Impact of Availability of Computer-Aided Detection Devices on Adenoma Detection During Colonoscopy: A Cluster Randomized Study.
Jason A Dominitz, Andrew J Gawron, Grace B McKee et al.
✦ AI-curated · Sources linked
In 30 seconds
This pragmatic, multicentre cluster-randomised quality improvement study assessed whether making computer-aided detection (CADe) devices available affected adenoma detection during colonoscopy at Veterans Health Administration facilities. Across 42 CADe and 97 control facilities, adenoma detection rate (ADR) rose from 50.7% to 54.9% at CADe sites, an absolute increase of 4.2 percentage points (95% CI, 3.48 to 4.74 percentage points); at control sites, ADR fell from 51.8% to 51.1%. In adjusted analysis, CADe availability was associated with higher odds of adenoma detection (odds ratio, 1.22; 95% CI, 1.15 to 1.28), without changes in other lesion detection or withdrawal time.
Key findings
- ADR increased by 4.2 percentage points (95% CI, 3.48 to 4.74 percentage points), from 50.7% to 54.9%, at CADe sites.
- At control sites, ADR decreased by 0.7 percentage points (95% CI, -1.16 to -0.28 percentage points), from 51.8% to 51.1%.
- CADe availability was associated with higher odds of adenoma detection (odds ratio, 1.22; 95% CI, 1.15 to 1.28), but not with detection of other lesions or withdrawal-time changes.
- Baseline endoscopist ADR quintile was not associated with the effect of CADe availability on ADR.
Why it matters
Adenoma detection is clinically relevant because endoscopists’ ADRs are inversely associated with patients’ risk of postcolonoscopy colorectal cancer death. This pragmatic study found improved adenoma detection when CADe was available in routine practice, addressing uncertainty from real-world studies that had generally not shown benefit. Whether the observed detection increase improves cancer outcomes remains unknown.
What to keep in mind
The study did not determine effects on cancer outcomes or potential endoscopist deskilling.