Post written by Honggang Yu, MD, from the Department of Gastroenterology, Renmin Hospital of Wuhan University, the Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, and the Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China.

The current study retrospectively collected colonoscopy images to train the AI system named ENDOANGEL. This system provides an accurate evaluation method for real-time bowel preparation. To verify the performance of ENDOANGEL, we conducted a human-machine contest between AI and endoscopists. ENDOANGEL achieved 93.33% accuracy in the human–machine contest with 120 images, which was better than that of all endoscopists.

We provided a novel and more accurate evaluation method for bowel preparation and developed an objective and stable system that can be applied reliably and steadily in clinical settings. This system can help endoscopists recommend a more precise follow-up interval, which is beneficial to detecting colonic lesions.

We can also use ENDOANGEL to compare clinical effectiveness among different bowel preparation agents. More importantly, we can compare the performance of ENDOANGEL using colonoscopes from different suppliers.

Read the full article online.

The information presented in Endoscopedia reflects the opinions of the authors and does not represent the position of the American Society for Gastrointestinal Endoscopy (ASGE). ASGE expressly disclaims any warranties or guarantees, expressed or implied, and is not liable for damages of any kind in connection with the material, information, or procedures set forth.