Background and Aims
EGD is the most vital procedure for the diagnosis of upper GI lesions. We aimed to
compare the performance of unsedated ultrathin transoral endoscopy (U-TOE), unsedated
conventional EGD (C-EGD), and sedated C-EGD with or without the use of an artificial
intelligence (AI) system.
Methods
In this prospective, single-blind, 3-parallel-group, randomized, single-center trial,
437 patients scheduled to undergo outpatient EGD were randomized to unsedated U-TOE,
unsedated C-EGD, or sedated C-EGD, and each group was then divided into 2 subgroups:
with or without the assistance of an AI system to monitor blind spots during EGD.
The primary outcome was the blind spot rate of these 3 groups with the assistance
of AI. The secondary outcomes were to compare blind spot rates of unsedated U-TOE,
unsedated, and sedated C-EGD with or without the assistance of AI, respectively, and
the concordance between AI and the endoscopists’ review.
Results
The blind spot rate with AI-assisted sedated C-EGD was significantly lower than that
of unsedated U-TOE and unsedated C-EGD (3.42% vs 21.77% vs 31.23%, respectively; P < .05). The blind spot rate of the AI subgroup was lower than that of the control
subgroup in all 3 groups (sedated C-EGD: 3.42% vs 22.46%, P < .001; unsedated U-TOE: 21.77% vs 29.92%, P < .001; unsedated C-EGD: 31.23% vs 42.46%, P < .001).
Conclusions
The blind spot rate of sedated C-EGD was the lowest among the 3 types of EGD, and
the addition of AI had a maximal effect on sedated C-EGD. (Clinical trial registration
number: ChiCTR1900020920.)
Graphical abstract
Graphical Abstract
Abbreviations:
AI (artificial intelligence), C-EGD (conventional EGD), RD (risk difference), U-TOE (unsedated ultrathin transoral endoscopy)To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Gastrointestinal EndoscopyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Esophagogastroduodenoscopy.Europe PMC. Statpearls. 2018; (Available at:)
- Quality in gastrointestinal endoscopy.Endoscopy. 2014; 46: 526-528
- Longer observation time increases proportion of neoplasms detected by esophagogastroduodenoscopy.Gastroenterology. 2017; 153: 460-469
- The endoscopy Global Rating Scale-Canada: development and implementation of a quality improvement tool.Can J Gastroenterol. 2013; 27: 74-82
- Utilization of anesthesia services during outpatient endoscopies and colonoscopies and associated spending in 2003-2009.JAMA. 2012; 307: 1178-1184
- Anesthesia service use during outpatient gastroenterology procedures continued to increase from 2010 to 2013 and potentially discretionary spending remained high.Am J Gastroenterol. 2017; 112: 297-302
- Gastrointestinal endoscopy sedation and monitoring practices in Spain: a nationwide survey in the year 2014.Endoscopy. 2015; 47: 383-390
- Sedation in gastrointestinal endoscopy: current issues.World J Gastroenterol. 2013; 19: 463-481
- Use of sedation for routine diagnostic upper gastrointestinal endoscopy: a European Society of Gastrointestinal Endoscopy Survey of National Endoscopy Society Members.Digestion. 2006; 74: 69-77
- Patients' attitudes and apprehensions about endoscopy: how to calm troubled waters.Am J Gastroenterol. 2001; 96: 280-284
- Ultra-thin caliber endoscopes in daily practice: uses for therapeutic application and beyond on the basis of review of 1028 procedures.Endosc Int Open. 2015; 3: E400-E404
- Krefeld CONTRA study: conventional peroral Esophago-Gastro-Duodenoscopy (EGD) vs. transnasal EGD—a prospective and randomised study with independent evaluation of conscious sedation, endoscope diameter, and access path.Z Gastroenterol. 2010; 48: 818-824
- Unsedated small caliber esophagogastroduodenoscopy: can we trust this technique?.Turk J Gastroenterol. 2011; 22: 237-242
- High-definition medicine.Cell. 2017; 170: 828-843
- Deep learning.Nature. 2015; 521: 436-444
- Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study.Lancet Oncol. 2019; 20: 193-201
- Accurate classification of diminutive colorectal polyps using computer-aided analysis.Gastroenterology. 2018; 154: 568-575
Mnih V, Kavukcuoglu K, Silver D, et al. Playing atari with deep reinforcement learning. Cornell University. arXiv. Available at: https://arxiv.org/abs/1312.5602. Accessed December 19, 2013.
- Randomized controlled trial of Wisense, a real-time quality improving system for monitoring blind spots during esophagogastroduodenoscopy.Gut. Epub. 2019 Mar 11;
- A deep neural network improves endoscopic detection of early gastric cancer without blind spots.Endoscopy. 2019; 51: 1-19
- Unsedated ultrathin EGD by using a 5.2-mm-diameter videoscope: evaluation of acceptability and diagnostic accuracy.Gastrointest Endosc. 2006; 64: 868-873
- Comparison of thin versus standard esophagogastroduodenoscopy.J Fam Pract. 2002; 51: 625-629
- Sedation versus no sedation in the performance of diagnostic upper gastrointestinal endoscopy: a Canadian randomized controlled cost-outcome study.Am J Gastroenterol. 2004; 99: 1692-1699
- Ultrathin endoscopy versus high-resolution endoscopy for diagnosing superficial gastric neoplasia.Gastrointest Endosc. 2009; 70: 240-245
- Performance measures for upper gastrointestinal endoscopy: a European Society of Gastrointestinal Endoscopy (ESGE) quality improvement initiative.Endoscopy. 2016; 48: 843-864
- Development of an e-learning system for teaching endoscopists how to diagnose early gastric cancer: basic principles for improving early detection.Gastric Cancer. 2017; 20: 28-38
- Improving the endoscopic detection rate in patients with early gastric cancer.Clin Endosc. 2015; 48: 291-296
- Clinicopathological characterisation of small (2cm or less) proximal and distal gastric carcinomas in a Chinese population.Pathology. 2015; 47: 526-532
- Pethidine dose and female sex as risk factors for nausea after esophagogastroduodenoscopy.J Clin Biochem Nutr. 2018; 63: 230-232
- Unsedated ultrathin EGD is well accepted when compared with conventional sedated EGD: a multicenter randomized trial.Gastroenterology. 2003; 125: 1606-1612
- A pilot study assessing tolerance safety and feasibility of diagnostic transnasal esophagogastroduodenoscopy using an improved larger caliber endoscope and an adapted topical anesthesia.Surg Endosc. 2015; 29: 3002-3009
Article info
Publication history
Published online: September 18, 2019
Accepted:
September 8,
2019
Received:
March 1,
2019
Footnotes
DISCLOSURE: The following author received research support for this study from Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision (2019), the National Natural Science Foundation of China (grant no. 81672387): H. Yu. All authors disclosed no financial relationships relevant to this publication.
If you would like to chat with an author of this article, you may contact Dr Yu at [email protected]
Identification
Copyright
© 2020 by the American Society for Gastrointestinal Endoscopy
ScienceDirect
Access this article on ScienceDirectLinked Article
- Artificial intelligence in endoscopy: the guardian angel is around the cornerGastrointestinal EndoscopyVol. 91Issue 2
- PreviewArtificial intelligence (AI), which mimics human cognitive functioning, has revolutionized many industries, including medicine.1 Recent advances in technology, including increased computational power, more efficient hardware, and the development of deep learning algorithms, have led to the emergence of several AI applications in GI endoscopy.2 Physicians who perform endoscopy often require several clinical skills, including the simultaneous dexterous operation of endoscopic devices and also the visual identification of disease, so as to drive clinical decision making.
- Full-Text
- Preview
