aceCombining pathology artificial intelligence and genomic biomarkers to refine long-term postprostatectomy outcome prediction
BACKGROUND: A multimodal AI (MMAI) model has been validated in prostate biopsy specimens to guide treatment intensification in men receiving radiation. The MMAI has been explored to an extent for prostatectomy patients and has not yet been examined in relation to established genomic scores. METHODS: We applied the MMAI biopsy model to a tissue microarray (TMA) of 424 prostatectomy cases with long-term follow-up. MMAI scores were derived from digitized pathology images and clinical variables. Associations with bi…
In 414 prostatectomy cases, the MMAI score derived from digitized pathology images was associated with long-term biochemical recurrence and metastasis, and when combined with genomic CCP score reached the highest discrimination for metastasis.
MMAI lost independent prognostic value after adjustment for CAPRA clinical risk score and did not outperform established clinical tools for postprostatectomy outcome prediction.
Model was originally developed for whole slide biopsy specimens and tested on TMA spots, did not outperform established clinical tools, and authors note need for further refinement and validation in diverse settings.
Evidence
- Peer-reviewedJNCI: Journal of the National Cancer Institute2026-07-10
How should this claim be treated?
Truvace Impact Record TRV-2026-0324, v1: “Combining pathology artificial intelligence and genomic biomarkers to refine long-term postprostatectomy outcome prediction.” Truvace, 2026-07-20. /record/TRV-2026-0324 (accessed at citation time). sha256 9ab5a0f023213d7e…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-0324 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.