AI Tool Predicts Barrett's Esophagus Recurrence

The tool is 90% accurate at predicting recurrence risk and timing, information that could help prevent a deadly form of esophageal cancer.

Apr. 8, 2026 at 12:54am

Got story updates? Submit your updates here. ›

A highly detailed, translucent X-ray image showing the intricate internal structure of the human esophagus, conceptually representing the advanced medical technology used to predict and prevent esophageal cancer.An advanced AI tool could help doctors catch esophageal cancer early by predicting which patients are at highest risk of Barrett's esophagus recurrence after treatment.Chapel Hill Today

Researchers have developed an artificial intelligence (AI)-based tool that can accurately predict the risk and timing of Barrett's esophagus (BE) recurrence in patients who have undergone endoscopic eradication therapy (EET). The tool was over 90% accurate in predicting which patients would experience a recurrence of BE and when it was likely to occur, which could help doctors personalize follow-up care and catch any cancer progression early.

Why it matters

BE is the only known precursor to esophageal adenocarcinoma, an aggressive cancer with high mortality rates. Early detection of BE-related dysplasia and esophageal adenocarcinoma is crucial for saving lives. This AI tool could help identify high-risk patients for more intensive monitoring, reducing unnecessary tests and improving healthcare resource utilization.

The details

The AI model was developed and validated by researchers using data from over 2,500 patients who had been treated with EET. The analysis revealed that nearly 30% of patients experienced a recurrence of BE about 2 years after successful treatment. The model was trained to identify risk factors like longer Barrett's tissue, higher body weight, older age, more treatment sessions, and more advanced cell changes at diagnosis. When tested on both similar and different patient groups, the tool maintained over 90% accuracy in predicting recurrence risk and timing.

  • The AI tool was developed and validated using data from patients treated over several years.
  • The analysis found that BE recurrence occurred about 2 years after successful EET on average.

The players

Sachin Wani, MD

The study's senior author and executive director of the University of Colorado Anschutz Cancer Center's Rady Esophageal and Gastric Center of Excellence.

Johns Hopkins University

One of the collaborating institutions that provided data and expertise for the development of the AI tool.

Got photos? Submit your photos here. ›

What they’re saying

“Early detection of Barrett's esophagus related dysplasia and associated esophageal adenocarcinoma can save lives. Identifying recurrence in the form of BE, BE-related dysplasia and BE-related esophageal adenocarcinoma earlier, especially in high‑risk patients who have undergone endoscopic eradication therapy, creates opportunities for timely treatment before cancer develops or progresses.”

— Sachin Wani, MD, Executive Director, University of Colorado Anschutz Cancer Center's Rady Esophageal and Gastric Center of Excellence

“The challenge is that recurrence of Barrett's esophagus can still occur even after endoscopic eradication therapy, and current surveillance strategies don't distinguish between patients at high versus low risk. Everyone is followed using the same schedule regardless of their risk.”

— Sachin Wani, MD, Executive Director, University of Colorado Anschutz Cancer Center's Rady Esophageal and Gastric Center of Excellence

What’s next

The next step is to further validate the model using international datasets through collaborations in the Netherlands, the United Kingdom, Belgium and Switzerland. The goal is to validate the tool so it can be applied broadly and used as a reliable, universal aid in clinical care.

The takeaway

This AI-powered tool represents a significant advancement in the early detection and prevention of esophageal cancer by helping doctors identify high-risk patients for more intensive monitoring and treatment, potentially saving lives through earlier intervention.