Evaluating the prognostic value of radiomics and clinical features in metastatic prostate cancer using...

Prostate cancer is a significant global health issue due to its high incidence and poor outcomes in metastatic disease. This study aims to develop models predicting overall survival for patients with metastatic biochemically recurrent prostate cancer, potentially helping to identify high-risk patients and enabling more tailored treatment options. A multi-centre cohort of 180 such patients underwent [⁶⁸Ga]Ga-PSMA-11 PET/CT scans, with lesions semi-automatically segmented and radiomic features extracted from lesions. The analysis included two phases: univariable and multivariable. Univariable analysis used Kaplan-Meier curves and Cox proportional hazards models to correlate individual features with overall survival. Multivariable analysis used the LASSO Cox proportional hazards method to create 13 models: radiomics-only, clinical-only, and various combinations of radiomic and clinical features. Each model included six features and was bootstrapped 1000 times to obtain concordance indices with 95% confidence intervals, followed by optimism correction. In the univariable analysis, 6 out of 8 clinical features and 68 out of 89 radiomic features were significantly correlated with overall survival, including age, disease stage, total lesional uptake and total lesional volume. The optimism-corrected concordance indices from the multivariable models were 0.722 (95% CI 0.653-0.784) for the clinical model, 0.681 (95% CI 0.616-0.745) for the radiomics model, and 0.704 (95% CI 0.648-0.768) for the combined model with three clinical and three radiomic features, when extracting radiomic features from the largest lesion only. While univariable analysis showed significant prognostic value for many radiomic features, their integration into multivariable models did not improve predictive accuracy beyond clinical features alone.