... WhatsApp

Can AI Help Predict Cancer Survival? New Tool Shows Promise for GI Cancers

You are here >> Home > Latest Updates > Stomach Cancer Updates > Can AI…

Foundation Model for Predicting Prognosis and Adjuvant Therapy Benefit From Digital Pathology in GI Cancers.DOI 10.1200JCO-24-01501

A new artificial intelligence (AI) model might help doctors better understand which patients with gastrointestinal (GI) cancers are at higher risk after surgery—and who might benefit the most from extra treatment.

This study looked at patients with stomach, esophageal, and colorectal cancers. Researchers trained the AI using over 100,000 pathology slides—the kind doctors use to look at cancer cells under a microscope. The AI learned patterns from more than 130 million image sections.

Once trained, the AI could tell which patients were more likely to live longer without their cancer coming back. Patients were placed into high-risk or low-risk groups. In gastric cancer, low-risk patients had a 5-year survival rate of up to 92%, while high-risk patients had rates as low as 49%. In colorectal cancer, the difference was also large—from 43% in high-risk patients to 98% in low-risk ones.

This tool also showed something important: only the high-risk patients seemed to benefit from extra chemotherapy after surgery. Low-risk patients didn’t gain as much from additional treatment.

By combining this AI model with traditional cancer staging, doctors could get a clearer picture of a patient’s outlook. The goal is to give more treatment to those who need it—and avoid extra side effects for those who don’t.

The model still needs to be tested in future studies before it’s used in hospitals. But it could lead to more personalized care and better outcomes for people with GI cancers.

Rate this post

Exclusive Health Tips and Updates

Dr Harsh Shah - GI & HPB Oncosurgeon in Ahmeadbad
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.