Impacto en el mundo real de la inteligencia artificial en la detección de adenomas: estudio transversal en un solo centro, Lima, Perú

IF 2 Q3 GASTROENTEROLOGY & HEPATOLOGY

Revista de Gastroenterologia de Mexico Pub Date : 2026-04-01 Epub Date: 2025-11-22 DOI:10.1016/j.rgmx.2025.09.006

B. Guillen, R. Zambrano-Huailla, J.A. Chirinos

{"title":"Impacto en el mundo real de la inteligencia artificial en la detección de adenomas: estudio transversal en un solo centro, Lima, Perú","authors":"B. Guillen, R. Zambrano-Huailla, J.A. Chirinos","doi":"10.1016/j.rgmx.2025.09.006","DOIUrl":null,"url":null,"abstract":"<div><h3>Introduction</h3><div>The use of artificial intelligence (AI) in endoscopic studies has grown in recent years. The present study evaluates the performance of AI in detecting polyps and adenomas in daily clinical practice.</div></div><div><h3>Materials and methods</h3><div>A cross-sectional study was conducted, in which AI-assisted colonoscopies (AIACs) performed between January 2021 and May 2024 were reviewed. Logistic regression was applied for adenoma detection, based on their characteristics.</div></div><div><h3>Results</h3><div>A total of 1,251 colonoscopies were reviewed. The patients in the AIAC group were older than the control group (59±13 vs. 56±12 years, <em>P</em><.05). There were no differences between sex, procedure indication, bowel preparation, and procedure time. Regarding the primary aim, the AIAC group had a significantly higher polyp detection rate (58 vs. 52%; <em>P</em><.05) and non-significantly higher adenoma detection rate (39 vs. 33%; <em>P</em>>.05), compared with the control group. In the analysis of adenoma characteristics, the identification of polypoid adenomas (OR: 1.28; 95% CI: 1.04-1.59), smaller 10mm (OR: 1.41; 95% CI: 1.14-1.74), and located in the proximal colon (OR: 1.31; 95% CI: 1.05-1.65) was significantly higher in the AIAC group, compared with the control group.</div></div><div><h3>Conclusions</h3><div>The use of AI in colonoscopies resulted in a non-significant increase in the adenoma detection rate but a significant increase in detecting polypoid adenomas smaller than 10mm and located in the proximal colon.</div></div>","PeriodicalId":51767,"journal":{"name":"Revista de Gastroenterologia de Mexico","volume":"91 2","pages":"Pages 200-206"},"PeriodicalIF":2.0000,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Revista de Gastroenterologia de Mexico","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0375090625001727","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/11/22 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"GASTROENTEROLOGY & HEPATOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Introduction

The use of artificial intelligence (AI) in endoscopic studies has grown in recent years. The present study evaluates the performance of AI in detecting polyps and adenomas in daily clinical practice.

Materials and methods

A cross-sectional study was conducted, in which AI-assisted colonoscopies (AIACs) performed between January 2021 and May 2024 were reviewed. Logistic regression was applied for adenoma detection, based on their characteristics.

Results

A total of 1,251 colonoscopies were reviewed. The patients in the AIAC group were older than the control group (59 ± 13 vs. 56 ± 12 years, P<.05). There were no differences between sex, procedure indication, bowel preparation, and procedure time. Regarding the primary aim, the AIAC group had a significantly higher polyp detection rate (58 vs. 52%; P<.05) and non-significantly higher adenoma detection rate (39 vs. 33%; P>.05), compared with the control group. In the analysis of adenoma characteristics, the identification of polypoid adenomas (OR: 1.28; 95% CI: 1.04-1.59), smaller 10 mm (OR: 1.41; 95% CI: 1.14-1.74), and located in the proximal colon (OR: 1.31; 95% CI: 1.05-1.65) was significantly higher in the AIAC group, compared with the control group.

Conclusions

The use of AI in colonoscopies resulted in a non-significant increase in the adenoma detection rate but a significant increase in detecting polypoid adenomas smaller than 10 mm and located in the proximal colon.

Abstract Image

查看原文本刊更多论文

人工智能对腺瘤检测的现实世界影响：一项单一中心的横断面研究，秘鲁利马

近年来，人工智能（AI）在内镜研究中的应用有所增长。本研究评估了人工智能在日常临床实践中检测息肉和腺瘤的性能。材料和方法进行了一项横断面研究，回顾了2021年1月至2024年5月期间进行的人工智能辅助结肠镜检查（AIACs）。根据腺瘤的特征，应用逻辑回归进行检测。结果共回顾结肠镜检查1251例。AIAC组患者年龄大于对照组（59±13岁vs. 56±12岁，p < 0.05）。性别、手术适应证、肠道准备和手术时间之间没有差异。在主要目的方面，与对照组相比，AIAC组息肉检出率（58比52%；P> 0.05）显著高于对照组，腺瘤检出率（39比33%；P> 0.05）无显著高于对照组。在腺瘤特征分析中，AIAC组对息肉样腺瘤（OR: 1.28; 95% CI: 1.04-1.59）、小于10 mm （OR: 1.41; 95% CI: 1.14-1.74）、位于结肠近端（OR: 1.31; 95% CI: 1.05-1.65）的鉴别明显高于对照组。结论人工智能在结肠镜检查中的应用对腺瘤的检出率无显著提高，但对小于10 mm且位于结肠近端的息肉样腺瘤的检出率有显著提高。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Revista de Gastroenterologia de Mexico GASTROENTEROLOGY & HEPATOLOGY-

CiteScore

1.60

自引率

12.50%

发文量

102

审稿时长

12 weeks

期刊介绍： La Revista de Gastroenterología de México es el órgano oficial de la Asociación Mexicana de Gastroenterología. Sus espacios están abiertos a los miembros de la Asociación como a todo miembro de la comunidad médica que manifieste interés por utilizar este foro para publicar sus trabajos, cumpliendo con las políticas editoriales que a continuación se mencionan. El objetivo principal de la Revista de Gastroenterología de México, es publicar trabajos originales del amplio campo de la gastroenterología, así como proporcionar información actualizada y relevante para el área de la especialidad y áreas afines. Los trabajos científicos incluyen las áreas de Gastroenterología clínica, endoscópica, quirúrgica y pediátrica.