Breast Cancer Research and Treatment

, Volume 22, Issue 3, pp 285–293 | Cite as

A practical application of neural network analysis for predicting outcome of individual breast cancer patients

  • Peter M. Ravdin
  • Gary M. Clark


It has been previously shown that Neural Networks can be trained to recognize individual breast cancer patients at high and low risk for recurrent disease and death. This paper expands on the initial investigation and shows that by coding time as one of the prognostic variables, a Neural Network can use censored survival data to predict patient outcome over time. In this demonstration a Neural Network was trained, tested, and validated using censored survival data from a group of 1373 patients with node-positive breast cancer. The Neural Network method predicted patient outcome as accurately as Cox Regression modeling. The final Neural Network model can be presented with a patient's prognostic information and make a series of predictions about probability of relapse at different times of follow-up, allowing one to draw survival probability curves for individual patients.

Key words

artificial intelligence breast cancer neural networks prognostic factors 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Gorman RP, Sejnowski TJ: Analysis of hidden units in a layered network trained to classify Sonar targets. Neural Networks 1:75–89, 1988.Google Scholar
  2. 2.
    O'Neill MC: Training back-propagation neural networks to define and detect DNA-binding sites. Nucleic Acids Res 19:313–318, 1991.Google Scholar
  3. 3.
    Qian N, Sejnowski TJ: Predicting the secondary structure of globular proteins using neural network models. J Mol Biol 202:865–884, 1988.Google Scholar
  4. 4.
    Sejnowski TJ, Rosenberg CR: Net talk: A parallel network that learns to read aloud. Technical Report JHU/eecs-86-01. The Johns Hopkins University, 1986.Google Scholar
  5. 5.
    Reibnegger G, Weiss G, Werner-Felmayer G, Judmaier G, Wachter H: Neural networks as a tool for utilizing laboratory information: Comparison with linear discriminant analysis and with classification and regression trees. Proc Natl Acad Sci USA 88:11426–11430, 1991.Google Scholar
  6. 6.
    Rosenblatt T: Principles of Neurodynamics. Spartan Books, New York, 1969.Google Scholar
  7. 7.
    Rumelhart DE, Hinton GE, Williams RJ: Learning representations by back propagating errors. Nature 323: 533–536, 1986.Google Scholar
  8. 8.
    White H: Learning in artificial neural networks: a statistical approach. Neural Comput 1:425–464, 1989.Google Scholar
  9. 9.
    Ravdin PM, Clark GM, Hilsenbeck SG, Owens MA, Vendely P, Pandian MR, McGuire WL: Demonstration that breast cancer recurrence can be predicted by Neural Network Analysis. Breast Cancer Res Treat 21:47–53, 1992.Google Scholar
  10. 10.
    Ravdin PM, Clark GM, Hough JJ, Pounds G, Owens MA, McGuire WL: The use of Neural Networks to interpret DNA flow cytometric histograms. Proc Am Assoc Cancer Res 32:28, 1992.Google Scholar
  11. 10.
    Cox DR: Regression models and life tables. J R Stat Soc [B] 34:187–220, 1972.Google Scholar
  12. 11.
    Grossberg S: Nonlinear neural networks: principles mechanisms, and architectures. Neural Networks 1: 17–61, 1988.Google Scholar

Copyright information

© Kluwer Academic Publishers 1992

Authors and Affiliations

  • Peter M. Ravdin
    • 1
  • Gary M. Clark
    • 1
  1. 1.Medicine/OncologyUniversity of Texas Health Science Center at San AntonioSan AntonioUSA

Personalised recommendations