A novel predictive model using changes in clinical and serum biomarkers and automated quantitative imaging for mCRPC patients treated with AR-directed therapy.

264 Background: In mCRPC, standard risk models use baseline clinical and blood-based biomarkers, excluding imaging. This study developed a new predictive model incorporating baseline and early on-treatment clinical, blood, and imaging biomarkers to inform overall survival (OS). The training set was derived from COU-AA-302 and validated using Alliance 031201 (A031201). Eligibility required patients to have at least two CT and bone scans within 6 months of randomization (COU-AA-302: n = 785; A031201: n = 582). Methods: Conventional biomarker data included PSA, albumin, alkaline phosphatase, hemoglobin, and ECOG status. Imaging data included > 1000 radiomic features and the automated Bone Scan Index (aBSI). Six-month biomarker trajectories were summarized using the intercept and slope from a random effects model, yielding over 2000 risk biomarkers. Due to the high dimensionality, an elastic net proportional hazards model was applied. Predictive concordance probability, which evaluates the ability to distinguish between long-term and short-term survivors, and R-square, a calibration measure that indicates how accurately the model predicts actual survival time were determined. Results: 46 biomarkers were selected from over 2000, including 9 blood-based, 4 from aBSI, 1 tumor volume measure, and the remaining from radiomic features. In contrast, the non-imaging risk model contained 10 risk factors. Risk scores from these models were categorized into low, moderate, and high-risk groups. The median survival per group revealed significant separation, with a difference of over 30 months between low and high-risk groups. This separation was observed regardless of whether imaging was included in the model. Conclusions: This is the first model for mCRPC to integrate pre-treatment and early on-treatment serum, imaging, and clinical data from two large phase 3 trials, with external validation. While both imaging and non-imaging models showed good predictive accuracy, imaging did not significantly improve the discrimination of long-term from short-term survivors or enhance the precision of the model-based survival predictions. Clinical + Serum biomarkers with imaging Clinical + Serum biomarkers without imaging Total # of risk factors 46 10 # of clinical/serum factors 9 10 # of radiomics factors 32 0 # of aBSI factors 4 0 # of tumor volume factors 1 0 Median Survival (mos) Low risk group 55 54 Moderate risk group 38 39 High risk group 20 21 Predictive Concordance Probability 0.74 0.73 R-square Measure of Calibration 0.37 0.39