Keywords
endoscopic surgery
peptic ulcer disease
diagnosis
treatment
gastrointestinal tract
intelligent endoscopy
convolutional neural networks
decision support systems
Abstract
Introduction. Artificial intelligence (AI) significantly enhances gastrointestinal endoscopy by automating ulcer detection, accelerating image analysis, and improving clinical outcome prediction. The growing body of disparate data on AI algorithm efficacy necessitates systematization to define priorities and barriers for clinical implementation.
The objective is to systematize current AI applications in diagnosing peptic ulcer disease, classifying bleeding activity (Forrest classification), and predicting acute hemorrhage risk. This review also aimed to identify key gaps in the clinical validation of developed models.
Materials and methods. A systematic scoping review (PRISMA-ScR) of PubMed, Scopus, and Web of Science was conducted for the period 2010–2025. From an initial 184 records, 22 studies met inclusion criteria after screening and full-text assessment and were included in the final analysis. Results. Primary research focused on diagnostics (13/22, 59 %), complication prediction (5/22, 23 %), and clinical decision support systems (3/22, 13 %). Deep convolutional neural networks (CNN) were the dominant technology (64 %), demonstrating high diagnostic accuracy (AUC 0.82–0.96; sensitivity 76–94 %). However, robust validation was lacking: only 50 % (11/22) of studies reported internal validation, and just 27 % (6/22) included external validation, indicating insufficient reproducibility testing.
Discussion. AI algorithms show high accuracy, sometimes exceeding endoscopist performance, especially during active bleeding. Yet, clinical implementation is hindered by low reproducibility on external cohorts, a scarcity of prospective multicenter trials, IT integration challenges, and heterogeneous reporting standards.
Conclusion. AI is a promising tool for improving diagnosis and risk stratification in peptic ulcer disease. However, its full integration into clinical practice demands standardized validation protocols, uniform clinical endpoints, and studies assessing AI’s real-world impact on treatment strategies and patient outcomes.
For citation
Zhilyakov AV, Sokolov SY, Chernyadev SA, Zhilyakov AA. The use of artificial intelligence in endoscopic diagnosis and treatment of gastrointestinal ulcers: A thematic overview. USMU Medical Bulletin. 2026;11(1):e00207. DOI: https://doi.org/10.52420/usmumb.11.1.e00207. EDN: https://elibrary.ru/SBOOSD.
References
Lanas A, Chan FKL. Peptic ulcer disease. The Lancet. 2017;390(10094):613–624. DOI: https://doi.org/10.1016/S0140-6736(16)32404-7.
Srivastav Y, Mansoori MF, Hameed A, Hashmi A, Ahmad MI. Condensed statement: Critical framework of the diagnosis along with management of peptic ulcer disease (PUD). In: Marinho SA (ed.). Advanced Concepts in Pharmaceutical Research. Vol. 8. BP International; 2024. P. 90–111. DOI: https://doi.org/10.9734/BPI/ACPR/V8/8357E.
Parkash O, Siddiqui ATS, Jiwani U, Rind F, Padhani ZA, Rizvi A, et al. Diagnostic accuracy of artificial intelligence for detecting gastrointestinal luminal pathologies: A systematic review and meta-analysis. Frontiers in Medicine. 2022;9:1018937. DOI: https://doi.org/10.3389/fmed.2022.1018937.
Correia FP, Lourenço LC. Artificial intelligence application in diagnostic gastrointestinal endoscopy — Deus ex machina? World Journal of Gastroenterology. 2021;27(32):5351–5361. DOI: https://doi.org/10.3748/wjg.v27.i32.5351.
Tian Z, Wang D, Sun X, Fan Y, Guan Y, Zhang N, et al. Current status and trends of artificial intelligence research on the four traditional Chinese medicine diagnostic methods: A scientometric study. Annals of Translational Medicine. 2023;11(3):145. DOI: https://doi.org/10.21037/atm-22-6431.
Zhu N, Cao J, Shen K, Chen X, Zhu S. A decision support system with intelligent recommendation for multi-disciplinary medical treatment. ACM Transactions on Multimedia Computing, Communications, and Applications. 2020;16(1s):33. DOI: https://doi.org/10.1145/3352573.
Mota J, Almeida MJ, Mendes F, Martins M, Ribeiro T, Afonso J, et al. From data to insights: How is AI revolutionizing small-bowel endoscopy? Diagnostics. 2024;14(3):291. DOI: https://doi.org/10.3390/diagnostics14030291.
Жиляков АВ, Чернядьев СА, Коробова НЮ, Киршина ОВ, Соколов СЮ, Белькова КС, и др., авторы; УГМУ, правообладатель. Программа для автоматической классификации желудочно-кишечных кровотечений по шкале J. A. Forrest. РФ, свидетельство о гос. регистрации прогр. для ЭВМ RU2023615451. 15 марта 2023. [Zhilyakov AV, Chernyadyev SA, Korobova NY, Kirshina OV, Sokolov SY, Belkova KS, et al., inventors; Ural State Medical University, assignee. Program for automatic classification of gastrointestinal ulcer bleeding according to the J. A. Forrest scale. Russian Federation certificate of state registration of a computer program RU2023615451. 15 March 2023. (In Russ.)]. EDN: https://elibrary.ru/UOJRRS.
Yen HH, Wu PY, Wu TL, Huang SP, Chen YY, Chen MF, et al. Forrest classification for bleeding peptic ulcer: A new look at the old endoscopic classification. Diagnostics. 2022;12(5):1066. DOI: https://doi.org/10.3390/diagnostics12051066.
Tan Q, Ye M, Ma AJ, Yang B, Yip TCF, Wong GLH, et al. Explainable uncertainty-aware convolutional recurrent neural network for irregular medical time series. IEEE Transactions on Neural Networks and Learning Systems. 2021;32(10):4665–4679. DOI: https://doi.org/10.1109/TNNLS.2020.3025813.
Aoki T, Yamada A, Aoyama K, Saito H, Tsuboi A, Nakada A, et al. Automatic detection of erosions and ulcerations in wireless capsule endoscopy images based on a deep convolutional neural network. Gastrointestinal Endoscopy. 2019;89(2):357–363.e2. DOI: https://doi.org/10.1016/j.gie.2018.10.027.
Pannala R, Krishnan K, Melson J, Parsi MA, Schulman AR, Sullivan S, et al. Artificial intelligence in gastrointestinal endoscopy. VideoGIE. 2020;5(12):598–613. DOI: https://doi.org/10.1016/J.VGIE.2020.08.013.
Korinteli I, Khalvashi M, Turkadze E. Modern aspects of evidence-based medicine. Experimental and Clinical Medicine Georgia. 2022;(6). DOI: https://doi.org/10.52340/JECM.2022.06.026.
Литвинов С. ResNet (34, 50, 101): «остаточные» CNN для классификации изображений. Neurohive. 29 января 2019. [Litvinov S. ResNet (34, 50, 101): “residual” CNNs for image classification. Neurohive. 29 January 2019. (In Russ.)]. Available from: https://clck.ru/3ST6h2 (accessed 8 October 2025).
Азизов РР, Лукьянчиков АИ. Алгоритм классификации пользователей и жестов с помощью сверточной нейронной сети на основе сигналов электромиографии. E-Scio. 2022;(5):101–110. [Azizov RR, Lukyanchikov AI. Algorithm for classifying users and gestures using a convolutional neural network based on electromyography signals. E-Scio. 2022;(5):101–110. (In Russ.)]. EDN: https://elibrary.ru/XCIRDB.
Draganov PV, Aihara H, Karasik MS, Ngamruengphong S, Aadam AA, Othman MO, et al. Endoscopic submucosal dissection in North America: A large prospective multicenter study. Gastroenterology. 2021;160(7):2317–2327.e6. DOI: https://doi.org/10.1053/j.gastro.2021.02.036.
Rasmy L, Wu Y, Wang N, Geng X, Zheng WJ, Wang F, et al. A study of generalizability of recurrent neural network-based predictive models for heart failure onset risk using a large and heterogeneous EHR data set. Journal of Biomedical Informatics. 2018;84:11–16. DOI: https://doi.org/10.1016/j.jbi.2018.06.011.
Gour S, Joshi M, Qureshi A. Artificial intelligence and intelligent computing techniques for healthcare decision support. In: Artificial Intelligence and Their Applications. 2024. P. 97–116. DOI: https://doi.org/10.58532/nbennurch58.
Byrne MF, Chapados N, Soudan F, Oertel C, Linares Pérez M, Kelly R, et al. Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model. Gut. 2019;68(1):94–100. DOI: https://doi.org/10.1136/gutjnl-2017-314547.
Ebigbo A, Mendel R, Probst A, Manzeneder J, Souza LA Jr, Papa JP, et al. Computer-aided diagnosis using deep learning in the evaluation of early oesophageal adenocarcinoma. Gut. 2019;68(7):1143–1145. DOI: https://doi.org/10.1136/gutjnl-2018-317573.
Carrinho P, Falcao G. Highly accurate and fast YOLOv4-based polyp detection. Expert Systems with Applications. 2023;232:120834. DOI: https://doi.org/10.1016/j.eswa.2023.120834.
Kim YS, Lee SM, Yuk JC, Park SH. Real-time defect detection in wire-laser directed energy deposition process using U-Net-based semantic segmentation. International Journal of Precision Engineering and Manufacturing-Smart Technology. 2025;3(1):39–52. DOI: https://doi.org/10.57062/ijpem-st.2024.00178.
Triester SL, Leighton JA, Leontiadis GI, Fleischer DE, Hara AK, Heigh RI, et al. A meta-analysis of the yield of capsule endoscopy compared to other diagnostic modalities in patients with obscure gastrointestinal bleeding. American Journal of Gastroenterology. 2005;100(11):2407–2418. DOI: https://doi.org/10.1111/j.1572-0241.2005.00274.x.
Nehme F, Feldman K. Evolving role and future directions of natural language processing in gastroenterology. Digestive Diseases and Sciences. 2021;66(1):29–40. DOI: https://doi.org/10.1007/s10620-020-06156-y.
Simsek C, Aydinli H, Yazarkan Y, Bozdogan AB, Tinaz B, Melihcan HS, et al. Gastroenterology-specific AI model GastroGPT outperforms attending physicians’ and ChatGPT in analyses of clinical notes of real-world endoscopy cases. Endoscopy. 2024;56(S2):S142. DOI: https://doi.org/10.1055/s-0044-1782999.
Zecevic A, Jackson L, Zhang X, Pavlidis P, Dunn J, Trudgill N, et al. Automated decision making in Barrett’s oesophagus: Development and deployment of a natural language processing tool. npj Digital Medicine. 2024;7(1):312. DOI: https://doi.org/10.1038/s41746-024-01302-6.
Vadyala SR, Sherer EA. Natural language processing accurately categorizes indications, findings, and pathology reports from multicenter colonoscopy [preprint]. 2021. DOI: https://doi.org/10.20944/preprints202301.0061.v1.
Larsen SLV, Mori Y. Artificial intelligence in colonoscopy: A review on the current status. DEN Open. 2022;2(1):e109. DOI: https://doi.org/10.1002/deo2.109.
Fleischmann C, Probst A, Ebigbo A, Faiss S, Schumacher B, Allgaier HP, et al. Endoscopic submucosal dissection in Europe: Results of 1000 neoplastic lesions from the German endoscopic submucosal dissection registry. Gastroenterology. 2021;161(4):1168–1178. DOI: https://doi.org/10.1053/j.gastro.2021.06.049.
Choi E, Schuetz A, Stewart WF, Sun J. Using recurrent neural network models for early detection of heart failure onset. Journal of the American Medical Informatics Association. 2017;24(2):361–370. DOI: https://doi.org/10.1093/jamia/ocw112.
Nazir S, Dickson DM, Akram MU. Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks. Computers in Biology and Medicine. 2023;156:106668. DOI: https://doi.org/10.1016/j.compbiomed.2023.106668.
Mukhtorov D, Rakhmonova M, Muksimova S, Cho YI. Endoscopic image classification based on explainable deep learning. Sensors. 2023;23(6):3176. DOI: https://doi.org/10.3390/s23063176.
Ustabaşı KN. What are the challenges and opportunities of integrating AI into existing healthcare infrastructure? Next Frontier for Life Sciences and AI. 2024;8(1):141. DOI: https://doi.org/10.62802/dvmbnm16.
Nelson S, Saranya R. Revolutionizing health records: The AI way. International Journal of Science and Research. 2024;13(4):1310–1313. DOI: https://doi.org/10.21275/sr24417190214.
Alyami MSM, Alyami MMM, Khuraim HAM, Alsalem AMS, Alrayshan HAM, Albakri KAM, et al. Integrating artificial intelligence across medical clinics: Strengthening collaborative efforts for improved patient outcomes. Journal of Ecohumanism. 2024;3(7):2691–2698. DOI: https://doi.org/10.62754/joe.v3i7.4668.
Karalis V. The integration of artificial intelligence into clinical practice. Applied Biosciences. 2024;3(1):14–44. DOI: https://doi.org/10.3390/applbiosci3010002.
İlikhan SU, Özer M, Tanberkan H, Bozkurt V. How to mitigate the risks of deployment of artificial intelligence in medicine? Turkish Journal of Medical Sciences. 2024;54(3):483–492. DOI: https://doi.org/10.55730/1300-0144.5814.
Singh P, Chakurkar P. Deep learning based Wireless Capsule Endoscopy for Small Intestinal Lesions Detection and personalized treatment pathways. In: 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT). 2023. P. 1–8. DOI: https://doi.org/10.1109/icccnt56998.2023.10307509.
Yen HH, Wu PY, Su PY, Yang CW, Chen YY, Chen MF, et al. Performance comparison of the deep learning and the human endoscopist for bleeding peptic ulcer disease. Journal of Medical and Biological Engineering. 2021;41(4):504–513. DOI: https://doi.org/10.1007/s40846-021-00608-0.
Swied MY, Alom M, Daaboul O, Swied A. Screening and diagnostic advances of artificial intelligence in endoscopy. Innovations in Digital Health, Diagnostics, and Biomarkers. 2024;4:31–43. DOI: https://doi.org/10.36401/iddb-23-15.
Shi Y, Wei N, Wang K, Tao T, Yu F, Lv B. Diagnostic value of artificial intelligence-assisted endoscopy for chronic atrophic gastritis: a systematic review and meta-analysis. Frontiers in Medicine. 2023;10:1134980. DOI: https://doi.org/10.3389/fmed.2023.1134980.
Wang M, Chen S, Zhong C, Zhang T, Xu YX, Guo HY, et al. Diagnosis using artificial intelligence based on the endocytoscopic observation of the gastrointestinal tumours: A systematic review and meta-analysis. Inplasy protocol 202320096. Inplasy. 22 February 2023. DOI: https://doi.org/10.37766/inplasy2023.2.0096.
Seshia SA, Sadigh D, Sastry SS. Toward verified artificial intelligence. Communications of the ACM. 2022;65(7):46–55. DOI: https://doi.org/10.1145/3503914.
Kuleshov A. Formalizing AI system parameters in standardization of AI. In: 2018 International Conference on Artificial Intelligence Applications and Innovations (IC-AIAI). 2018. P. 51–54. DOI: https://doi.org/10.1109/IC-AIAI.2018.8674446.
Hand DJ, Khan S. Validating and verifying AI systems. Patterns. 2020;1(3):100037. DOI: https://doi.org/10.1016/j.patter.2020.100037.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
Copyright © 2026 Zhilyakov A. V., Sokolov S. Y., Chernyadev S. A., Zhilyakov A. A.