Gastroenterology & Artificial Intelligence: 3rd Annual Global Artificial Intelligence Summit | September 2021-How to Evaluate AI in the GI Literature and Clinical Trials

Video Transcription

Video Summary

In this transcription of a video, the speaker discusses the implementation of artificial intelligence (AI) in gastrointestinal (GI) endoscopy. They emphasize the importance of evaluating the GI literature and using large data sets of images in order to assess the effectiveness and value of AI in clinical practice. The speaker introduces Cesare Hassan, a renowned endoscopist researcher, who discusses the different phases of the innovation cycle for AI in GI endoscopy. They explain that AI standalone performance studies have shown that AI can accurately detect and characterize lesions in images, but there are still concerns about the lack of understanding regarding how AI algorithms work. The speaker emphasizes the need for randomized trials to evaluate the real-world benefits and consequences of using AI in endoscopy. They also highlight the importance of considering training and testing data sets, potential biases, and the value of AI in terms of costs and cancer prevention. The speaker concludes by stating that careful evaluation and consideration of all aspects of AI implementation in endoscopy are necessary for acceptance and reimbursement.

Asset Subtitle

Cesare Hassan, MD

Keywords

artificial intelligence

gastrointestinal endoscopy

GI literature

large data sets

AI algorithms