Research source
AI predicted two important cancer markers simultaneously from routine tissue images and patient data.
Based on A multi-task deep learning framework for simultaneous prediction of microsatellite instability and tumor mutational burden in gastric cancer from histopathological images.
Published by Frontiers in oncologyJun 8, 2026
Peer-reviewed paperMedium evidenceHuman study
What researchers observed
A new AI model predicted biomarkers for gastric cancer immunotherapy using routine pathology images and clinical data with good accuracy.
What this could mean
This could help researchers develop faster, cheaper ways to find key markers for immunotherapy using regular hospital images. If validated further, it may point toward screening tools that reduce costly genetic testing.
What researchers still need to learn
Researchers still need to learn whether this AI approach works well broadly across many hospitals and patient groups.