Real-Time Feedback for Colonoscopy in a Multicenter Clinical Trial Tavanapong, Wallapak Tavanapong, Wallapak Oh, JungHwan Kijkul, Gavin Pratt, Jacob Wong, Johnny deGroen, Piet
dc.contributor.department Computer Science 2020-09-08T20:21:54.000 2021-02-25T00:34:31Z 2021-02-25T00:34:31Z Wed Jan 01 00:00:00 UTC 2020 2020-09-08 2020-01-01
dc.description.abstract <p>We report the technical challenges, solutions, and lessons learned from deploying real-time feedback systems in three hospitals as part of a multi-center controlled clinical trial to improve quality of colonoscopy. Previous clinical trials were conducted in one center. The technical challenges for our multicenter clinical trial include 1) reducing additional work by the endoscopists to utilize real-time feedback, 2) handling different colonoscopy practices at different hospitals, and 3) training an effective CNN-based classification model with a large variety of patterns of data in day-to-day colonoscopy practice. We report performance of our real-time systems over a period of 20 weeks at each hospital. We conclude that CNN-based classification can achieve very good performance in real-world deployment when trained with high quality data.</p>
dc.description.comments <p>This is a manuscript of a proceeding published as W. Tavanapong, J. Oh, G. Kijkul, J. Pratt, J. Wong and P. deGroen, "Real-Time Feedback for Colonoscopy in a Multicenter Clinical Trial," <em>2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS)</em>, Rochester, MN, USA, 2020, pp. 13-18, doi: <a href="" target="_blank">10.1109/CBMS49503.2020.00010</a>.</p>
dc.format.mimetype application/pdf
dc.identifier archive/
dc.identifier.articleid 1049
dc.identifier.contextkey 19300925
dc.identifier.s3bucket isulib-bepress-aws-west
dc.identifier.submissionpath cs_conf/50
dc.language.iso en
dc.source.bitstream archive/|||Sat Jan 15 00:41:23 UTC 2022
dc.source.uri 10.1109/CBMS49503.2020.00010
dc.subject.disciplines Clinical Trials
dc.subject.disciplines Computer Sciences
dc.subject.disciplines Data Science
dc.subject.disciplines Medicine and Health Sciences
dc.subject.keywords Multi-center clinical trial
dc.subject.keywords Real-time feedback of colonoscopy quality
dc.subject.keywords Convolution Neural Network (CNN)
dc.title Real-Time Feedback for Colonoscopy in a Multicenter Clinical Trial
dc.type article
dc.type.genre conference
dspace.entity.type Publication
relation.isAuthorOfPublication f9b67a19-5d18-4682-9a80-4f91f92018a2
relation.isOrgUnitOfPublication f7be4eb9-d1d0-4081-859b-b15cee251456
Original bundle
Now showing 1 - 1 of 1
809.92 KB
Adobe Portable Document Format