Prediction of prostate capsule penetration using neural networks

Prediction is a straight forward application of neural networks (NN). The problem of prostate cancer evolution prediction is approached in this paper using NN. The original database contained 650 records of patients, which underwent radical prostatectomy for prostate cancer. The NN variables were the parameters with the highest prognostic value selected and preprocessed from the original database. Different NN architectures and NN parameters have been tested. The NN performance has been compared with the most widely used prediction statistical method, the logistic regresion. All NN models performed better than the logistic regression. The best obtained global prediction of 96.94% is better than the results of similar experiments available in literature. The NN prediction performance might be improved, because, in our opinion, its limit is given by the relatively small number of cases and the methods of collecting data.