Endoscopist Characteristics May Predict Improved Detection With CADe
Douglas K. Rex, MD, MASGE, reviewing Shaukat A, et al. Am J Gastroenterol 2023 Aug 24.
Most randomized controlled trials (RCTs) of computer-aided detection (CADe) demonstrate increased detection, but some RCTs and real-world experiences with CADe have failed to show a benefit. This has created uncertainty regarding CADe benefits, and the underlying reasons for disparate results remain elusive.
In a post hoc analysis of a previous RCT that showed a benefit of increased adenomas per colonoscopy (APC), the authors calculated z scores to determine whether the APC of certain groups significantly deviated from the mean APC of the comparator group. Based on these results, CADe was associated with more of an increase in APC for community-based endoscopists (APC increase, 0.258) compared with academic endoscopists (APC increase, 0.178). There was also a numerically higher increase in APC with a withdrawal time ≥8 minutes (0.213) versus <8 minutes (-0.026), as well as a higher increase for endoscopists with a baseline adenoma detection rate <45% (0.297) compared with a baseline ADR ≥45% (0.098). Further, the APC increase was higher for endoscopists with more than 20 years of experience (0.279) versus endoscopists with 1 to 10 years of experience (-0.035). All these differences were trends that did not reach statistical significance.
Note to readers: At the time we reviewed this paper, its publisher noted that it was not in final form and that subsequent changes might be made.
CITATION(S)
Shaukat A, Lichtenstein DR, Chung DC, et al. Endoscopist and procedure-level factors associated with increased adenoma detection with the use of a computer-aided detection (CADe) device. Am J Gastroenterol2023 Aug 24. (Epub ahead of print) (https://doi.org/10.14309/ajg.0000000000002479)