Artificial intelligence in colonoscopies is next frontier for procedure
UCI Health gastroenterologist says tools should be implemented as physician-AI hybrid
September 25, 2024
"Endoscopy has reached the limits of human visual capacity, where seeing more pixels won't necessarily improve clinical diagnosis. What's next for elevating the care of patients really is AI," says UCI Health gastroenterologist Dr. Jason B. Samarasena.
IN THE NEWS: Artificial intelligence tools could soon be a vital way for clinicians to improve their performance when giving colonoscopies.
UCI Health gastroenterologist Dr. Jason B. Samarasena told Medscape that such tools will push past the limitations of the endoscope in the procedure. They can help further identify polyps, assist with documentation and provide detailed feedback.
"Endoscopy has reached the limits of human visual capacity, where seeing more pixels won't necessarily improve clinical diagnosis. What's next for elevating the care of patients really is AI."
For best results, he suggests that new tools should be implemented as a physician-AI hybrid.
"In real-world practice, this is being implemented without attention to endoscopist inclination and behavior. Having a better understanding of physician attitudes could yield more optimal results."
Samarasena sees patients at the UCI Health Chao Digestive Health Institute at UCI Medical Center in Orange, where he is also the director of advanced endoscopic imaging. He specializes in treating gastrointestinal disorders, including gastroesophageal reflux disease (GERD), esophageal disease, pancreatic cysts, biliary tract disorders, gastric intestinal metaplasia and colorectal cancer.
Samarasena is also a professor of medicine at the UC Irvine School of Medicine. His research interests include colonoscopy bowel prep and advanced endoscopic imaging.
Read more
