Abstract
Optimization for diagnostic recognition rate was performed for subsets of symptoms of various sizes. The diagnostic problem was the recognition and identification of thyroid diseases. Unbiased evaluation of performance was obtained and the extent of the bias in other evaluation methods was determined. Interdependence of symptoms was shown to be a negligible nuisance in the application of Bayesian inference to the present data. An optimal size of optimized subsets of symptoms was observed. A comparison with sequential diagnosis shows that the two procedures are different, although theyare related, and that the optimality of subsets is sensitive to departures from their composition.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
J. A. Anderson and J. A. Boyle, “Computer diagnosis: statistical aspects,”Brit, Med. Bull. 24:230–235 (1968).
N. T. J. Bailey, “Probability methods of diagnosis based on small samples,” inMathematics and Computer Sciences in Biology and Medicine (H.M.S.O., London, 1965).
A. Bouckaert, “Computer diagnosis of goiters. III—Optimal subsymptomatoiogies,”J. Chron. Dis. 24:321–327 (1971).
A. Bouckaert,“Computer diagnosis of goiters. I—Classification and differential diagnosis,”J. Chron. Dis. 24:299–310 (1971).
A. Bouckaert, J. De Plaen, J. A. Kapita, and S. Ditu, “Statistical analysis of symptoms for the differential diagnosis of goiters,”Ann. Soc. Belge Med. Trop. 52:113–126 (1972).
F. Burbank, “A computer diagnostic system for the diagnosis of prolonged and undifferentiating liver diseases,”Amer. J. Med. 46:401–415 (1969).
M. F. Collen, L. Rubin, and L. Davis,“Computers in multiphasic screening,” inComputers in Biomedical Research, Vol. III (Academic Press, New York, 1965).
J. L. Fleiss, R. L. Spitzer, J. Cohen, and J. Endicott, “Three computer diagnosis methods compared,”Arch. Gen. Psychiat. 27:643–649 (1972).
J. C. Horrocks, A. P. McCann, J. R. Staniland, D. J. Leaper, and F. T. de Dombal, “Computer-aided diagnosis: description of an adaptable system, and operational experience with 2034 cases,”Brit. Med.J. 2:5–9 (1972).
L. Kanal and B. Chandrasekaran, “On dimensionality and sample size in statistical pattern recognition,”Pat. Recog. 3:225–234 (1971).
S. Koller, J. Michaelis, and E. Scheldt, “Untersuchungen an einem diagnostischen Simulationsmodell,”Meth. Inform. Med. 11:213–227 (1972).
P. A. Lachenbruch, “Estimation of error rates in discriminant analysis,” Ph.D. dissertation, UCLA., Los Angeles (1965).
J. Michaelis, “Zur Anwendung der Diskriminanzanalyse für die medizinische Diagnos-tik,” Habilitationsschrift, Medizinische Fakultät, Mainz (1972).
D. H. Moore, “Evaluation of five discrimination procedures for binary variables,”J. Amer. Stat. Ass. 68:399–404 (1973).
J. F. Mount and J. W. Evans, “Computer-aided diagnosis. A simulation study,” inFifth I.B.M. Symposium (Endicott, New York, 1963).
R. A. Nordyke, C. A. Kulikowski, and C. W. Kulikowski, “A comparison of methods for the automated diagnosis of thyroid dysfunction,”Comput. Biomed. Res. 4:374–389 (1971).
C. A. Nugent, H. R. Warner, J. T. Dunn, and E. H. Tyler, “Probability theory in the diagnosis of Cushing's syndrome,”J. Clin. Endocrin. 24:621–627 (1964).
P. Scheinok, “Symptom diagnosis, Bayes's theorem and Bahadur's distribution,”Biomed. Comput. 3:17–28 (1972).
P. A. Scheinok and J. A. Rinaldo, “Symptom diagnosis: optimal subsets for upper abdominal pain,”Comput. Biomed. Res. 1:221–236 (1967).
P. A. Scheinok and J. A. Rinaldo, “Symptom diagnosis: a comparison of mathematical models related to upper abdominal pain,”Comput. Biomed. Res. 1:475–489 (1968).
A. W. Templeton, C. Jansen, J. Lehr, and R. Hufft, “Solitary pulmonary lesions,”Radiology 89:605–613 (1967).
J. M. Vanderplas, “A method for determining probabilities for correct use of Bayes's theorem in medical diagnosis,”Comput. Biomed. Res. 1:215–220 (1967).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Bouckaert, A. Computer diagnosis of goiters. The optimal size of optimal subsymptomatologies. International Journal of Computer and Information Sciences 3, 345–362 (1974). https://doi.org/10.1007/BF00978979
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF00978979