Computer-Aided Diagnosis System Bombs in a Real-World Colon Polyp Histology Prediction Trial

Computer-Aided Diagnosis System Bombs in a Real-World Colon Polyp Histology Prediction Trial

Douglas K. Rex, MD, MASGE, reviewing Weiquan Li J, et al. Am J Gastroenterol 2023 Apr 11.

In a prospective study from Singapore, the computer-aided diagnosis (CADx) program CAD EYE (Fujifilm, Tokyo, Japan) was assessed in 661 consecutive polyps of all sizes in 320 patients. The findings revealed that 61.7% of polyps were neoplastic. The overall accuracy of CADx prediction was 71.6%, which was lower than that for the endoscopists (75.2%). CADx sensitivity for neoplastic polyps was 61.8% versus 70.3% for the endoscopists. For polyps ≤5 mm, CADx sensitivity was 53.6% versus 62.7% for endoscopists. CADx performed worse when polyps were in difficult locations. It also performed worse for inexperienced endoscopists compared with experienced endoscopists.

Both CADx (80.6%) and endoscopists (83.3%) had low negative predictive value for diminutive rectosigmoid polyps. With regard to supporting the resect-and-discard paradigm, CADx for diminutive lesions plus histology for lesions >5 mm produced agreement in surveillance intervals (using the U.S. Multisociety Task Force on Colorectal Cancer recommendations) in 70.8% of cases. Endoscopist prediction resulted in agreement in 71.9%.

Douglas K. Rex, MD, FASGE

COMMENT

These results are among the worst yet for a CADx program studied for real-time performance. These findings indicate that this CADx program, when used by these operators, is insufficient to support either a “leave in situ” paradigm for diminutive rectosigmoid hyperplastic polyps or a “resect-and-discard” paradigm. Other CADx programs, and this one when used by different endoscopists, have produced results comparable to those of expert endsocopists.

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)

Weiquan Li J, Ho Wu CC, Jie Lee JW, et al. Real-world validation of a computer-aided diagnosis system for prediction of polyp histology in colonoscopy: a prospective multicenter study. Am J Gastroenterol 2023 Apr 11. (Epub ahead of print) (https://doi.org/10.14309/ajg.0000000000002282)

Ähnliche Beiträge

VOR
Nach oben scrollen