Prioritizing Data Quality Governance for AI in Prostate Cancer: A Methodological Proof-of-Concept Using Neural Networks for Risk Stratification

Background: An accurate D’Amico risk stratification is mandatory for prostate cancer (PCa) management. The purpose of this proof-of-concept study was to establish a methodological framework of integrating validated clinical nomograms with strict data-quality governance in order to generate reliable artificial neural networks (ANN), even when the sample is small. Methods: We performed a retrospective analysis of a curated cohort of 49 patients from one center. A multilayer perceptron (MLP) was trained using 11 variables, including the ISUP biopsy grade and Briganti nomogram. Model development was guided by a proactive data-quality protocol based on FAIR principles, with stringent checks for accuracy, consistency and validity to ensure data were “AI-ready”. A sensitivity analysis was conducted on three data partitioning scenarios (20/80, 34/66 and 39/61). Results: From a starting pool of 76 patients, the FAIR-based data governance architecture was applied to create a highly selected cohort of 49 patients. A multilayer perceptron (MLP) trained on this “AI-ready” dataset achieved a mathematically perfect but clinically uninterpretable discrimination (AUC 1.000) for High vs. Intermediate risk groups on a small internal test set (N=9 for the 20/80 split). However, this complete accuracy is a best-case scenario reflecting the high data quality, not proof of generalizable clinical utility, as the large confidence interval (66.4-100%) and the requirement to exclude instances with unusual attributes for model validation (as described in the methods) highlight. Conclusions: The main contribution of this proof-of-concept study is the effective illustration of a strict, repeatable data governance approach for producing “AI-ready” urological datasets. Although the MLP demonstrated a robust internal signal for risk discrimination, its flawless accuracy is an ideal, non-generalizable situation. The most important deliverable that needs external validation is the framework, not the model’s performance metrics.