RESUMEN
BACKGROUND: Prostate cancer (PCa) is the most common malignancy seen in men and the second leading cause of cancer-related death in males. The incidence and mortality associated with PCa has been rapidly increasing in China recently. METHODS: Multiple diagnostic models of human PCa were developed based on Taylor database by combining the artificial neural networks (ANNs) to enhance the ability of PCa diagnosis. Genetic algorithm (GA) is used to select feature genes as numerical encoded parameters that reflect cancer, metastatic, or normal samples. Back propagation (BP) neural network and learning vector quantization (LVQ) neural network were used to build different Cancer/Normal, Primary/Metastatic, and Gleason Grade diagnostic models. RESULTS: The performance of these modeling approaches was evaluated by predictive accuracy (ACC) and area under the receiver operating characteristic curve (AUC). By observing the statistically significant parameters of the three training sets, our Cancer/Normal, Primary/Metastatic, and Gleason Grade models' with ACC and AUC can be drawn (97.33%, 0.9832), (99.17%, 0.9952), and (90.48%, 0.8742), respectively. CONCLUSION: These results indicated that our diagnostic models of human PCa based on Taylor database combining the feature gene expression profiling data and artificial intelligence algorithms might act as a powerful tool for diagnosing PCa. Gleason Grade diagnostic models were used as novel prognostic diagnosis models for biochemical recurrence-free survival and overall survival, which might be helpful in the prognostic diagnosis of PCa in patients.