Background: Endoscopy is the optimal choice of diagnosis of gastrointestinal (GI) diseases. Following the advancements made in medical technology, different kinds of novel endoscopy-methods have emerged. Although the significant progress in the penetration of endoscopic tools that have markedly improved the diagnostic rate of GI diseases, there are still some limitations, including instability of human diagnostic performance caused by intensive labor burden and high missed diagnosis rate of subtle lesions. Recently, artificial intelligence (AI) has been applied gradually to assist endoscopists in addressing these issues.
Methods and results: In this study, we provide an overview of the application of the AI technology in the field of endoscopy, as well as its current limitations and prospects. The result suggested that AI had a significantly higher diagnostic accuracy compared with human endoscopists in the diagnosis of GI diseases. With the help of AI technology, the diagnostic performances of nonexpert endoscopists had been improved considerably.
Conclusion: AI technology still has several limitations, and there are still plenty of opportunities for improvement.
Copyright © 2020 The Author(s). Published by Wolters Kluwer Health, Inc.