CHAI-based biomarker can prognosticate progression risk in LG NMIBC

In a recent interview with Urology Times®, Roger Li, MD, discussed the development and validation of a computational histology artificial intelligence (CHAI)-based biomarker designed to identify patients with low-grade non-muscle invasive bladder cancer (NMIBC) who are at an increased risk of progression. This work was presented at the 2025 Society of Urology Oncology Annual Meeting in Phoenix, Arizona.¹

In total, the study included 302 patients with low-grade NMIBC in the validation cohort. Of those, 13.6% of patients were classified as high-risk and 86.4% were classified as low risk by the CHAI platform.

Overall, the platform was able to accurately identify those with an increased risk of progression, with patients who were classified as high risk demonstrating a significantly increased risk of progression compared with those classified as low risk (HR, 4.75; 95% CI, 2.48 to 9.09; P < .0001).The high-risk group remained at higher risk of progression at 12 months (17% in the high-risk group vs 4.6% in the low-risk group; P = .11), 36 months (50% vs 12%; P < .05), and 60 months (73% vs 15%; P < .001).

Li added, “Even when we're pairing this with clinical factors that we know confer higher risk—such as the IBCG risk criteria—the AI path criteria still played a major role in predicting for progression. So, I think it's a very powerful tool.”

REFERENCE

1. Li R. Development and Validation of a Computational Histology AI (CHAI)-based biomarker to Prognosticate High Grade Progression risk in Low-Grade Non-muscle Invasive Bladder Cancer. Presented at: Society of Urologic Oncology Annual Meeting; December 2-5, 2025; Phoenix, Arizona. Abstract 197. https://suo-abstracts.secure-platform.com/a/gallery/rounds/24/details/4718