The application of the nomogram model based on ADC histogram features in predicting clinically significant prostate cancer

Objectives This study aimed to develop a nomogram model using ADC histogram features to predict clinically significant prostate cancer (CSPCa). Methods A retrospective analysis was conducted on 283 patients with suspected prostate cancer admitted to the Urology Department of Jiangnan University Affiliated Central Hospital from January 2019 to June 2024. Patients were randomly divided into a training set (70%, 198 cases) and an internal validation set (30%, 85 cases). Key features were selected through univariate analysis and LASSO regression, and a predictive model was further constructed using univariate and multivariate Logistic regression analysis. The validity of the model was assessed through ROC curves, calibration curves, and decision curve analysis. Results The study found that ADC_CoeffOfVar (odds ratio OR = 1.01, P = 0.034) and ADC_entropy (OR = 1.00, P < 0.001) are independent predictors for CSPCa. The nomogram model constructed based on these factors showed good predictive performance in both the training set (AUC = 0.844) and the internal validation set (AUC = 0.765). Calibration curve analysis showed that the model's predictions were highly consistent with actual observations, and decision curve analysis (DCA) further confirmed the net clinical benefit of the model in clinical decision-making. Conclusion The nomogram model constructed based on ADC histogram features not only provides a non-invasive tool for preoperative risk assessment but also has potential for practical clinical application.