• Douglas K Rex, Indira Bhavsar-Burke, Daniel Buckles, James Burton, Amanda Cartee, Kevin Comar, Adam Edwards, Blair Fennimore, Monika Fischer, Mark Gerich, Ashley Gilmore, Shadi Hamdeh, Jeffrey Hoffman, Michael Ibach, Mollie Jackson, Toyia James-Stevenson, Tonya Kaltenbach, Jeffrey Kaplan, Saurabh Kapur, Daniel Kohm, Michael Kriss, Shanker Kundumadam, Kondal R Kyanam Kabir Baig, Paul Menard-Katcher, Cary Kraft, James Langworthy, Bharat Misra, Eric Molloy, Juan Carlos Munoz, John Norvell, Thomas Nowak, Itegbemie Obaitan, Swati Patel, Mitesh Patel, Shajan Peter, B Marie Reid, Nicholas Rogers, Jason Ross, James Ryan, Sashidhar Sagi, Akira Saito, Salih Samo, Fayez Sarkis, Frank I Scott, Robert Siwiec, Shelby Sullivan, Amanda Wieland, Jianying Zhang, Alessandro Repici, Cesare Hassan, Michael F Byrne, and Amit Rastogi.
• Indiana University School of Medicine, Indianapolis, Indiana (D.K.R., I.B., M.F., A.G., T.J., S.K., T.N., I.O., N.R., S.S., A.S., R.S.).
• Ann. Intern. Med. 2024 Jul 1; 177 (7): 911918911-918.

BackgroundReal-time prediction of histologic features of small colorectal polyps may prevent resection and/or pathologic evaluation and therefore decrease colonoscopy costs. Previous studies showed that computer-aided diagnosis (CADx) was highly accurate, though it did not outperform expert endoscopists.ObjectiveTo assess the diagnostic performance of histologic predictions by general endoscopists before and after assistance from CADx in a real-life setting.DesignProspective, multicenter, single-group study. (ClinicalTrials.gov: NCT04437615).Setting6 centers across the United States.Participants1252 consecutive patients undergoing colonoscopy and 49 general endoscopists with variable experience in real-time prediction of polyp histologic features.InterventionReal-time use of CADx during routine colonoscopy.MeasurementsThe primary end points were the sensitivity and specificity of CADx-unassisted and CADx-assisted histologic predictions for adenomas measuring 5 mm or less. For clinical purposes, additional estimates according to location and confidence level were provided.ResultsThe CADx device made a diagnosis for 2695 polyps measuring 5 mm or less (96%) in 1252 patients. There was no difference in sensitivity between the unassisted and assisted groups (90.7% vs. 90.8%; P = 0.52). Specificity was higher in the CADx-assisted group (59.5% vs. 64.7%; P < 0.001). Among all 2695 polyps measuring 5 mm or less, 88.2% and 86.1% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be resected and discarded without pathologic evaluation. Among 743 rectosigmoid polyps measuring 5 mm or less, 49.5% and 47.9% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be left in situ without resection.LimitationDecision making based on CADx might differ outside a clinical trial.ConclusionCADx assistance did not result in increased sensitivity of optical diagnosis. Despite a slight increase, the specificity of CADx-assisted diagnosis remained suboptimal.Primary Funding SourceOlympus America Corporation served as the clinical study sponsor.

22 keywords...

hide…