Early treatment outcome prediction in metastatic castration-resistant prostate cancer utilizing 3-month tumor growth rate (-rate) based machine learning model.

[BACKGROUND] Once the treatment starts, early prediction of treatment benefit and its correlation with overall survival (OS) remains challenging in metastatic castration-resistant prostate cancer (mCRPC). Existing prognostic models require long-term follow-up, limiting their ability to inform timely treatment decisions. To address this gap, we evaluated tumor growth rate ( -rate)-based survival models across multiple treatment lines to assess their ability to predict OS and support early clinical decision-making.

[METHODS] We developed GxSurv, a Random Survival Forest (RSF)-based framework that incorporates baseline clinical variables and -rate calculated from serial on-treatment PSA, to construct line-specific prediction models of OS, a direct measure of treatment outcome. Three variants were developed: G3Surv, using the 3-month -rate; G6Surv, using the 6-month -rate; and GfSurv, using the final observed -rate. Model performance was evaluated using Harrell's C-index, Uno's C-index, Integrated Brier Score (IBS), time-dependent area under the curve (tAUC). Model interpretability was assessed using permutation importance to quantify predictor contributions within the GxSurv framework.

[FINDINGS] The study included 15912 treatment records from 11014 patients with mCPRC across four lines of therapy. We found that incorporation of -rate consistently improved model performance across all treatment lines, with all GxSurv models outperforming Cox proportional hazards (CoxPH). As the earliest prognostic model, our G3Surv demonstrated strong early predictive performance, with Harrell's C-index values ranging from 0·700 to 0·746 and tAUC values of 0·766 to 0·822 across all lines, representing 5-8% and 4-5% improvements over CoxPH, respectively. These results indicate that G3Surv accurately predicts individual treatment outcomes at 3 months after treatment initiation. Feature importance analyses consistently identified -rate as a top predictor, followed by baseline PSA and hemoglobin, with relative variation across treatment lines.

[INTERPRETATION] Integrating -rate calculated from on-treatment PSA values enables accurate, line-specific prediction of treatment outcomes in mCRPC, with the 3-month -rate providing robust early prognostic information to support timely, personalized clinical decision-making.

[FUNDING] U.S. National Science Foundation, National Institutes of Health, American Cancer Society.