Guidelines recommend that clinicians estimate patient life expectancy from other causes of mortality when making treatment decisions for prostate cancer. However, simple and accurate tools for estimating other-cause life expectancy in men with prostate cancer are lacking. We aimed to develop and validate an accurate, usable prediction model for other-cause mortality in patients with prostate cancer diagnosed in the United States.
Model training was performed using the National Health and Nutrition Examination Survey 1999-2010 including men age > 40 with follow-up through 2014. The model was validated in the Prostate, Lung, Colon, and Ovarian Cancer Screening Trial prostate cancer cohort, which enrolled patients from 1993-2001 with follow-up through 2015. Time-dependent AUC and calibration were assessed in the validation cohort. Analyses were performed to assess algorithmic bias.
The 2,420 patient training cohort had 459 deaths over a median follow-up of 8.8 years among survivors. The final model included 8 predictors: age, education, marital status, diabetes, hypertension, stroke, body mass index, and smoking. It had an AUC of 0.75 at 10 years for predicting other-cause mortality in the validation cohort of 8,220 patients. The final model significantly outperformed the Social Security Administration life tables and showed adequate predictive performance across race, educational attainment, and marital status subgroups. There is evidence of major variability in life expectancy that is not captured by age, with life expectancy predictions differing by 10+ years among patients of the same age.
Using two national cohorts, we have developed and validated a simple and useful prediction model for other-cause mortality for patients with prostate cancer treated in the United States, which will allow for more personalized treatment in accordance with guidelines.
BJU international. 2022 Apr 03 [Epub ahead of print]
Elizabeth C Chase, Alex K Bryant, Yilun Sun, William C Jackson, Daniel E Spratt, Robert T Dess, Matthew J Schipper
Department of Biostatistics, University of Michigan, Ann Arbor., Department of Radiation Oncology, University of Michigan, Ann Arbor., Department of Radiation Oncology, University Hospitals/Case Western Reserve University.