Researchers created an AI tool that predicts recurrence of Barrett’s esophagus following endoscopic eradication therapies with greater than 90% accuracy.
Key Details
- 1AI model predicts recurrence of Barrett’s esophagus and related dysplasia or cancer after EET.
- 2Model achieved over 90% accuracy using data from more than 2,500 patients.
- 3Key risk factors: longer affected tissue length, higher body weight, older age, more treatment sessions, higher-grade dysplasia.
- 4Recurrence occurred in about 30% of patients, with average return two years after therapy.
- 5Validated on internal and external datasets, showing robust performance across groups.
- 6International collaborations underway to further validate AI tool.
Why It Matters
This AI model could enable risk-stratified, personalized surveillance for Barrett’s esophagus after therapy, improving early cancer detection and reducing unnecessary procedures. If widely validated, the tool may optimize healthcare resource use and patient outcomes in endoscopic GI imaging workflows.
Source
EurekAlert
Related News
•EurekAlert
USC Receives $3M Gift for Alzheimer's Research Involving Imaging and AI
A $3 million donation to USC will accelerate Alzheimer's research, including imaging modality development and AI-based molecular analysis.
•EurekAlert
AI Pathology Analysis Predicts Immunotherapy Response in Rare Tumors
AI-based analysis of tumor pathology slides can predict immunotherapy outcomes in rare cancers, according to a recent MD Anderson study.
•EurekAlert
Review Highlights AI's Impact on Breast Cancer Imaging and Recurrence Prediction
A major review details how AI enhances early detection and recurrence prediction in breast cancer imaging.