Diagnostic Accuracy of Artificial Intelligence in Endoscopy: Umbrella Review

Abstract

Background: Some research has already reported the diagnostic value of artificial intelligence (AI) in different endoscopy outcomes. However, the evidence is confusing and of varying quality. Objective: To comprehensively evaluate the credibility of the evidence of the diagnostic accuracy of artificial intelligence in endoscopy. Methods: Before the study began, the protocol was registered in the International prospective register of systematic reviews (CRD42023483073). Firstly, two researchers searched PubMed, Web of Science, Embase, and Cochrane Library using comprehensive search terms. The deadline is November 2023. Then, researchers conduct screening research and extract information. We use A Measurement Tool to Assess Systematic Reviews 2 (AMSTAR2) to evaluate the quality of the article. We choose the research with higher quality evaluation for the same outcome for further analysis. In order to ensure the reliability of the conclusion, we have calculated each outcome again. Finally, the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) is used to evaluate the credibility of the outcome. Results: A total of 21 studies were included for analysis. Through AMSTAR2, it was found that eight research methodologies were of moderate quality, while other studies were regarded as low or critical low. The sensitivity and specificity of 17 different outcomes were analyzed. There are four different outcomes related to the esophagus, stomach, and colorectal, respectively. Two outcomes are associated with capsule endoscopy and laryngoscope, respectively. While the other is related to ultrasonic endoscopy. In terms of sensitivity, gastroesophageal reflux disease has the highest accuracy rate, reaching 97%, while the invasion depth of colon neoplasia has the lowest accuracy rate, only 71%. On the other hand, the specificity of colorectal cancer is the highest, reaching 98%, while the gastrointestinal stromal tumor has the lowest, only 80%. The GRADE evaluation suggests that the reliability of most outcomes are evaluated as low or very low. Conclusions: AI shows the value of diagnosis in endoscopy, especially in esophageal and colorectal diseases. These findings provide a theoretical basis for the development and evaluation of the use of AI-assisted systems, which are aimed at assisting endoscopists to carry out examinations to improve human health. However, it is worth noting further high-quality research is needed in the future.