16. Application of artificial intelligence in detecting reflux esophagitis on endoscopy images
Main Article Content
Abstract
Objectives: The purpose of this study was to evaluate the accuracy of an AI algorithm in detecting reflux esophagitis and to investigate factors related to missed lesions and errors. Methods: A cross-sectional descriptive study was conducted. The algorithm was tested on a dataset consisting of 1000 endoscopic images with various lighting modes, and the results were compared to the standard expert labeling. Accuracy was assessed using sensitivity, specificity, positive predictive value, and negative predictive value. Regression models were employed to investigate factors influencing the rate of missed and misdiagnosed lesions. Result: The algorithm achieved an accuracy rate of 81.7%. The analysis revealed that the number and size of lesions in the images were significantly associated with the rate of missed detections, while accompanying damage and image cleanliness levels were related to misdiagnosed lesions. Conclusion: The Yolo v8 algorithm demonstrates high accuracy and holds potential for further development, including real-time co-assistance during endoscopy, post-endoscopic examination, and medical training using large datasets.
Article Details
Keywords
Artificial intelligence, upper gastrointestinal endoscopy, reflux esophagitis, lesion localization
References
2. Tack J, Becher A, Mulligan C, Johnson DA. Systematic review: the burden of disruptive gastro-oesophageal reflux disease on health-related quality of life. Aliment Pharmacol Ther. 2012; 35(11): 1257-1266.
3. Herbella FA, Patti MG. Gastroesophageal reflux disease: From pathophysiology to treatment. World J Gastroenterol. 2010; 16(30): 3745-3749.
4. Goh KL, Lee YY, Leelakusolvong S, et al. Consensus statements and recommendations on the management of mild-to-moderate gastroesophageal reflux disease in the Southeast Asian region. JGH Open. 2021; 5(8): 855-863. doi:10.1002/jgh3.12602.
5. Gyawali CP, Kahrilas PJ, Savarino E, et al. Modern diagnosis of GERD: the Lyon Consensus. Gut. 2018; 67(7): 1351-1362.
6. Bjørsum-Meyer T, Koulaouzidis A, Baatrup G. Comment on “Artificial intelligence in gastroenterology: A state-of-the-art review.” World J Gastroenterol. 2022; 28(16): 1722-1724.
7. Sharma P, Hassan C. Artificial Intelligence and Deep Learning for Upper Gastrointestinal Neoplasia. Gastroenterology. 2022; 162(4): 1056-1066. doi:10.1053/j.gastro.2021.11.040.
8. Chiu YC, Chen WL, Yang TW, Tsai MC, Tseng MH. A Deep Learning Model for Classification of Endoscopic Gastroesophageal Reflux Disease. Int J Environ Res Public Health. 2021; 18(5): 2428.
9. Basford PJ, Brown J, Gadeke L, et al. A randomized controlled trial of pre-procedure simethicone and N-acetylcysteine to improve mucosal visibility during gastroscopy – NICEVIS. Endosc Int Open. 2016; 4(11): E1197-E1202. doi:10.1055/s-0042-117631.
10. Sami S, Ragunath K. The Los Angeles Classification of Gastroesophageal Reflux Disease. Video Journal and Encyclopedia of GI Endoscopy. 2013; 1:103-104. doi:10.1016/S2212-0971(13)70046-3.
11. Ge H, Zhou X, Wang Y, et al. Development and Validation of Deep Learning Models for the Multiclassification of Reflux Esophagitis Based on the Los Angeles Classification. Journal of Healthcare Engineering. 2023; 2023: e7023731. doi:10.1155/2023/7023731.
12. Visaggi P, Barberio B, Gregori D, et al. Systematic review with meta-analysis: artificial intelligence in the diagnosis of oesophageal diseases. Aliment Pharmacol Ther. 2022; 55(5): 528-540.
13. Kusano M, Ino K, Yamada T, et al. Interobserver and intraobserver variation in endoscopic assessment of GERD using the “Los Angeles” classification. Gastrointestinal Endoscopy. 1999; 49(6): 700-704. doi:10.1016/S0016-5107(99)70285-3.
14. Hoshihara Y, Kogure T. What are longitudinal vessels? Endoscopic observation and clinical significance of longitudinal vessels in the lower esophagus. Esophagus. 2006; 3(4): 145-150. doi:10.1007/s10388-006-0096-2.