nilsson,et al.  Learning Machines: Foundations of Trainable Pattern-Classifying Systems , 1965 .

[11]  P. Slovic,et al.  An analysis-of-variance model for the assessment of configural cue utilization in clinical judgment. , 1968, Psychological bulletin.

[12]  L. R. Goldberg.  Simple models or simple processes? Some research on clinical judgments. , 1968, The American psychologist.

[13]  P. Slovic.  Analyzing the expert judge: A descriptive study of a stockbroker's decision process. , 1969 .

[14]  Marvin Minsky,et al.  Perceptrons: An Introduction to Computational Geometry , 1969 .

[15]  Lewis R. Goldberg,et al.  Man versus model of man: A rationale, plus some evidence, for a method of improving on clinical inferences. , 1970 .

[16]  R. Dawes.  A case study of graduate admissions: Application of three principles of human decision making. , 1971 .

[17]  Nils J. Nilsson,et al.  Problem-solving methods in artificial intelligence , 1971, McGraw-Hill computer science series.

[18]  N. Anderson,et al.  Looking for configurality in clinical judgment. , 1972, Psychological bulletin.

[19]  H. Dreyfus.  What Computers Can't Do , 1972 .

[20]  P. Meehl.  Psychodiagnosis: Selected Papers , 1973 .

[21]  R. Dawes,et al.  Linear models in decision making. , 1974 .

[22]  B Kleinmuntz.  The computer as clinician. , 1975, The American psychologist.

[23]  Ebbe B. Ebbesen,et al.  Decision Making and Information Integration in the Courts: The Setting of Bail , 1975 .

[24]  R. Hogarth,et al.  Unit weighting schemes for decision making , 1975 .

[25]  Edward H. Shortliffe,et al.  Computer-based medical consultations, MYCIN , 1976 .

[26]  Antonio Leal,et al.  An Interactive Program Fo Conversational Elicitation of Decision Structures , 1977, IEEE Transactions on Systems, Man, and Cybernetics.

[27]  Timothy D. Wilson,et al.  Telling more than we can know: Verbal reports on mental processes. , 1977 .

[28]  Robyn M. Dawes,et al.  Predictive Models as a Guide to Preference , 1977, IEEE Transactions on Systems, Man, and Cybernetics.

[29]  B. Fischhoff,et al.  Behavioral Decision Theory , 1977 .

[30]  J. Shanteau,et al.  Livestock judges: How much information can an expert use? , 1978 .

[31]  Nils J. Nilsson,et al.  SEMANTIC NETWORK REPRESENTATIONS IN RULE-BASED INFERENCE SYSTEMS1 , 1978 .

[32]  Bruce G. Buchanan,et al.  Dendral and Meta-Dendral: Their Applications Dimension , 1978, Artif. Intell..

[33]  R. Hogarth,et al.  Confidence in judgment: Persistence of the illusion of validity. , 1978 .

[34]  Lawrence M. Fagan,et al.  Antimicrobial selection by a computer. A blinded evaluation by infectious diseases experts. , 1979, JAMA.

[35]  R. Dawes.  Judgment under uncertainty: The robust beauty of improper linear models in decision making , 1979 .

[36]  J. William,et al.  System aids in constructing consultation programs , 1981 .

[37]  Douglas B. Lenat,et al.  Knowledge-based systems in artificial intelligence , 1981 .

[38]  T. Gilovich,et al.  Seeing the past in the present: The effect of associations to familiar events on judgments and decisions. , 1981 .

[39]  P. E. Johnson,et al.  Multimethod study of clinical judgment. , 1982, Organizational behavior and human performance.

[40]  Gevarter,et al.  Overview of Expert Systems , 1982 .

[41]  B Kleinmuntz,et al.  Computational and noncomputational clinical information processing by computer. , 1982, Behavioral science.

[42]  Janice S. Aikins,et al.  Prototypical Knowledge for Expert Systems , 1983, Artif. Intell..

[43]  Chris Naylor.  Build your own expert system , 1983 .

[44]  William J. Clancey,et al.  The Epistemology of a Rule-Based Expert System - A Framework for Explanation , 1981, Artif. Intell..

[45]  Sholom M. Weiss,et al.  Using Empirical Analysis to Refine Expert System Knowledge Bases , 1984, Artif. Intell..

[46]  Satosi Watanabe,et al.  Pattern Recognition: Human and Mechanical , 1985 .