This study aims to identify independent risk factors associated with suicide after a prostate cancer diagnosis and develop a suicide risk prediction model to optimize individualized risk assessment and intervention strategies.

Using data from the Surveillance, Epidemiology, and End Results (SEER) database, we systematically analyzed mortality trends among prostate cancer patients diagnosed between 2010 and 2021, utilizing the standardized mortality ratio (SMR). A total of 404,120 eligible patients were randomly assigned to training and validation cohorts at a 7:3 ratio. A Cox proportional hazards model was used to identify independent predictors of suicide, based on which a nomogram prediction model was developed. Model performance was evaluated using the concordance index (C-index), receiver operating characteristic (ROC) curves, and calibration curves to assess its stability and accuracy.

A total of 475,139 prostate cancer patients were included, and a systematic analysis of mortality trends was conducted. The results indicated that the first six months after diagnosis represented the highest-risk period for suicide (SMR = 26.007, 95% CI: 19.303 - 34.287), while the suicide risk significantly declined after five years, underscoring the importance of early prediction and intervention. Multivariable analysis identified nine independent risk factors for suicide, including age, race, and Gleason score, based on which a nomogram prediction model was developed. The model demonstrated good performance in both the training and validation cohorts, with C-indices of 0.714 and 0.685, respectively. ROC curve analysis further confirmed its acceptable predictive capability.

In this study, we successfully developed and validated a nomogram-based suicide risk prediction model. The model demonstrated strong discriminatory ability and predictive performance in validation. It can help clinicians to quickly identify patients with higher suicide risk and take timely preventive measures.