Abstract
Estimating the risk of relapse for breast cancer patients is necessary, since it affects the choice of treatment. This problem involves analysing data of times to relapse of patients and relating them to prognostic variables. Some of the times to relapse will usually be censored.We investigate various ways of using neural network models to extend traditional statistical models in this situation. Such models are better able to model both non-linear effects of prognostic factors and interactions between them, than linear logistic or Cox regression models. With the dataset used in our study, however, the prediction of the risk of relapse is not significantly improved when using a neural network model. Predicting the risk that a patient will relapse within three years, say, is possible from this data, but not when any relapse will happen.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Kalbfleisch JD, Prentice RL. The Statistical Analysis of Failure Time Data. New York, Wiley, 1980
Baxt WG. Use of an artificial neural network for data analysis in clinical decision-making: the diagnosis of acute coronary occlusion. Neur Comp 1990; 2: 480–489
Baxt WG, Skora J. Prospective validation of artificial neural network trained to identify acute myocardial infarction. Lancet 1996; 347: 12–15
Bounds DG, Lloyd PJ, Mathew BG. A comparison of neural network and other pattern recognition approaches to the diagnosis of low back disorders. Neur Networks 1990; 3: 583–591
Lippmann RP, Kukolich L, Shinlan D. Predicting the risk of complications in coronary bypass operations using neural networks. In Advances in Neural Information Processing Systems 7, Tesauro G, Touretzky DS, Leen TK (eds), Cambridge, MA, MIT Press, 1995, pp 1055–1062
Tarassenko L, Whitehouse R, Gasparini G, Harris AL. Neural network prediction of relapse in breast cancer patients. Neur Comput Appl 1996; 4: 105–113
Burke HB, Rosen DB, Goodman PH. Comparing the prediction accuracy of artificial neural networks and other statistical models for breast cancer survival. In Advances in Neural Information Processing Systems 7, Tesauro G, Touretzky DS, Leen TK (eds), Cambridge, MA, MIT Press, 1995; 1063–1067
Ravdin PM, Clark GM. A practical application of neural network analysis for predicting outcome of individual breast cancer patients. Breast Canc Res Trt 1992; 22: 285–293
Akaike H. Prediction and entropy. In A Celebration of Statistics. The ISI Centenary Volume, Atkinson AC, Fienberg SE (eds), New York, Springer-Verlag, 1985, pp 1–24
MathSoft, Inc. S-PLUS system for statistical analysis, based on the S language developed at the (then) AT&T's Bell Laboratories, (now) Lucent Technologies. Marketed by the Data Analysis Products division of MathSoft, Inc, 1996
Venables WN, Ripley BD. Modern Applied Statistics with S-Plus. New York, Springer-Verlag, 1994
Ripley BD. S-Plus package multinom. Available at URL http://www.stats.ox.ac.uk/pub/S, 1994 [S-Plus code for multiple logistic regression]
Gill PE, Murray W, Wright MH. Practical Optimization, London, Academic Press, 1981
Cox DR. Regression models and life-tables (with discussion). J Roy Stat Soc B 1972; 34: 187–220
Fleiss JL. Statistical Methods for Rates and Proportions. New York, Wiley, 1981
Dawid AP. Probability forecasting. In Encyclopedia of Statistical Sciences, vol 7, Kotz S, Johnson NL, Read CB (eds), 7: 210–218. New York, Wiley, 1986
Cleveland WS, Grosse E, Shyu WM. Local regression models. In Statistical Models in S, Chambers JM, Hastie TJ (eds), Pacific Grove, CA, Wadsworth and Brooks/Cole, 1992
Ripley BD. Pattern Recognition and Neural Networks. Cambridge, Cambridge University Press, 1996
Ripley RM. Neural network models for breast cancer prognosis. PhD thesis, University of Oxford, 1998 (Available at http://www.robots.ox.ac.uk/∼ruth)
Gasparini G, Harris AL. Clinical importance of the determination of tumour angiogenesis in breast carcinoma: Much more than a new prognostic tool. J Clinical Oncology 1995; 13: 765–782
Tesauro G, Touretzky DS, Leen TK. (eds) Advances in Neural Information Processing Systems 7. Cambridge, MA, MIT Press, 1995
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Ripley, R.M., Harris, A.L. & Tarassenko, L. Neural network models for breast cancer prognosis. Neural Comput & Applic 7, 367–375 (1998). https://doi.org/10.1007/BF01428127
Issue Date:
DOI: https://doi.org/10.1007/BF01428127