On the misuses of artificial neural networks for prognostic and diagnostic classification in oncology

Stat Med. 2000 Feb 29;19(4):541-61. doi: 10.1002/(sici)1097-0258(20000229)19:4<541::aid-sim355>3.0.co;2-v.

Abstract

The application of artificial neural networks (ANNs) for prognostic and diagnostic classification in clinical medicine has become very popular. In particular, feed-forward neural networks have been used extensively, often accompanied by exaggerated statements of their potential. In this paper, the essentials of feed-forward neural networks and their statistical counterparts (that is, logistic regression models) are reviewed. We point out that the uncritical use of ANNs may lead to serious problems, such as the fitting of implausible functions to describe the probability of class membership and the underestimation of misclassification probabilities. In applications of ANNs to survival data, further difficulties arise. Finally, the results of a search in the medical literature from 1991 to 1995 on applications of ANNs in oncology and some important common mistakes are reported. It is concluded that there is no evidence so far that application of ANNs represents real progress in the field of diagnosis and prognosis in oncology.

MeSH terms

  • Decision Support Techniques*
  • Diagnostic Techniques and Procedures
  • Humans
  • Logistic Models
  • Models, Statistical*
  • Neoplasms / diagnosis*
  • Neoplasms / mortality*
  • Neural Networks, Computer*
  • Probability
  • Prognosis
  • Survival Analysis