Anna Wilkins speaks to ecancer about external validation of a digital pathology-based multimodal artificial intelligence (MMAI)-derived prognostic biomarker in the randomised phase III CHHiP trial.

This study externally validated the ArteraAI MMAI algorithm, which integrates age, T-stage, PSA, and digital biopsy H&E images, in 1,797 patients with localised prostate cancer from the CHHiP trial.

Over a median follow-up of 14.3 years, MMAI effectively stratified patients into high, intermediate, and low risk, showing strong associations with biochemical/clinical recurrence (BCR) and development of distant metastases.

Dr Wilkins says that incorporating MMAI into existing risk models, including Cambridge Prognostic Group (CPG) and NCCN, significantly improved predictive accuracy and model fit.

This large-scale external validation demonstrates MMAI’s potential to guide personalised treatment decisions and optimise management in localised prostate cancer.