Enzalutamide (AR inhibitor) benefit in mHSPC concentrates in APIC-negative tumors (OS HR 0.50), not APIC-positive (HR 1.04)

APIC is a locked AI histopathology classifier applied to baseline H&E prostate cancer specimens to predict differential benefit from enzalutamide (androgen receptor inhibitor) added to ADT in mHSPC. In this prespecified ENZAMET biomarker analysis (ANZUP 1304; NCT02446405), 492/1125 randomized patients with digitized tissue were evaluable (median follow-up 68.8 months); APIC labeled 64% APIC-negative and 36% APIC-positive, and significantly modified OS benefit (treatment-by-biomarker interaction p=0.014): APIC-negative patients had improved OS with enzalutamide vs NSAA (HR 0.50; 60-month OS 76.5% vs 58.3%), while APIC-positive patients did not (HR 1.04; 60-month OS 55.6% vs 58.8%). In low-volume disease, the split widened (APIC-negative HR 0.31 vs APIC-positive HR 1.04; interaction p=0.015), and when excluding early concurrent docetaxel, benefit remained larger in APIC-negative (HR 0.40; 60-month OS 82.0% vs 61.0%) than APIC-positive (HR 0.79; 60-month OS 62.8% vs 57.6%)—notable because AR pathway inhibitor intensification (including enzalutamide) is broadly used in mHSPC and ENZAMET’s overall OS benefit for enzalutamide was previously established (overall trial-level HR ~0.67), so this classifier is aiming to carve out a “who actually needs enzalutamide” subgroup rather than arguing against intensification wholesale.