Digital Pathology-Based Multimodal Artificial Intelligence Scores and Outcomes in a Randomized Phase III Trial in Men With Nonmetastatic Castration-Resistant Prostate Cancer.

Abstract

The SPARTAN trial demonstrated that the addition of apalutamide to androgen deprivation therapy improves outcomes among patients with nonmetastatic castration-resistant prostate cancer (nmCRPC). We applied a previously reported digital histopathology-based multimodal artificial intelligence (MMAI) algorithm to estimate clinical outcomes in SPARTAN. Patients with available hematoxylin and eosin-stained slides from the primary tumor were included. Histopathology slides were digitized. MMAI scores ranging from 0 to 1 were generated from digital histopathology and baseline clinical parameters. Patients were categorized into MMAI non-high-risk and high-risk groups using previously validated cutoffs. Kaplan-Meier estimates were calculated for metastasis-free survival (MFS), second progression-free survival (PFS2), and overall survival (OS); comparisons were performed using Cox proportional hazards regression for treatment arms and MMAI risk. The interaction between treatment arm and risk group was evaluated using a Cox proportional hazards model. The study included 420 evaluable patients after excluding those with missing clinical data or inadequate histopathology images. Of these, 63% (n = 266) were MMAI high risk and 37% (n = 154) were non-high risk. MMAI risk score was associated with shorter MFS (hazard ratio [HR], 1.72; <i>P</i> < .005), PFS2 (HR, 1.57; <i>P</i> < .005), and OS (HR, 1.41; <i>P</i> = .02). MMAI high-risk patients receiving apalutamide demonstrated significant improvement in MFS (HR, 0.19; <i>P</i> < .005), PFS2 (HR, 0.47; <i>P</i> < .005), and OS (HR, 0.6; <i>P</i> = .01). The interaction between MMAI risk score and treatment for MFS (<i>P</i> = .01) and PFS2 (<i>P</i> = .03) was significant, indicating greater benefit from apalutamide treatment in MMAI high-risk patients. MMAI is a prognostic marker in nmCRPC and may serve as a predictive biomarker with high-risk patients deriving the greatest benefit from treatment with apalutamide. These results represent the first extension of an MMAI classifier to patients with castration-resistant prostate cancer, warranting additional validation.