Validation of a digital pathology-based multimodal artificial intelligence biomarker in a prospective, real-world prostate cancer cohort treated with prostatectomy

Abstract Purpose: A multimodal artificial intelligence (MMAI) biomarker was developed using clinical trial data from North American men with localized prostate cancer (PCa) treated with definitive radiation, using biopsy digital pathology images and key clinical information (age, PSA, T-stage) to generate prognostic scores. This study externally validates the biomarker in a prospective, real-world dataset of men who underwent radical prostatectomy (RP) for localized PCa at a tertiary referral center in Sweden. Experimental Design: Association between the MMAI scores (continuously and categorically) and endpoints of interest were performed with Fine-Gray and cumulative incidence analyses for biochemical recurrence (BCR) and logistic regression for adverse pathology (AP) at RP. Results: The analysis included 143 patients with evaluable biopsy pathology images and complete clinical data to generate MMAI scores. Median follow-up was 8.8 years. At diagnosis, median PSA was 7.5 ng/mL, median age 64 years, 29% had Gleason grade group ≥3, and 88 men were evaluable for AP at RP. MMAI was significantly associated with BCR (subdistribution HR 2.45 [95% CI 1.77-3.38], p<0.001) and AP at RP (OR 4.85 [95% CI 2.54-10.78], p<0.001). Estimated 5-yr BCR rates for MMAI Intermediate-High vs Low were 25% (95% CI 16%-36%) vs 4% (95% CI 1%-11%), respectively. Conclusions: The MMAI biomarker, previously shown to be prognostic for distant metastasis and prostate cancer-specific mortality in men receiving definitive radiation, was prognostic for post-RP endpoints: BCR and AP. This biomarker validation study further supports the use of MMAI biomarkers in men with PCa outside North America and those treated with RP.