Provider Attitudes and Perceptions on Using Artificial Intelligence in Colonoscopy: A Systematic Review and...

Area of Science:

• Gastroenterology
• Medical Technology
• Artificial Intelligence

Background:

• Colonoscopy is the standard for colorectal cancer screening but is operator-dependent.
• Artificial intelligence (AI) integration in colonoscopy offers potential for improved adenoma detection.
• Successful AI implementation requires understanding provider attitudes and effective human-AI collaboration.

Purpose of the Study:

• To systematically review provider attitudes and perspectives on AI-assisted colonoscopy.
• To pool data on provider interest, perceived benefits, and concerns regarding AI in colonoscopy.

Main Methods:

• Systematic review of 13 studies involving 1538 healthcare providers.
• Analysis of pooled proportions (Pp) and 95% confidence intervals (CI) for key outcomes.
• Identification of top-ranked perceived advantages and disadvantages based on participant voting.

Main Results:

• A large majority of providers (80%) expressed interest in using AI-assisted colonoscopy.
• Most providers (74%) believed AI can enhance adenoma or polyp detection rates.
• Key concerns included cost (52%), high false positive rates, and lack of clinical guidelines.

Conclusions:

• Gastroenterology providers are generally receptive to AI in colonoscopy, anticipating improved detection rates.
• Provider acceptance is influenced by perceived benefits versus concerns about financial implications, accuracy, and regulatory frameworks.
• Addressing provider concerns is crucial for the successful integration of AI into colorectal cancer screening.