Probabilistic information processing: implementation and evaluation of a Semi-PIP diagnostic system.

Abstract A computer-aided diagnostic system called Semi-PIP which uses subjectively estimated patient attribute-disease relationships and is sensitive to conditional dependencies is described and tested. This model uses the best of four tested methods to subjectively classify data into conditionally independent complexes. Its performance is compared to two models which ignore conditional dependencies, and to three physicians diagnosing on the basis of symptoms, physical signs and laboratory information. Analysis of the results indicates that Semi-PIP is superior to the other computer models, and almost as accurate as the majority physician diagnosis.

[1]  F A Hipona,et al.  Cardiac lymphangiography. A preliminary report on a roentgen study of the cardiac lymphatics in the dog. , 1966, Investigative radiology.

[2]  G. William Walster,et al.  A comparative study of differences in subjective likelihood estimates made by individuals, interacting groups, Delphi groups, and nominal groups☆ , 1973 .

[3]  D. Schum,et al.  Inferences on the basis of conditionally nonindependent data. , 1966, Journal of experimental psychology.

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

[5]  R. Nesbitt,et al.  Persistent urogenital membrane sinus as a clinical entity. , 1968, JAMA.

[6]  Cameron R. Peterson,et al.  Probabilistic information processing systems: Evaluation with conditionally dependent data☆ , 1972 .

[7]  G A Gorry,et al.  Sequential diagnosis by computer. , 2015, JAMA.

[8]  P. Slovic,et al.  Analyzing use of diagnostic signs. , 1971, Investigative radiology.

[9]  J. Overall,et al.  Conditional probability program for diagnosis of thyroid function. , 1963, JAMA.

[10]  J M Vanderplas,et al.  A method for determining probabilities for correct use of Bayes's theorem in medical diagnosis. , 1967, Computers and biomedical research, an international journal.

[11]  D H Gustafson,et al.  Initial evaluation of a subjective Bayesian diagnostic system. , 1971, Health services research.

[12]  W. G. Cochran.  The comparison of percentages in matched samples. , 1950, Biometrika.

[13]  Paul Slovic,et al.  Comparison of Bayesian and Regression Approaches to the Study of Information Processing in Judgment. , 1971 .

[14]  Z. J. Ulehla,et al.  Internal consistency of subjective probabilities. , 1965, Journal of Experimental Psychology.

[15]  Lee Roy Beach,et al.  Combinatorial properties of personal probabilities , 1972 .

[16]  L. Beach,et al.  Man as an Intuitive Statistician , 2022 .

[17]  G. Anthony Gorry.  Strategies for computer-aided diagnosis , 1968 .

[18]  Merilyn Grinnell,et al.  Bayesian predictions of faculty judgments of graduate school success , 1971 .

[19]  Ward Edwards,et al.  Probabilistic Information Processing Systems: Design and Evaluation , 1968, IEEE Trans. Syst. Sci. Cybern..

[20]  Thomas L. Lincoln,et al.  Medical Diagnosis Using Bayes Theorem. , 1967 .

[21]  David H. Gustafson,et al.  Evaluation of probabilistic information processing in medical decision making , 1969 .

[22]  Warner V. Slack,et al.  Subjective Probabilities in Medical Diagnosis , 1969 .

[23]  Homer R. Warner,et al.  A Mathematical Approach to Medical Diagnosis , 1961 .

[24]  G. Anthony Gorry,et al.  Automating Judgmental Decision Making for a Serious Medical Problem , 1971 .