Artificial Intelligence for Real-Time Prediction of the Histology of Colorectal Polyps by General Endoscopists
Douglas K. Rex, Indira Bhavsar-Burke, Daniel Buckles, James R. Burton, Amanda K. Cartee, Kevin M. Comar, Adam Edwards, Blair Fennimore, Monika Fischer, Mark E. Gerich, Ashley C. Gilmore, Shadi Hamdeh, J. C. Hoffman, Michael B. Ibach, Mollie Jackson, Toyia N. 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 Muñoz, John P. Norvell, Thomas Nowak, Itegbemie Obaitan, Swati Patel, Mitesh Patel, Shajan Peter, BJ Reid, Nicholas Rogers, Jason Ross, James C. Ryan, Sashidhar Sagi, Akira Saito, Salih Samo, Fayez Sarkis, Frank I. Scott, Robert M. Siwiec, Shelby Sullivan, Amanda Wieland, Jianying Zhang, Alessandro Repici, Cesare Hassan, Michael F. Byrne, Amit Rastogi
Abstract
BACKGROUND: Real-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. OBJECTIVE: To assess the diagnostic performance of histologic predictions by general endoscopists before and after assistance from CADx in a real-life setting. DESIGN: Prospective, multicenter, single-group study. (ClinicalTrials.gov: NCT04437615). SETTING: 6 centers across the United States. PARTICIPANTS: 1252 consecutive patients undergoing colonoscopy and 49 general endoscopists with variable experience in real-time prediction of polyp histologic features. INTERVENTION: Real-time use of CADx during routine colonoscopy. MEASUREMENTS: The 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. RESULTS: < 0.001) in the CADx-assisted and unassisted groups, respectively, could be left in situ without resection. LIMITATION: Decision making based on CADx might differ outside a clinical trial. CONCLUSION: CADx assistance did not result in increased sensitivity of optical diagnosis. Despite a slight increase, the specificity of CADx-assisted diagnosis remained suboptimal. PRIMARY FUNDING SOURCE: Olympus America Corporation served as the clinical study sponsor.