Abstract
BACKGROUND: Limited evidence exists on the diagnostic performance of Artificial Intelligence (AI)-assisted Simplified Prostate Imaging Reporting and Data System version 2.1 (S-PI-RADS v2.1) combined with quantitative MRI parameters for detecting clinically significant prostate cancer (csPCa). PURPOSE: To develop and validate a nomogram incorporating AI-assisted S-PI-RADS v2.1 (based on biparametric MRI [bpMRI]) and R2* mapping for csPCa prediction. METHODS: This prospective study enrolled 345 patients grouped by pathology: non-csPCa with benign prostatic hyperplasia (n = 230) and csPCa (n = 115). Clinical (age, body mass index [BMI], prostate-specific antigen [PSA], free PSA) and imaging parameters (prostate volume [PV], S-PI-RADS score, R2*) were analyzed. Independent predictors were identified via logistic regression. A nomogram was developed using R software with the DynNom package (Version 2.0) and validated (1000 bootstrap iterations), with performance assessed by area under the curve (AUC), calibration, decision curve analysis (DCA), and DeLong test (p < 0.05 significant). RESULTS: Independent csPCa predictors included BMI, PSA ≥ 10 ng/mL, PV, S-PI-RADS scores 4-5, and R2* (all p < 0.05). The full model (BMI + PSA + PV + S-PI-RADS + R2*) showed superior discrimination (AUC = 0.915) versus the baseline model (AUC = 0.891, p = 0.008), with 85.2% sensitivity and 80.9% specificity. Internal validation was robust (C-index = 0.884). DCA confirmed clinical utility. An interactive nomogram was deployed (https://aiguangyong2025.shinyapps.io/dynnomapp/). CONCLUSION: The AI-enhanced nomogram integrating clinical and multiparametric MRI data accurately predicts csPCa noninvasively, with R2* significantly improving performance. This tool facilitates personalized clinical decision-making.