Multimodal Artificial Intelligence Prediction of Abiraterone Efficacy in Two STAMPEDE Phase 3 Trials of Non-Metastatic Very High-Risk Prostate Cancer

BACKGROUND: Long-term androgen deprivation therapy (LT-ADT) with radiotherapy is standard-of-care for high-risk localized prostate cancer, with abiraterone added for clinically very high-risk disease. Given the toxicity and cost of abiraterone, a predictive biomarker to refine patient selection is needed. We evaluated a digital pathology multimodal artificial intelligence (MMAI) model, previously validated as a prognostic biomarker, for prediction of abiraterone benefit amongst non-metastatic clinically very high-risk prostate cancer. PATIENTS AND METHODS: percentile threshold to classify patients as MMAI very high-risk or standard high-risk. The primary endpoint was metastasis-free survival (MFS). Treatment effects and risk estimates were obtained using Cox regression and Kaplan-Meier method, respectively. Prediction was assessed using a treatment-by-biomarker interaction Cox model. RESULTS: In total, 1137 patients randomized to LT-ADT (N=583) or LT-ADT with abiraterone (N=554), were included. The MMAI very high-risk group (N=268) demonstrated significant MFS improvement from adding abiraterone (HR 0.47; 95% CI 0.31-0.70), with 5-year MFS increasing from 62% (95% CI 53-70%) in LT-ADT to 81% (95% CI 74-87%) in LT-ADT with abiraterone. Limited abiraterone benefit was observed in the MMAI standard high-risk group (N=869; HR 0.83; 95% CI 0.63-1.09), with a 5-year MFS of 82% (95% CI 78-85%) versus 84% (95% CI 80-87%, interaction p-value=0.02). This differential effect was consistent in local node-negative and node-positive subgroups. CONCLUSIONS: In this post-hoc study of randomized clinical trial data, a locked digital pathology MMAI test displayed a strong prognostic association and predicted abiraterone efficacy in very high-risk, non-metastatic prostate cancer. This biomarker could be implemented clinically to maximize benefit from treatment intensification whilst avoiding unnecessary toxicity.