Patrick W Chang, Denis D Nguyen, Niwen Kong, Daniel Wang, Sarah Wang, Justin Ong, Maziar M Amini, Nisha Sharma, Aileen Bui, Omar Bakr, Dara Bruce, Helen Lee, Jennifer L Dodge, Ara B Sahakian, James L Buxbaum
{"title":"人工智能辅助结肠镜检查对胃肠病学同事表现的影响：一项实用的随机对照试验。","authors":"Patrick W Chang, Denis D Nguyen, Niwen Kong, Daniel Wang, Sarah Wang, Justin Ong, Maziar M Amini, Nisha Sharma, Aileen Bui, Omar Bakr, Dara Bruce, Helen Lee, Jennifer L Dodge, Ara B Sahakian, James L Buxbaum","doi":"10.1016/j.gie.2025.09.045","DOIUrl":null,"url":null,"abstract":"<p><strong>Background and aims: </strong>The substantial miss rate during screening and surveillance colonoscopy, particularly for the right side, underscores the need to improve training. The role of artificial intelligence (AI) assisted colonoscopy in the training environment has not been thoroughly defined. This study explores the impact of artificial intelligence on colonoscopy performed by trainees in a Gastroenterology (GI) fellowship program.</p><p><strong>Methods: </strong>Between March and October 2023, we randomly assigned GI fellows to artificial intelligence (AI) enhanced versus conventional colonoscopy (CC) rooms daily. Consecutive colonoscopies performed by fellows were included unless there were attending interventions, inadequate bowel preparation or incomplete colonoscopy. The primary endpoint was adenoma detection rate (ADR) defined as the proportion of colonoscopies with one or more adenomas detected. Additional outcomes included adenoma detection on the right side (RADR) and left side (LADR), the polyp detection rate (PDR), procedure (colonoscope insertion to withdrawal) and withdrawal (cecum to withdrawal) times. Mean ADR differences for the AI versus CC procedures were estimated utilizing generalized linear models.</p><p><strong>Results: </strong>A total of 1,045 colonoscopies were performed by 16 fellows. Overall ADR was similar for AI (40.5±3.9%) vs. CC (35.0±3.6%); mean difference 5.5% (95% CI: -4.3 to 15.3%). The right sided ADR was higher in AI (24.1%) versus CC (16.5%); mean difference: 7.6% (95% CI: 1.7 to 13.5%). Among 130 screening colonoscopies, ADR for AI was 49.1% vs 26.7% for CC; mean difference: 22.3% (95% CI: -2.7 to 47.4%) while RADR was higher for AI (AI: 35.1% vs CC: 13.7%); mean difference: 21.0% (95% CI: 7.6% to 35.2%). This was most pronounced for first and second year fellows. There was no difference in procedural or withdrawal time with the addition of AI.</p><p><strong>Conclusion: </strong>This pragmatic randomized controlled trial demonstrates that AI assisted colonoscopy improves RADR for gastroenterology trainees. Overall ADR was not significantly different between groups. We propose a use case via AI assisted colonoscopy for trainees guiding improvement of adenoma detection in the right colon and standardizing a critically needed colorectal cancer screening quality metric.</p>","PeriodicalId":12542,"journal":{"name":"Gastrointestinal endoscopy","volume":" ","pages":""},"PeriodicalIF":7.5000,"publicationDate":"2025-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Impact of artificial intelligence-assisted colonoscopy on gastroenterology fellow performance: A pragmatic randomized controlled trial.\",\"authors\":\"Patrick W Chang, Denis D Nguyen, Niwen Kong, Daniel Wang, Sarah Wang, Justin Ong, Maziar M Amini, Nisha Sharma, Aileen Bui, Omar Bakr, Dara Bruce, Helen Lee, Jennifer L Dodge, Ara B Sahakian, James L Buxbaum\",\"doi\":\"10.1016/j.gie.2025.09.045\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background and aims: </strong>The substantial miss rate during screening and surveillance colonoscopy, particularly for the right side, underscores the need to improve training. The role of artificial intelligence (AI) assisted colonoscopy in the training environment has not been thoroughly defined. This study explores the impact of artificial intelligence on colonoscopy performed by trainees in a Gastroenterology (GI) fellowship program.</p><p><strong>Methods: </strong>Between March and October 2023, we randomly assigned GI fellows to artificial intelligence (AI) enhanced versus conventional colonoscopy (CC) rooms daily. Consecutive colonoscopies performed by fellows were included unless there were attending interventions, inadequate bowel preparation or incomplete colonoscopy. The primary endpoint was adenoma detection rate (ADR) defined as the proportion of colonoscopies with one or more adenomas detected. Additional outcomes included adenoma detection on the right side (RADR) and left side (LADR), the polyp detection rate (PDR), procedure (colonoscope insertion to withdrawal) and withdrawal (cecum to withdrawal) times. Mean ADR differences for the AI versus CC procedures were estimated utilizing generalized linear models.</p><p><strong>Results: </strong>A total of 1,045 colonoscopies were performed by 16 fellows. Overall ADR was similar for AI (40.5±3.9%) vs. CC (35.0±3.6%); mean difference 5.5% (95% CI: -4.3 to 15.3%). The right sided ADR was higher in AI (24.1%) versus CC (16.5%); mean difference: 7.6% (95% CI: 1.7 to 13.5%). Among 130 screening colonoscopies, ADR for AI was 49.1% vs 26.7% for CC; mean difference: 22.3% (95% CI: -2.7 to 47.4%) while RADR was higher for AI (AI: 35.1% vs CC: 13.7%); mean difference: 21.0% (95% CI: 7.6% to 35.2%). This was most pronounced for first and second year fellows. There was no difference in procedural or withdrawal time with the addition of AI.</p><p><strong>Conclusion: </strong>This pragmatic randomized controlled trial demonstrates that AI assisted colonoscopy improves RADR for gastroenterology trainees. Overall ADR was not significantly different between groups. We propose a use case via AI assisted colonoscopy for trainees guiding improvement of adenoma detection in the right colon and standardizing a critically needed colorectal cancer screening quality metric.</p>\",\"PeriodicalId\":12542,\"journal\":{\"name\":\"Gastrointestinal endoscopy\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":7.5000,\"publicationDate\":\"2025-09-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Gastrointestinal endoscopy\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1016/j.gie.2025.09.045\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"GASTROENTEROLOGY & HEPATOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Gastrointestinal endoscopy","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.gie.2025.09.045","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GASTROENTEROLOGY & HEPATOLOGY","Score":null,"Total":0}
Impact of artificial intelligence-assisted colonoscopy on gastroenterology fellow performance: A pragmatic randomized controlled trial.
Background and aims: The substantial miss rate during screening and surveillance colonoscopy, particularly for the right side, underscores the need to improve training. The role of artificial intelligence (AI) assisted colonoscopy in the training environment has not been thoroughly defined. This study explores the impact of artificial intelligence on colonoscopy performed by trainees in a Gastroenterology (GI) fellowship program.
Methods: Between March and October 2023, we randomly assigned GI fellows to artificial intelligence (AI) enhanced versus conventional colonoscopy (CC) rooms daily. Consecutive colonoscopies performed by fellows were included unless there were attending interventions, inadequate bowel preparation or incomplete colonoscopy. The primary endpoint was adenoma detection rate (ADR) defined as the proportion of colonoscopies with one or more adenomas detected. Additional outcomes included adenoma detection on the right side (RADR) and left side (LADR), the polyp detection rate (PDR), procedure (colonoscope insertion to withdrawal) and withdrawal (cecum to withdrawal) times. Mean ADR differences for the AI versus CC procedures were estimated utilizing generalized linear models.
Results: A total of 1,045 colonoscopies were performed by 16 fellows. Overall ADR was similar for AI (40.5±3.9%) vs. CC (35.0±3.6%); mean difference 5.5% (95% CI: -4.3 to 15.3%). The right sided ADR was higher in AI (24.1%) versus CC (16.5%); mean difference: 7.6% (95% CI: 1.7 to 13.5%). Among 130 screening colonoscopies, ADR for AI was 49.1% vs 26.7% for CC; mean difference: 22.3% (95% CI: -2.7 to 47.4%) while RADR was higher for AI (AI: 35.1% vs CC: 13.7%); mean difference: 21.0% (95% CI: 7.6% to 35.2%). This was most pronounced for first and second year fellows. There was no difference in procedural or withdrawal time with the addition of AI.
Conclusion: This pragmatic randomized controlled trial demonstrates that AI assisted colonoscopy improves RADR for gastroenterology trainees. Overall ADR was not significantly different between groups. We propose a use case via AI assisted colonoscopy for trainees guiding improvement of adenoma detection in the right colon and standardizing a critically needed colorectal cancer screening quality metric.
期刊介绍：
Gastrointestinal Endoscopy is a journal publishing original, peer-reviewed articles on endoscopic procedures for studying, diagnosing, and treating digestive diseases. It covers outcomes research, prospective studies, and controlled trials of new endoscopic instruments and treatment methods. The online features include full-text articles, video and audio clips, and MEDLINE links. The journal serves as an international forum for the latest developments in the specialty, offering challenging reports from authorities worldwide. It also publishes abstracts of significant articles from other clinical publications, accompanied by expert commentaries.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
