Endoscopists performance in optical diagnosis of colorectal polyps in artificial intelligence studies.
artificial intelligence
colonoscopy
endoscopist performance
human factor
polyp characterization
polyp detection
Journal
United European gastroenterology journal
ISSN: 2050-6414
Titre abrégé: United European Gastroenterol J
Pays: England
ID NLM: 101606807
Informations de publication
Date de publication:
10 2022
10 2022
Historique:
received:
15
03
2022
accepted:
18
07
2022
pubmed:
20
8
2022
medline:
15
10
2022
entrez:
19
8
2022
Statut:
ppublish
Résumé
Widespread adoption of optical diagnosis of colorectal neoplasia is prevented by suboptimal endoscopist performance and lack of standardized training and competence evaluation. We aimed to assess diagnostic accuracy of endoscopists in optical diagnosis of colorectal neoplasia in the framework of artificial intelligence (AI) validation studies. Literature searches of databases (PubMed/MEDLINE, EMBASE, Scopus) up to April 2022 were performed to identify articles evaluating accuracy of individual endoscopists in performing optical diagnosis of colorectal neoplasia within studies validating AI against a histologically verified ground-truth. The main outcomes were endoscopists' pooled sensitivity, specificity, positive and negative predictive value (PPV/NPV), positive and negative likelihood ratio (LR) and area under the curve (AUC for sROC) for predicting adenomas versus non-adenomas. Six studies with 67 endoscopists and 2085 (IQR: 115-243,5) patients were evaluated. Pooled sensitivity and specificity for adenomatous histology was respectively 84.5% (95% CI 80.3%-88%) and 83% (95% CI 79.6%-85.9%), corresponding to a PPV, NPV, LR+, LR- of 89.5% (95% CI 87.1%-91.5%), 75.7% (95% CI 70.1%-80.7%), 5 (95% CI 3.9%-6.2%) and 0.19 (95% CI 0.14%-0.25%). The AUC was 0.82 (CI 0.76-0.90). Expert endoscopists showed a higher sensitivity than non-experts (90.5%, [95% CI 87.6%-92.7%] vs. 75.5%, [95% CI 66.5%-82.7%], p < 0.001), and Eastern endoscopists showed a higher sensitivity than Western (85%, [95% CI 80.5%-88.6%] vs. 75.8%, [95% CI 70.2%-80.6%]). Quality was graded high for 3 studies and low for 3 studies. We show that human accuracy for diagnosis of colorectal neoplasia in the setting of AI studies is suboptimal. Educational interventions could benefit by AI validation settings which seem a feasible framework for competence assessment.
Identifiants
pubmed: 35984903
doi: 10.1002/ueg2.12285
pmc: PMC9557953
doi:
Types de publication
Journal Article
Review
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
817-826Commentaires et corrections
Type : CommentIn
Informations de copyright
© 2022 The Authors. United European Gastroenterology Journal published by Wiley Periodicals LLC. on behalf of United European Gastroenterology.
Références
Clin Gastroenterol Hepatol. 2010 Oct;8(10):865-9, 869.e1-3
pubmed: 20621680
Endoscopy. 2020 Aug;52(8):687-700
pubmed: 32572858
Gastroenterology. 2013 Jan;144(1):81-91
pubmed: 23041328
Gastrointest Endosc. 2012 May;75(5):1022-30
pubmed: 22405698
Endoscopy. 2022 Apr;54(4):403-411
pubmed: 33951743
Endoscopy. 2022 Jan;54(1):88-99
pubmed: 34872120
Scand J Gastroenterol. 2018 Sep;53(9):1100-1106
pubmed: 30270677
Gastrointest Endosc. 2020 Jul;92(1):11-22.e6
pubmed: 32119938
Gastroenterology. 2018 Feb;154(3):568-575
pubmed: 29042219
United European Gastroenterol J. 2022 Oct;10(8):817-826
pubmed: 35984903
Gastrointest Endosc. 2011 Mar;73(3):419-22
pubmed: 21353837
Dig Dis Sci. 2015 Feb;60(2):502-8
pubmed: 25287002
Clin Res Hepatol Gastroenterol. 2019 Apr;43(2):201-207
pubmed: 30266580
BMC Med Res Methodol. 2016 Jan 15;16:6
pubmed: 26772804
Ann Intern Med. 2017 Oct 17;167(8):544-554
pubmed: 28973514
Ann Intern Med. 2011 Oct 18;155(8):529-36
pubmed: 22007046
Endoscopy. 2020 Oct;52(10):899-923
pubmed: 32882737
Endoscopy. 2022 Feb;54(2):180-184
pubmed: 33494106
Ann Intern Med. 2018 Sep 18;169(6):357-366
pubmed: 30105375
Endoscopy. 2017 Apr;49(4):378-397
pubmed: 28268235
J Clin Epidemiol. 2005 Oct;58(10):982-90
pubmed: 16168343
Int J Colorectal Dis. 2016 Mar;31(3):675-83
pubmed: 26847619
Clin Gastroenterol Hepatol. 2020 Jul;18(8):1874-1881.e2
pubmed: 31525512
Endosc Int Open. 2021 May;9(5):E716-E726
pubmed: 33937513
Gut. 2020 Nov;69(11):2035-2045
pubmed: 32393540
Gastroenterology. 2020 Jun;158(8):2169-2179.e8
pubmed: 32119927
Gut. 2020 Oct 30;:
pubmed: 33127833
J Clin Epidemiol. 2009 Oct;62(10):1006-12
pubmed: 19631508
Gut. 2017 May;66(5):887-895
pubmed: 27196576