Large-scale esophageal cancer screening through noncontrast computed tomography and artificial intelligence.

EAGLE AI model detects early esophageal cancer with 90% sensitivity and 98.5% specificity from chest CT scans across multiple centers, enabling scalable screening.

• Why it matters: Early detection of esophageal cancer remains challenging due to the lack of accurate, noninvasive, and scalable screening tools, risking delayed diagnosis and treatment.
• What they did: The study trained and validated the EAGLE AI model on over 80,000 patients from diverse international cohorts using chest noncontrast CT scans, assessing its performance in real-world screening settings.
• The result: EAGLE achieved high accuracy in identifying precancerous and early-stage cancers, reducing false positives significantly and demonstrating potential to improve early detection and screening efficiency globally.