Artificial Intelligence for Real-Time Prediction of the Histology of Colorectal Polyps by General Endoscopists

被引：13

作者：

Rex, Douglas K. ^{[1
]}

Bhavsar-Burke, Indira ^{[1
]}

Buckles, Daniel ^{[2
]}

Burton, James ^{[3
]}

Cartee, Amanda ^{[4
]}

Comar, Kevin ^{[5
]}

Edwards, Adam ^{[4
]}

Fennimore, Blair ^{[3
]}

Fischer, Monika ^{[1
]}

Gerich, Mark ^{[3
]}

Gilmore, Ashley ^{[1
]}

Hamdeh, Shadi ^{[2
]}

Hoffman, Jeffrey ^{[5
]}

Ibach, Michael ^{[5
]}

Jackson, Mollie ^{[2
]}

James-Stevenson, Toyia ^{[1
]}

Kaltenbach, Tonya ^{[6
]}

Kaplan, Jeffrey ^{[3
]}

Kapur, Saurabh ^{[2
]}

Kohm, Daniel ^{[5
]}

Kriss, Michael ^{[3
]}

Kundumadam, Shanker ^{[1
]}

Baig, Kondal R. Kyanam Kabir ^{[4
]}

Menard-Katcher, Paul ^{[3
]}

Kraft, Cary ^{[6
]}

Langworthy, James ^{[2
]}

Misra, Bharat ^{[5
]}

Molloy, Eric ^{[2
]}

Munoz, Juan Carlos ^{[5
]}

Norvell, John ^{[3
]}

Nowak, Thomas ^{[1
]}

Obaitan, Itegbemie ^{[1
]}

Patel, Swati ^{[3
]}

Patel, Mitesh ^{[2
]}

Peter, Shajan ^{[4
]}

Reid, B. Marie ^{[5
]}

Rogers, Nicholas ^{[1
]}

Ross, Jason ^{[5
]}

Ryan, James ^{[6
]}

Sagi, Sashidhar ^{[1
]}

Saito, Akira ^{[1
]}

Samo, Salih ^{[2
]}

Sarkis, Fayez ^{[4
]}

Scott, Frank I. ^{[3
]}

Siwiec, Robert ^{[1
]}

Sullivan, Shelby ^{[3
]}

Wieland, Amanda ^{[3
]}

Zhang, Jianying ^{[7
]}

Repici, Alessandro ^{[8
,9
,10
]}

Hassan, Cesare ^{[8
,9
,10
,14
]}

机构：

[1] Indiana Univ Sch Med, Indianapolis, IN USA

[2] Univ Kansas Med Ctr, Kansas City, KS USA

[3] Univ Colorado Boulder, Boulder, CO USA

[4] Univ Alabama Birmingham, Birmingham, AL USA

[5] Borland Groover, Jacksonville, FL USA

[6] San Francisco VA Med Ctr, San Francisco, CA USA

[7] Olympus Corp Amer, Center Valley, PA USA

[8] Humanitas Univ, Dept Biomed Sci, Pieve Emanuele, Italy

[9] IRCCS, Humanitas Clin & Res Hosp, Rozzano, Italy

[10] IRCCS, Endoscopy Unit, Rozzano, Italy

[11] Vancouver Gen Hosp, Div Gastroenterol, Vancouver, BC, Canada

[12] Univ British Columbia, Vancouver, BC, Canada

[13] Satisfai Hlth, Vancouver, BC, Canada

[14] Humanitas Res Hosp, Humanitas Res Hosp & Univ, Via Manzoni 56, I-20089 Rozzano, Milano, Italy

来源：

ANNALS OF INTERNAL MEDICINE | 2024年 / 177卷 / 07期

关键词：

COLON POLYPS; ACCURACY; VALIDATION; DIAGNOSIS; SYSTEM;

D O I：

10.7326/M24-0086

中图分类号：

R5 [内科学];

学科分类号：

1002 ; 100201 ;

摘要：

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: The 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. 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.

引用

页码：911 / 918

页数：9

共 24 条

[1] Implementation of optical diagnosis with a "resect and discard" strategy in clinical practice: DISCARD3 study [J].