Neural network analysis of clinicopathological and molecular markers in bladder cancer

Purpose: To evaluate retrospectively the ability of an artificial neural ne twork (ANN) to predict bladder cancer recurrence within 6 months of diagnos is and stage progression in patients with Ta/T1 bladder cancer, and 12-mont h cancer-specific survival in patients with T2-T4 bladder cancer. Materials and Methods: Data were analyzed using a NeuralWorks Professional II/Plus software package. The input neural data consisted of clinicopatholo gical and molecular characteristics. Distinct patient groups were used for the prediction of stage progression and tumor recurrence in Ta/T1 bladder c ancers, and 12-month cancer-specific survival for patients with T2-T4 tumor s. ANN predictions were compared with those of four consultant urologists. Results: The accuracy of the neural network in predicting stage progression and recurrence within 6 months for Ta/T1 tumors and 12-month cancer-specif ic survival for T2-T4 cancers was 80%, 75% and 82% respectively; with corre sponding figures for clinicians being 74%, 79% and 65%. On restricting the validation subset to patients with T1G3 tumors in relation to stage progres sion, the sensitivity of the ANN analysis increased to 100% with a specific ity of 78% and an overall accuracy of 82%. The performance of the ANN in pr edicting stage progression in T1G3 tumors was significantly higher than tha t of clinicians (p = 0.25 for the ANN and p = 0.008 for clinicians, McNemar test). Conclusions: Data analysis using an ANN has been shown to be a useful adjun ct in predicting outcomes in patients with bladder cancer and out-performs clinicians' predictions of stage progression in the high risk group of pati ents with T1G3 disease.