Impact of Computer-Assisted System on the Learning Curve and Quality in Esophagogastroduodenoscopy: Randomized Controlled Trial

Li Huang, Jun Liu, Lianlian Wu, Ming Xu, Liwen Yao, Lihui Zhang, Renduo Shang, Mengjiao Zhang, Qiutang Xiong, Dawei Wang, Zehua Dong, Youming Xu, Jia Li, Yijie Zhu, Dexin Gong, Huiling Wu, Honggang Yu, Li Huang, Jun Liu, Lianlian Wu, Ming Xu, Liwen Yao, Lihui Zhang, Renduo Shang, Mengjiao Zhang, Qiutang Xiong, Dawei Wang, Zehua Dong, Youming Xu, Jia Li, Yijie Zhu, Dexin Gong, Huiling Wu, Honggang Yu

Abstract

Background and Aims: To investigate the impact of the computer-assisted system on esophagogastroduodenoscopy (EGD) training for novice trainees in a prospective randomized controlled trial. Methods: We have constructed a computer-aided system (CAD) using retrospective images based on deep learning which could automatically monitor the 26 anatomical landmarks of the upper digestive tract and document standard photos. Six novice trainees were allocated and grouped into the CAD group and control group. Each of them took the training course, pre and post-test, and EGD examination scored by two experts. The CAD group was trained with the assistance of the CAD system and the control group without. Results: Both groups achieved great improvements in EGD skills. The CAD group received a higher examination grading score in the EGD examination (72.83 ± 16.12 vs. 67.26 ± 15.64, p = 0.039), especially in the mucosa observation (26.40 ± 6.13 vs. 24.11 ± 6.21, p = 0.020) and quality of collected images (7.29 ± 1.09 vs. 6.70 ± 1.05). The CAD showed a lower blind spot rate (2.19 ± 2.28 vs. 3.92 ± 3.30, p = 0.008) compared with the control group. Conclusion: The artificial intelligence assistant system displayed assistant capacity on standard EGD training, and assisted trainees in achieving a learning curve with high operation quality, which has great potential for application. Clinical Trial Registration: This trial is registered at https:/clinicaltrials.gov/, number NCT04682821.

Keywords: artificial intelligence; endoscopy; esophagogastroduodenoscopy; learning curve; training.

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Copyright © 2021 Huang, Liu, Wu, Xu, Yao, Zhang, Shang, Zhang, Xiong, Wang, Dong, Xu, Li, Zhu, Gong, Wu and Yu.

Figures

Figure 1
Figure 1
Graphic abstract of the study.
Figure 2
Figure 2
The display screen of the CAD group and control group during their training of EGD. #In the CAD group, the CAD system would remind the trainees of blind spots in real-time.
Figure 3
Figure 3
Flow chart of the study.
Figure 4
Figure 4
The learning curve of the CAD and control group.

References

    1. Rutter MD, Rees CJ. Quality in gastrointestinal endoscopy. Endoscopy. (2014) 46:526–8. 10.1055/s-0034-1365738
    1. Khan R, Grover SC. A standardized technique for gastroscopy: still missing? Endosc Int Open. (2020) 8:E1231–2. 10.1055/a-1216-1933
    1. Miller AT, Sedlack RE, Sedlack RE, Coyle WJ, Obstein KL, Poles MA, et al. . Competency in esophagogastroduodenoscopy: a validated tool for assessment and generalizable benchmarks for gastroenterology fellows. Gastrointest Endosc. (2019) 90:613–20.e1. 10.1016/j.gie.2019.05.024
    1. Di Giulio E, Fregonese D, Casetti T, Cestari R, Chilovi F, D'Ambra G, et al. . Training with a computer-based simulator achieves basic manual skills required for upper endoscopy: a randomized controlled trial. Gastrointest Endosc. (2004) 60:196–200. 10.1016/S0016-5107(04)01566-4
    1. Ende A, Zopf Y, Konturek P, Naegel A, Hahn EG, Matthes K, et al. . Strategies for training in diagnostic upper endoscopy: a prospective, randomized trial. Gastrointest Endosc. (2012) 75:254–60. 10.1016/j.gie.2011.07.063
    1. Ferlitsch A, Glauninger P, Gupper A, Schillinger M, Haefner M, Gangl A, et al. . Evaluation of a virtual endoscopy simulator for training in gastrointestinal endoscopy. Endoscopy. (2002) 34:698–702. 10.1055/s-2002-33456
    1. Ferlitsch A, Schoefl R, Puespoek A, Miehsler W, Schoeniger-Hekele M, Hofer H, et al. . Effect of virtual endoscopy simulator training on performance of upper gastrointestinal endoscopy in patients: a randomized controlled trial. Endoscopy. (2010) 42:1049–56. 10.1055/s-0030-1255818
    1. Li S, Li G, Liu Y, Xu W, Yang N, Chen H, et al. . Development and assessment of a gastroscopy electronic learning system for primary learners: randomized controlled trial. J Med Int Res. (2020) 22:e16233. 10.2196/16233
    1. Sedlack RE. Validation of computer simulation training for esophagogastroduodenoscopy: pilot study. J Gastroenterol Hepatol. (2007) 22:1214–9. 10.1111/j.1440-1746.2007.04841.x
    1. Wu L, Zhang J, Zhou W, An P, Shen L, Liu J, et al. . Randomised controlled trial of WISENSE, a real-time quality improving system for monitoring blind spots during esophagogastroduodenoscopy. Gut. (2019) 68:2161. 10.1136/gutjnl-2018-317366
    1. Ekkelenkamp VE, Koch AD, de Man RA, Kuipers EJ. Training and competence assessment in GI endoscopy: a systematic review. Gut. (2016) 65:607–15. 10.1136/gutjnl-2014-307173
    1. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. (2015) 521:436–44. 10.1038/nature14539
    1. Shen D, Wu G, Suk HIJARoBE. Deep learning in medical image analysis. Annu Rev Biomed Eng. Annu Rev Biomed Eng. (2017) 19:221–48. 10.1146/annurev-bioeng-071516-044442
    1. Min JK, Kwak MS, Cha JM. Overview of deep learning in gastrointestinal endoscopy. Gut Liver. (2019) 13:388. 10.5009/gnl18384
    1. Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, et al. . Human-level control through deep reinforcement learning. Nature. (2015) 518:529–33. 10.1038/nature14236
    1. Silver D, Huang A, Maddison CJ, Guez A, Sifre L, Van Den Driessche G, et al. . Mastering the game of Go with deep neural networks and tree search. Nature. (2016) 529:484–9. 10.1038/nature16961
    1. Chen D, Wu L, Li Y, Zhang J, Liu J, Huang L, et al. . Comparing blind spots of unsedated ultrafine, sedated, and unsedated conventional gastroscopy with and without artificial intelligence: a prospective, single-blind, 3-parallel-group, randomized, single-center trial. Gastrointest Endosc. (2020) 91:332–9.e3. 10.1016/j.gie.2019.09.016
    1. Wu L, Zhou W, Wan X, Zhang J, Shen L, Hu S, et al. . A deep neural network improves endoscopic detection of early gastric cancer without blind spots. Endoscopy. (2019) 51:522–31. 10.1055/a-0855-3532
    1. An P, Yang D, Wang J, Wu L, Zhou J, Zeng Z, et al. . A deep learning method for delineating early gastric cancer resection margin under chromoendoscopy and white light endoscopy. Gastric Cancer. (2020) 23:884–92. 10.1007/s10120-020-01071-7
    1. Wen Z, Li B, Kotagiri R, Chen J, Chen Y, Zhang R. Improving efficiency of SVM k-fold cross-validation by alpha seeding. [Preprints]. (2017). Available online at:
    1. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). (2016). p. 770–778. 10.1109/CVPR.2016.90
    1. Kruglikova I, Grantcharov TP, Drewes AM, Funch-Jensen P. The impact of constructive feedback on training in gastrointestinal endoscopy using high-fidelity virtual-reality simulation: a randomised controlled trial. Gut. (2010) 59:181–5. 10.1136/gut.2009.191825
    1. Walsh CM. In-training gastrointestinal endoscopy competency assessment tools: types of tools, validation and impact. Best Pract Res Clin Gastroenterol. (2016) 30:357–74. 10.1016/j.bpg.2016.04.001
    1. Han S, Obuch JC, Duloy AM, Keswani RN, Hall M, Simon V, et al. . A prospective multicenter study evaluating endoscopy competence among gastroenterology trainees in the era of the next accreditation system. Acad Med. (2020) 95:283–92. 10.1097/ACM.0000000000002885
    1. Beg S, Ragunath K, Wyman A, Banks M, Trudgill N, Pritchard DM, et al. . Quality standards in upper gastrointestinal endoscopy: a position statement of the british society of gastroenterology (BSG) and association of upper gastrointestinal surgeons of great britain and Ireland (AUGIS). Gut. (2017) 66:1886–99. 10.1136/gutjnl-2017-314109
    1. Rey J-F, Lambert R, Committee tEQA. ESGE recommendations for quality control in gastrointestinal endoscopy: guidelines for image documentation in upper and lower GI endoscopy. Endoscopy. (2001) 33:901–3. 10.1055/s-2001-42537
    1. Cohen J, Safdi MA, Deal SE, Baron TH, Chak A, Hoffman B, et al. . Quality indicators for esophagogastroduodenoscopy. Gastrointest Endosc. (2006) 63:S10–5. 10.1016/j.gie.2006.02.018
    1. Sedlack RE, Coyle WJ, Obstein KL, Al-Haddad MA, Bakis G, Christie JA, et al. . ASGE's assessment of competency in endoscopy evaluation tools for colonoscopy and EGD. Gastrointest Endosc. (2014) 79:1–7. 10.1016/j.gie.2013.10.003
    1. Sedlack RE, Coyle WJ, Obstein KL, Poles MA, Ramirez FC, Lukens FJ, et al. . Assessment of competency in endoscopy: establishing and validating generalizable competency benchmarks for colonoscopy. Gastrointest Endosc. (2016) 83:516–23. 10.1016/j.gie.2015.04.041
    1. Kwon RS, Davila RE, Mullady DK, Al-Haddad MA, Bang JY, Bingener-Casey J, et al. . EGD core curriculum. VideoGIE. (2017) 2:162–8. 10.1016/j.vgie.2017.03.009
    1. Joint Advisory Group on Gastrointestinal Endoscopy Formative DOPS: Diagnostic Upper Gastrointestinal Endoscopy (OGD). (2016). Available online at: (accessed November 26, 2021).

Source: PubMed

Sponsors et collaborateurs

Les conditions médicales

Interventions en matière de drogue

3
S'abonner