A Computational Pathology Model to Predict Docetaxel Benefit in Localized High-Risk and Metastatic Prostate Cancer

Docetaxel improves survival in metastatic hormone-sensitive prostate cancer (mHSPC) and high-risk localized disease, but benefits vary substantially among patients. Without predictive biomarkers, clinicians cannot identify patients who will benefit, exposing many to unnecessary toxicity. We developed and validated an artificial intelligence-based pathology image classifier (APIC) to predict docetaxel benefit.

We analyzed digitized hematoxylin and eosin-stained biopsy specimens from two phase 3 trials: CHAARTED (286/790 patients with mHSPC) and NRG/RTOG 0521 (350/563 patients with high-risk localized disease). APIC used features capturing tumor-immune spatial interactions and nuclear heterogeneity. We evaluated the predictive value of APIC for docetaxel benefit on overall survival (OS) and castration resistance using Cox proportional hazards with interaction terms.

In CHAARTED, APIC-positive patients (56.7%) showed significant OS improvement with docetaxel [HR, 0.52; 95% confidence interval (CI), 0.31-0.85; P = 0.008] and delayed castration resistance (HR, 0.48; 95% CI, 0.33-0.71; P < 0.001), whereas APIC-negative patients (43.3%) showed no benefit (HR, 1.31; 95% CI, 0.71-2.44; P = 0.39). Treatment-APIC interactions were significant (P = 0.022 and P = 0.031). In NRG/RTOG 0521, APIC-positive patients (44.7%) demonstrated survival benefit (HR, 0.49; 95% CI, 0.26-0.92; P = 0.023), whereas APIC-negative patients (55.3%) showed no benefit. Treatment-APIC interaction was significant (P = 0.024). Predictive value remained significant after adjusting for clinical variables. Limitations include retrospective analysis and need for prospective validation.

APIC predicts docetaxel benefit in both metastatic and localized prostate cancers, independent of clinical factors. Validation in triplet therapy with androgen receptor pathway inhibitors is needed.