Artificial Intelligence-Assisted Colonoscopy With or Without Mucosal Exposure Device for Detection of Colorectal...

Area of Science:

• Gastroenterology
• Medical Technology
• Artificial Intelligence in Medicine

Background:

• Artificial intelligence (AI) and devices like Endocuff have individually enhanced adenoma detection rates (ADR) in colonoscopies.
• This study investigates the synergistic effect of combining Endocuff with AI versus AI alone.

Purpose of the Study:

• To evaluate the combined impact of Endocuff and AI on colorectal neoplasia detection rates.
• To compare the adenoma detection rate (ADR) and advanced adenoma detection rate (AADR) between the Endocuff+AI and AI alone groups.

Main Methods:

• A meta-analysis of three randomized controlled trials (RCTs) involving 2404 subjects.
• Compared outcomes including ADR, AADR, sessile serrated lesion detection rate (SSLDR), cecal intubation time, and withdrawal time.
• Utilized a random-effects model to calculate pooled risk ratios (RRs) and mean differences (MDs) with 95% confidence intervals (CIs).

Main Results:

• The Endocuff+AI group showed a significantly higher ADR (54% vs. 48%, RR 1.12, P=0.01).
• Trends towards higher AADR and SSLDR in the Endocuff+AI group did not reach statistical significance.
• Cecal intubation and withdrawal times were comparable between the two groups.

Conclusions:

• Combining Endocuff with AI significantly improves the adenoma detection rate (ADR) in colonoscopies.
• This combined approach is superior to AI alone for ADR enhancement.
• The use of Endocuff with AI does not increase procedural time.