Artificial Intelligence–Assisted Capsule Endoscopy Versus Conventional Capsule Endoscopy for Detection of Small Bowel Lesions: A Systematic Review and Meta-Analysis

IF 3.7 3区医学 Q2 GASTROENTEROLOGY & HEPATOLOGY

Journal of Gastroenterology and Hepatology Pub Date : 2025-03-13 DOI:10.1111/jgh.16931

Arkadeep Dhali, Vincent Kipkorir, Rick Maity, Bahadar S. Srichawla, Jyotirmoy Biswas, Roger B. Rathna, Hareesha Rishab Bharadwaj, Ibsen Ongidi, Talha Chaudhry, Gisore Morara, Maryann Waithaka, Clinton Rugut, Miheso Lemashon, Isaac Cheruiyot, Daniel Ojuka, Sukanta Ray, Gopal Krishna Dhali

{"title":"Artificial Intelligence–Assisted Capsule Endoscopy Versus Conventional Capsule Endoscopy for Detection of Small Bowel Lesions: A Systematic Review and Meta-Analysis","authors":"Arkadeep Dhali, Vincent Kipkorir, Rick Maity, Bahadar S. Srichawla, Jyotirmoy Biswas, Roger B. Rathna, Hareesha Rishab Bharadwaj, Ibsen Ongidi, Talha Chaudhry, Gisore Morara, Maryann Waithaka, Clinton Rugut, Miheso Lemashon, Isaac Cheruiyot, Daniel Ojuka, Sukanta Ray, Gopal Krishna Dhali","doi":"10.1111/jgh.16931","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Capsule endoscopy (CE) is a valuable tool used in the diagnosis of small intestinal lesions. The study aims to systematically review the literature and provide a meta-analysis of the diagnostic accuracy, specificity, sensitivity, and negative and positive predictive values of AI-assisted <span>CE</span> in the diagnosis of small bowel lesions in comparison to <span>CE</span>.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>Literature searches were performed through PubMed, SCOPUS, and EMBASE to identify studies eligible for inclusion. All publications up to 24 November 2024 were included. Original articles (including observational studies and randomized control trials), systematic reviews, meta-analyses, and case series reporting outcomes on AI-assisted <span>CE</span> in the diagnosis of small bowel lesions were included. The extracted data were pooled, and a meta-analysis was performed for the appropriate variables, considering the clinical and methodological heterogeneity among the included studies. Comprehensive Meta-Analysis v4.0 (Biostat Inc.) was used for the analysis of the data.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>A total of 14 studies were included in the present study. The mean age of participants across the studies was 54.3 years (SD 17.7), with 55.4% men and 44.6% women. The pooled accuracy for conventional <span>CE</span> was 0.966 (95% CI: 0.925–0.988), whereas for AI-assisted <span>CE,</span> it was 0.9185 (95% CI: 0.9138–0.9233). Conventional <span>CE</span> exhibited a pooled sensitivity of 0.860 (95% CI: 0.786–0.934) compared with AI-assisted <span>CE</span> at 0.9239 (95% CI: 0.8648–0.9870). The positive predictive value for conventional <span>CE</span> was 0.982 (95% CI: 0.976–0.987), whereas AI-assisted <span>CE</span> had a PPV of 0.8928 (95% CI: 0.7554–0.999). The pooled specificity for conventional <span>CE</span> was 0.998 (95% CI: 0.996–0.999) compared with 0.5367 (95% CI: 0.5244–0.5492) for AI-assisted <span>CE</span>. Negative predictive values were higher in AI-assisted <span>CE</span> at 0.9425 (95% CI: 0.9389–0.9462) versus 0.760 (95% CI: 0.577–0.943) for conventional <span>CE</span>.</p>\n </section>\n \n <section>\n \n <h3> Conclusion</h3>\n \n <p>AI-assisted <span>CE</span> displays superior diagnostic accuracy, sensitivity, and positive predictive values albeit the lower pooled specificity in comparison with conventional <span>CE</span>. Its use would ensure accurate detection of small bowel lesions and further enhance their management.</p>\n </section>\n </div>","PeriodicalId":15877,"journal":{"name":"Journal of Gastroenterology and Hepatology","volume":"40 5","pages":"1105-1118"},"PeriodicalIF":3.7000,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/jgh.16931","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Gastroenterology and Hepatology","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/jgh.16931","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GASTROENTEROLOGY & HEPATOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Capsule endoscopy (CE) is a valuable tool used in the diagnosis of small intestinal lesions. The study aims to systematically review the literature and provide a meta-analysis of the diagnostic accuracy, specificity, sensitivity, and negative and positive predictive values of AI-assisted CE in the diagnosis of small bowel lesions in comparison to CE.

Methods

Literature searches were performed through PubMed, SCOPUS, and EMBASE to identify studies eligible for inclusion. All publications up to 24 November 2024 were included. Original articles (including observational studies and randomized control trials), systematic reviews, meta-analyses, and case series reporting outcomes on AI-assisted CE in the diagnosis of small bowel lesions were included. The extracted data were pooled, and a meta-analysis was performed for the appropriate variables, considering the clinical and methodological heterogeneity among the included studies. Comprehensive Meta-Analysis v4.0 (Biostat Inc.) was used for the analysis of the data.

Results

A total of 14 studies were included in the present study. The mean age of participants across the studies was 54.3 years (SD 17.7), with 55.4% men and 44.6% women. The pooled accuracy for conventional CE was 0.966 (95% CI: 0.925–0.988), whereas for AI-assisted CE, it was 0.9185 (95% CI: 0.9138–0.9233). Conventional CE exhibited a pooled sensitivity of 0.860 (95% CI: 0.786–0.934) compared with AI-assisted CE at 0.9239 (95% CI: 0.8648–0.9870). The positive predictive value for conventional CE was 0.982 (95% CI: 0.976–0.987), whereas AI-assisted CE had a PPV of 0.8928 (95% CI: 0.7554–0.999). The pooled specificity for conventional CE was 0.998 (95% CI: 0.996–0.999) compared with 0.5367 (95% CI: 0.5244–0.5492) for AI-assisted CE. Negative predictive values were higher in AI-assisted CE at 0.9425 (95% CI: 0.9389–0.9462) versus 0.760 (95% CI: 0.577–0.943) for conventional CE.

Conclusion

AI-assisted CE displays superior diagnostic accuracy, sensitivity, and positive predictive values albeit the lower pooled specificity in comparison with conventional CE. Its use would ensure accurate detection of small bowel lesions and further enhance their management.

Abstract Image

查看原文本刊更多论文

人工智能辅助胶囊内窥镜与传统胶囊内窥镜检测小肠病变：系统综述和荟萃分析。

背景：胶囊内镜（CE）是小肠病变诊断的重要工具。本研究旨在系统回顾文献，并对人工智能辅助CE与CE诊断小肠病变的诊断准确性、特异性、敏感性、阴性和阳性预测值进行meta分析。方法：通过PubMed、SCOPUS和EMBASE进行文献检索，确定符合纳入条件的研究。包括截至2024年11月24日的所有出版物。原始文章（包括观察性研究和随机对照试验）、系统综述、荟萃分析和病例系列报告了人工智能辅助CE诊断小肠病变的结果。将提取的数据汇总，考虑到纳入研究的临床和方法学异质性，对适当的变量进行荟萃分析。采用综合meta分析软件4.0 （Biostat Inc.）对数据进行分析。结果：本研究共纳入14项研究。研究参与者的平均年龄为54.3岁（SD 17.7），男性55.4%，女性44.6%。常规CE的汇总准确率为0.966 (95% CI: 0.925-0.988)，而人工智能辅助CE的汇总准确率为0.9185 （95% CI: 0.9138-0.9233）。常规CE的总敏感度为0.860 (95% CI: 0.786-0.934)，人工智能辅助CE的总敏感度为0.9239 （95% CI: 0.8648-0.9870）。常规CE的阳性预测值为0.982 (95% CI: 0.976 ~ 0.987)，而人工智能辅助CE的PPV为0.8928 （95% CI: 0.7554 ~ 0.999）。常规CE的合并特异性为0.998 (95% CI: 0.996-0.999)，而人工智能辅助CE的合并特异性为0.5367 （95% CI: 0.5244-0.5492）。人工智能辅助CE的阴性预测值更高，为0.9425 (95% CI: 0.9389-0.9462)，而传统CE的阴性预测值为0.760 （95% CI: 0.577-0.943）。结论：人工智能辅助CE显示出更高的诊断准确性、敏感性和阳性预测值，尽管与常规CE相比，其综合特异性较低。它的使用将确保小肠病变的准确检测，并进一步加强其管理。

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

Journal of Gastroenterology and Hepatology 医学-胃肠肝病学

CiteScore

7.90

自引率

2.40%

发文量

326

审稿时长

2.3 months

期刊介绍： Journal of Gastroenterology and Hepatology is produced 12 times per year and publishes peer-reviewed original papers, reviews and editorials concerned with clinical practice and research in the fields of hepatology, gastroenterology and endoscopy. Papers cover the medical, radiological, pathological, biochemical, physiological and historical aspects of the subject areas. All submitted papers are reviewed by at least two referees expert in the field of the submitted paper.