New Study Finds AI Matched Performance of Gastroenterologists in Evaluating Endoscopies
Crohn's disease patients who underwent endoscopies had their results evaluated by AI, and the results matched, and potentially exceeded, the doctors' notes.
A new study found that artificial intelligence “matched and potentially exceeded the performance of gastroenterologists and conventional scoring in evaluating endoscopies of Crohn’s disease patients.”
The results “show a computer vision model identified mucosal ulceration as accurately as physician reviewing videos, while also being strongly correlated with the most common endoscopic scoring system.”
In the study, “two gastroenterologists annotated ulcer areas in 4,487 still images from endoscopic videos. The computer vision AI model reviewed the same images, from previous clinical trials.” The AI model’s results “had a higher overall DICE similarity score with ground truth (.591) than when comparing the agreement between two gastroenterologists (.462).” Computer vision assessments of the colonoscopy videos “were also strongly correlated with Simple Endoscopic Score for Crohn’s Disease (SES-CD) values.”
Researchers hope that “AI-powered metrics will not only improve consistency between providers but more importantly may offer more quantitative detail to describe disease.” They also identified several other potential advantages to more consistent endoscopy metrics, giving areas without IBD specialists help in guiding treatment change.
