The Use of Artificial Intelligence for Endoscopic Evaluation of the Small Bowel

Abstract

There remains great potential for widespread implementation of artificial intelligence (AI) in managing small bowel disorders. Studies have shown excellent accuracy in diagnosing various diseases and lesions throughout the small bowel, with most showing equivalency or superiority to expert endoscopists or capsule readers. AI has significant potential to improve efficiency in small bowel investigation and, depending on the relative costs of these new technologies, could reduce health care expenditure. AI algorithms for capsule endoscopy will offer many clinical and efficiency benefits but we also must remain alert to new risks, particularly with regard to automation bias and unique cybersecurity considerations.

Keywords: Artificial intelligence; Automation; CADe; Capsule endoscopy; Convolutional neural networks; GI bleeding; Inflammatory bowel disease; Small bowel.