Abstract
The introduction of computer-directed secondary testing techniques into a Multiphasic Health Testing System will bring about a need for on-line classification of patients. This paper discusses one method for classifying patients by means of their responses to a medical history questionnaire. The questionnaire data are processed through a trainable pattern classifer which uses a linear discriminant function. The algorithm selected for training purposes is based upon a fixed-increment error correction scheme and is a function of a predetermined maximum likelihood ratio value.
The accuracy of the pattern classifier was tested by means of published questionnaire data relating to two different disease categories. Preliminary results indicate that the pattern classifier can be trained to a high degree of accuracy (>90%) and that the savings in computer storage space for this classification approach is significant.
Similar content being viewed by others
References
Collen, M. F. Machine diagnosis from a multiphasic screening program.5th IBM Medical Symposium, Endicott, NY 1963, Pp. 131–153.
Collen, M. F., Rubin, L. Neyman, J., Dantzig, G. B., Baer, R. M., andSiegelaub, A. B. Automated multiphasic screening and diagnosis.American Journal of Public Health 196454, 741–750.
Henderson, C. A study of automation in health screening systems. M.S. thesis, UCLA, 1969.
Minsky, M., andPapert, S. Perceptrons, Cambridge, MA: MIT Press, 1969.
Nilsson, N. J. Learning machines. New York: McGraw-Hill, 1965.
Rubin, L., Collen, M. F., andGoldman, G. E. Frequency decision theoretical approach to automated medical diagnosis. InProceedings of the fifth Berkeley symposium on mathematical statistics and probability. Berkeley, CA: University of California Press, 1967. Vol. IV, pp. 867–886.
Thorner, R. M., andRemein, Q. R. Principles and procedures in the evaluation of screening for disease.Public Health Monograph, No. 67. Washington, DC: Department of Health, Education and Welfare, 1961.
Widrow, B., andHoff, M. E. Adaptive switching circuits. Technical Report, SU-SEL-TR-1553-1. Stanford, CA: Stanford Electronics Laboratory, Stanford University, 1960.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Henderson, C. A trainable pattern classifier for medical questionnaires. Ann Biomed Eng 1, 115–133 (1972). https://doi.org/10.1007/BF02363422
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02363422