Developing a diagnostic model for predicting prostate cancer: a retrospective study based on Chinese multicenter clinical data

Abstract

The overdiagnosis of prostate cancer (PCa) caused by nonspecific elevation serum prostate-specific antigen (PSA) and the overtreatment of indolent PCa have become a global problem that needs to be solved urgently. We aimed to construct a prediction model and provide a risk stratification system to reduce unnecessary biopsies. In this retrospective study, clinical data of 1807 patients from three Chinese hospitals were used. The final model was built using stepwise logistic regression analysis. The apparent performance of the model was assessed by receiver operating characteristic curves, calibration plots, and decision curve analysis. Finally, a risk stratification system of clinically significant prostate cancer (csPCa) was created, and diagnosis-free survival analyses were performed. Following multivariable screening and evaluation of the diagnostic performances, a final diagnostic model comprised of the PSA density and Prostate Imaging-Reporting and Data System (PI-RADS) score was established. Model validation in the development cohort and two external cohorts showed excellent discrimination and calibration. Finally, we created a risk stratification system using risk thresholds of 0.05 and 0.60 as the cut-off values. The follow-up results indicated that the diagnosis-free survival rate for csPCa at 12 months and 24 months postoperatively was 99.7% and 99.4%, respectively, for patients with a risk threshold below 0.05 after the initial negative prostate biopsy, which was significantly better than patients with higher risk. Our diagnostic model and risk stratification system can achieve a personalized risk calculation of csPCa. It provides a standardized tool for Chinese patients and physicians when considering the necessity of prostate biopsy.

Protocol for SNOTOB study: radical prostatectomy without prostate biopsy following18F-PSMA-1007 PET/CT based on a diagnostic model: a single-centre, single-arm, open-label study

“…Recently, we made some updates to this model and an online dynamic nomogram was created (https://ustcprostatecancerprediction.shinyapps.io/ dynnomapp/). 13 We found when the risk probability of the patients reaches 0.60, they are extremely likely to be diagnosed as clinically significant PCa (csPCa). If we set the cut-off value 0.60 as diagnostic criteria for csPCa diagnosis, the specificities and true positive rates are greater than 90% and 80%, respectively.…”