Development and validation of a digital pathology artificial intelligence (DPAI)-derived risk score…

AI / informaticsFuture oncology (London, England)· Jul 2026

Development and validation of a digital pathology artificial intelligence (DPAI)-derived risk score predicting Gleason grade group reclassification for patients who are candidates for active surveillance.

Brent Mabey, Lauren H Lenz, Matthew J Schiewer … Alexander Gutin

Genitourinary PathologyAI / informaticsPrognosisQ1IF 2.6

AI-derived risk score linked to higher odds of Gleason grade group upgrading on biopsy

Development and validation of a digital pathology artificial intelligence (DPAI)-derived risk score predicting Gleason grade group reclassification for patients who are candidates for active surveillance.

Brent Mabey … Alexander Gutin

Future oncology (London, England) · Jul 2026 · Q1 in General Medicine

Purpose

Active surveillance (active surveillance) allows selected men with localized prostate cancer to defer curative therapy and reduce treatment morbidity.

Methods

The digital pathology artificial intelligence model was trained using histopathology image features from diagnostic biopsies of 998 patients and validated in an independent cohort of 296 patients meeting criteria for active surveillance.

n = 998 patients

OR 1.60

Results

OR 1.60

higher AI risk score means greater odds of grade group upgrading

n = 998 patients

More results

Predicted risks were similar across time from diagnosis (~10-15% to ~85% at 1, 1.5, or 2 years; p for time = 0.50), consistent with initial biopsy mischaracterization rather than time-dependent progression.

“

Conclusion · 1 of 2

Artificial Intelligence-Gleason Upgrade Risk provides individualized estimates of confirmatory-biopsy gleason grade group upgrading for active surveillance candidates.

Conclusion · 2 of 2

Using digital pathology artificial intelligence may improve shared decision-making by complementing standard clinicopathologic tools and molecular testing using the same biopsy specimen, while informing the likelihood of grade upgrade at confirmation.

Development and validation of a digital pathology artificial intelligence (DPAI)-derived risk score predicting Gleason grade group reclassification for patients who are candidates for active surveillance.

Development and validation of a digital pathology artificial intelligence (DPAI)-derived risk score predicting Gleason grade group reclassification for patients who are candidates for active surveillance.

Related papers