ASGE Annual Postgraduate Course: Clinical Challenges and Real-Time Decision Making in GI Endoscopy (Live and Virtual)

Video Transcription

Video Summary

The video transcript features a panel discussion on the value and outcomes of AI in medical fields such as cancer prevention and endoscopy. The panelists, Michael, Cesare, Naina, Sham, and Nicholas, discuss topics such as the time it takes to see the impact of AI on main outcomes like cancer incidence and mortality, the value of AI in endoscopy based on intermediate outcomes, the need for AI developers to accept liability, and the transparency of data on training sets for AI algorithms. They also touch on the importance of standardized training sets and the need for real-world data and ongoing audits to track AI performance over time. The panelists express the need for clinicians to be aware of population biases and the potential for malpractice insurance specifically for AI. The discussion concludes with a classification of AI as either autonomous, augmented, or assistive, depending on the level of trust and reliance on the AI system.<br /><br />Note: The summary does not include the Q&A portion of the video.

Asset Subtitle

Michael Abramoff, MD, Nicholas Petrick, PhD, Nayantara Coelho-Prabhu, MD,FASGE,Shyam Thakkar, MD, FASGE

Keywords

AI in medical fields

cancer prevention

endoscopy

transparency of data

AI performance