*EMBARGOED All research presented at the 2018 ACG Annual Scientific Meeting and Postgraduate Course is strictly embargoed until Monday, October 8, 2018, at 8:00 am EDT.
P0758 Artificial Intelligence Can Accurately Detect Tools Used During Colonoscopy: Another Step Forward Toward Autonomous Report Writing
Author Insight from Jason B. Samarasena, MD, FACG, University of California Irvine Medical Center
What’s new here and important for clinicians?
Artificial intelligence (AI) can help a clinician work more efficiently and accurately. The documentation “burden” on clinicians is only getting worse, and any solution that can help us spend less time in front of a computer typing a note will be great for the clinician and their patients, because more time will be available to spend with patients.
Gastroenterologists spend a large amount of their day writing procedure reports. This usually involves using an endowriter software program and clicking through menus and writing free text to generate a report. Wouldn’t it be great if someone that was watching you do your procedure could complete your procedure report for you while you are doing the procedure? I predict this is exactly what AI will be able to do for us very soon.
The AI algorithm that we designed was able to detect exactly which tool was displayed during colonoscopy. This algorithm is now being used in a real time overlay that can detect and identify tools during live colonoscopy. This information and other information about the procedure (polyp detected, locations, size) can then be output to a documentation module that will create the procedure note.
What do patients need to know?
This will benefit patients because documentation will be quicker and easier, which will free up time for clinicians to spend more time with their patients and less time on the computer.
Author Contact
Jason B. Samarasena, MD, FACG, University of California Irvine Medical Center
jason.samarasena@gmail.com
Media Interview Requests
To arrange an interview with any ACG experts or abstract authors, please contact Brian Davis of ACG via email at bdavis@gi.org or by phone at 301-263-9000.