Multicentre Evaluation of an AI-Assisted Urine Test for Clinically Significant Prostate Cancer in Men Undergoing Initial Biopsy - PubMed

4 hours ago

The Extracellular Vesicles Gene-based Prostate Score (EGPS) is an AI diagnostic tool for detecting clinically significant prostate cancer (csPCa) using urinary EV-derived gene expression.
EGPS does not require digital rectal examination (DRE) and aims to reduce unnecessary biopsies caused by limited specificity of prostate-specific antigen (PSA).
The study evaluated EGPS in 645 patients with PSA levels of 0-15 ng/mL, divided into training, internal validation, and external validation cohorts.
EVs were isolated using the EXODUS platform, and gene expression was measured by RT-qPCR. Ten machine learning algorithms were used to construct the EGPS model.
The EGPS model, incorporating AMACR, HOXB13, and PSGR, achieved AUCs of 0.838, 0.825, and 0.811 in training, internal validation, and external validation cohorts, respectively.
At a cut-off value of 0.22, the model showed sensitivity above 95% and reduced unnecessary biopsies by 23.37%, 18.62%, and 15.25% across the cohorts.
A DeepSeek-powered AI diagnostic system integrating EGPS was developed to support csPCa diagnosis and minimize unnecessary biopsies.
EGPS enables accurate, non-invasive prediction of csPCa in men with PSA levels of 0-15 ng/mL and supports early screening and personalized clinical decision-making.

Hasty Briefsbeta