Does computer-aided diagnostic endoscopy improve the detection of commonly missed polyps? A meta-analysis

Area of Science:

• Gastroenterology
• Medical Technology
• Oncology

Background:

• Colonoscopy is the standard for detecting colorectal neoplasia, but misses common adenomas.
• Diminutive (≤5 mm) and nonpedunculated polyps are frequently overlooked during colonoscopy.
• Computer-aided detection (CADe) systems aim to enhance real-time lesion identification during endoscopy.

Purpose of the Study:

• To evaluate the effectiveness of CADe systems in improving the real-time detection of commonly missed colorectal adenomas.
• To assess CADe system performance based on polyp morphology and lesion size.

Main Methods:

• A meta-analysis of randomized controlled trials was conducted.
• Studies involving CADe-assisted and conventional colonoscopies were included.
• Data on adenoma detection rates were analyzed using random-effects modeling.

Main Results:

• CADe-assisted colonoscopy showed an 80% increase in detecting diminutive adenomas per patient (0.31 vs. 0.17).
• A 91.7% increase in detecting nonpedunculated adenomas per patient was observed with CADe (0.32 vs. 0.19).
• Seven studies with 2,595 CADe-assisted and 2,622 conventional colonoscopies were analyzed.

Conclusions:

• CADe-assisted endoscopy significantly boosts the detection of frequently missed adenomas.
• This technology shows promise for improving colonoscopy outcomes.
• Further real-time studies are needed to address current data limitations.