Prediction of individual patient outcome in cancer: comparison of artificial neural networks and Kaplan--Meier methods.

摘要: BACKGROUND There is a great need for accurate treatment and outcome prediction in cancer. Two methods prediction, artificial neural networks Kaplan– Meier plots, have not, to the authors' knowledge, been compared previously. METHODS This review compares advantages disadvantages of use Kaplan–Meier curves cancer. RESULTS Artificial are useful individual patients with cancer because they as best traditional statistical methods, able capture complex phenomena without priori can be reduced simpler model if not complex. plots limited accuracy require partitioning variables, cutting continuous variables into discrete pieces, only handle one or two effectively. CONCLUSIONS Artificial an efficient method that utilizes all available powerful prognostic factors maximizes predictive accuracy. Use predictions discouraged serious technical limitations low Cancer 2001;91:1643–6. © 2001 American Society.