Prognostic model for predicting long-term risk for prostate cancer mortality following a PSA test

Despite the scale of prostate-specific antigen (PSA) testing for prostate cancer (PCa) screening, prediction models do not predicte time-to-event endpoints or adjust for patient life expectancy. Analysis of results of the PCa screening group of the Prostate, Lung, Colorectal, and Ovarian (PLCO) Cancer screening trial resulted in development of a prognostic model predicting long-term risk for prostate cancer mortality following a PSA test, which was validated in a Veterans Affairs (VA) population of patients undergoing PSA testing. The analysis included male patients aged 55 to 77 years in the PLCO PCa screening group (n=33,339) and the VA Healthcare System (n=147,787). The model’s predicted outcome is prostate cancer-specific mortality (PCSM) at a specified time point; predictors included PSA level, family history of PCa, and race. Predictors of other-cause mortality included age, body mass index, smoking status, and presence of hypertension, diabetes, or stroke. In the development cohort, the AUC at 29.5 years from screening was 0.666 compared to 0.643 for a previously validated prostate biopsy model (PBGC; p<0.001). In the validation cohort, the AUC at 20 years form screening was 0.776 for the PLCO model versus 0.749 for the PBCG model (p=0.031). The authors conclude that this PCSM prognostic model may be used to improve interpretation of PSA results.