File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: New insights on missed colonic lesions during colonoscopy through artificial intelligence-assisted real-time detection (with video)

TitleNew insights on missed colonic lesions during colonoscopy through artificial intelligence-assisted real-time detection (with video)
Authors
Issue Date2020
PublisherMosby, Inc. The Journal's web site is located at http://www.elsevier.com/locate/gie
Citation
Gastrointestinal Endoscopy, 2020, v. 93 n. 1, p. 193-200.E1 How to Cite?
AbstractBackground and Aims: Recent meta-analysis showed that up to 26% of adenoma could be missed during colonoscopy. We investigated whether the use of artificial intelligence (AI) assisted real-time detection could provide new insights into mechanisms underlying missed lesions during colonoscopy. Methods: A validated real-time deep learning AI model for detection of colonic polyps was first tested in the videos of tandem colonoscopy of the proximal colon for missed lesions. The real-time AI model was then prospectively validated in total colonoscopy in which endoscopist was blinded to the real-time AI findings. Segmental unblinding of the AI findings were provided and that colonic segment would be re-examined when there were missed lesions detected by AI but not the endoscopist. All polyps were removed for histological examination as the criterion standard. Results: Sixty-five videos of tandem examination of the proximal colon were reviewed by AI. AI could detect 79.1% (19/24) of missed proximal adenoma in the video of the first-pass examination. In the 52 prospective colonoscopies, real-time AI detection could detect at least one missed adenoma in 14 (26.9%) patients and increased total number of adenomas detected by 23.6%. Multivariable analysis showed that missed adenoma(s) was more likely when there were multiple polyps (adjusted OR, 1.05; 95% CI, 1.02-1.09; p < 0.0001) or colonoscopy by less experienced endoscopists (adjusted OR, 1.30; 95% CI, 1.05-1.62; p=0.02). Conclusion: Our findings provide new insights on the prominent role of human factors, including inexperience and distraction, play on missed colonic lesions. With the use of real-time AI assistance, up to 80% of missed adenoma could be prevented.
Persistent Identifierhttp://hdl.handle.net/10722/282529
ISSN
2023 Impact Factor: 6.7
2023 SCImago Journal Rankings: 1.749
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLui, TKL-
dc.contributor.authorHui, CKY-
dc.contributor.authorTsui, VWM-
dc.contributor.authorCheung, KS-
dc.contributor.authorKo, MKL-
dc.contributor.authorFoo, ACC-
dc.contributor.authorMak, LY-
dc.contributor.authorYeung, CK-
dc.contributor.authorLui, THW-
dc.contributor.authorWong, SY-
dc.contributor.authorLeung, WK-
dc.date.accessioned2020-05-15T05:29:18Z-
dc.date.available2020-05-15T05:29:18Z-
dc.date.issued2020-
dc.identifier.citationGastrointestinal Endoscopy, 2020, v. 93 n. 1, p. 193-200.E1-
dc.identifier.issn0016-5107-
dc.identifier.urihttp://hdl.handle.net/10722/282529-
dc.description.abstractBackground and Aims: Recent meta-analysis showed that up to 26% of adenoma could be missed during colonoscopy. We investigated whether the use of artificial intelligence (AI) assisted real-time detection could provide new insights into mechanisms underlying missed lesions during colonoscopy. Methods: A validated real-time deep learning AI model for detection of colonic polyps was first tested in the videos of tandem colonoscopy of the proximal colon for missed lesions. The real-time AI model was then prospectively validated in total colonoscopy in which endoscopist was blinded to the real-time AI findings. Segmental unblinding of the AI findings were provided and that colonic segment would be re-examined when there were missed lesions detected by AI but not the endoscopist. All polyps were removed for histological examination as the criterion standard. Results: Sixty-five videos of tandem examination of the proximal colon were reviewed by AI. AI could detect 79.1% (19/24) of missed proximal adenoma in the video of the first-pass examination. In the 52 prospective colonoscopies, real-time AI detection could detect at least one missed adenoma in 14 (26.9%) patients and increased total number of adenomas detected by 23.6%. Multivariable analysis showed that missed adenoma(s) was more likely when there were multiple polyps (adjusted OR, 1.05; 95% CI, 1.02-1.09; p < 0.0001) or colonoscopy by less experienced endoscopists (adjusted OR, 1.30; 95% CI, 1.05-1.62; p=0.02). Conclusion: Our findings provide new insights on the prominent role of human factors, including inexperience and distraction, play on missed colonic lesions. With the use of real-time AI assistance, up to 80% of missed adenoma could be prevented.-
dc.languageeng-
dc.publisherMosby, Inc. The Journal's web site is located at http://www.elsevier.com/locate/gie-
dc.relation.ispartofGastrointestinal Endoscopy-
dc.titleNew insights on missed colonic lesions during colonoscopy through artificial intelligence-assisted real-time detection (with video)-
dc.typeArticle-
dc.identifier.emailLui, TKL: lkl484@hku.hk-
dc.identifier.emailCheung, KS: cks634@hku.hk-
dc.identifier.emailFoo, ACC: ccfoo@hku.hk-
dc.identifier.emailMak, LY: lungyi@HKUCC-COM.hku.hk-
dc.identifier.emailWong, SY: ksywong@hkucc.hku.hk-
dc.identifier.authorityCheung, KS=rp02532-
dc.identifier.authorityFoo, ACC=rp01899-
dc.identifier.authorityMak, LY=rp02668-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.gie.2020.04.066-
dc.identifier.pmid32376335-
dc.identifier.scopuseid_2-s2.0-85089729777-
dc.identifier.hkuros309946-
dc.identifier.volume93-
dc.identifier.issue1-
dc.identifier.spage193-
dc.identifier.epage200.E1-
dc.identifier.isiWOS:000600548600027-
dc.publisher.placeUnited States-
dc.identifier.issnl0016-5107-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats