Predicting the outcome of prostate biopsy in screen-positive men by a multilayer perceptron network

Objectives. To assess whether an artificial neural network (multilayer perc eptron, MLP) and logistic regression (LR) could eliminate more false-positi ve prostate-specific antigen (PSA) results than the proportion of free: PSA in a prostate cancer screening. Methods. MLP and LR models were constructed on the basis of data on total P SA, the proportion of free PSA, digital rectal examination (DRE), and prost ate volume from 656 consecutive men (aged 55 to 67 years) with total serum PSA concentrations of 4 to 10 ng/mL in the randomized population-based pros tate cancer screening study in Finland. The MLP and LR models were validate d using the "leave-one-out" method. Results. Of the 656 men, 23% had prostate cancer and 77% had either normal prostatic histology or a benign disease. At a 95% sensitivity level, 19% of the false-positive PSA results could be eliminated by using the proportion of free PSA versus 24% with the LR model and 33% with the MLP model (P < 0 .001). At 80% to 99% sensitivity levels, the accuracy of the MLP and LR mod els was significantly higher than that of the proportion of free PSA. At 89 % to 99% sensitivities, the accuracy of the MLP was higher than that of LR (P less than or equal to 0.001). Conclusions. At clinically relevant sensitivity levels, the MLP and LR mode ls based on total PSA, the proportion of free PSA, DRE, and prostate volume could reduce the number of unnecessary biopsies significantly better than the proportion of free PSA alone in men with total PSA levels in the range 4 to 10 ng/mL. UROLOGY 56: 418-422, 2000. (C) 2000, Elsevier Science Inc.