多中心研究,评估人工智能仪器在支持结直肠息肉定性诊断方面的性能。

IF 3.3 Q2 GASTROENTEROLOGY & HEPATOLOGY
Keigo Sato, Mizuki Kuramochi, Akihiko Tsuchiya, Akihiro Yamaguchi, Yasuo Hosoda, Norio Yamaguchi, Naohiro Nakamura, Yuki Itoi, Yu Hashimoto, Kengo Kasuga, Hirohito Tanaka, Shiko Kuribayashi, Yoji Takeuchi, Toshio Uraoka
{"title":"多中心研究,评估人工智能仪器在支持结直肠息肉定性诊断方面的性能。","authors":"Keigo Sato, Mizuki Kuramochi, Akihiko Tsuchiya, Akihiro Yamaguchi, Yasuo Hosoda, Norio Yamaguchi, Naohiro Nakamura, Yuki Itoi, Yu Hashimoto, Kengo Kasuga, Hirohito Tanaka, Shiko Kuribayashi, Yoji Takeuchi, Toshio Uraoka","doi":"10.1136/bmjgast-2024-001553","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>Computer-aided diagnosis (CAD) using artificial intelligence (AI) is expected to support the characterisation of colorectal lesions, which is clinically relevant for efficient colorectal cancer prevention. We conducted this study to assess the diagnostic performance of commercially available CAD systems.</p><p><strong>Methods: </strong>This was a multicentre, prospective performance evaluation study. The endoscopist diagnosed polyps using white light imaging, followed by non-magnified blue light imaging (non-mBLI) and mBLI. AI subsequently assessed the lesions using non-mBLI (non-mAI), followed by mBLI (mAI). Eventually, endoscopists made the final diagnosis by integrating the AI diagnosis (AI+endoscopist). The primary endpoint was the accuracy of the AI diagnosis of neoplastic lesions. The diagnostic performance of each modality (sensitivity, specificity and accuracy) and confidence levels were also assessed.</p><p><strong>Results: </strong>Overall, 380 lesions from 139 patients were included in the analysis. The accuracy of non-mAI was 83%, 95% CI (79% to 87%), which was inferior to that of mBLI (89%, 95% CI (85% to 92%)) and mAI (89%, 95% CI (85% to 92%)). The accuracy (95% CI) of diagnosis by expert endoscopists using mAI (91%, 95% CI (87% to 94%)) was comparable to that of expert endoscopists using mBLI (91%, 95% CI (87% to 94%)) but better than that of non-expert endoscopists using mAI (83%, 95% CI (75% to 90%)). The level of confidence in making a correct diagnosis was increased when using magnification and AI.</p><p><strong>Conclusions: </strong>The diagnostic performance of mAI for differentiating colonic lesions is comparable to that of endoscopists, regardless of their experience. However, it can be affected by the use of magnification as well as the endoscopists' level of experience.</p>","PeriodicalId":9235,"journal":{"name":"BMJ Open Gastroenterology","volume":null,"pages":null},"PeriodicalIF":3.3000,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11499753/pdf/","citationCount":"0","resultStr":"{\"title\":\"Multicentre study to assess the performance of an artificial intelligence instrument to support qualitative diagnosis of colorectal polyps.\",\"authors\":\"Keigo Sato, Mizuki Kuramochi, Akihiko Tsuchiya, Akihiro Yamaguchi, Yasuo Hosoda, Norio Yamaguchi, Naohiro Nakamura, Yuki Itoi, Yu Hashimoto, Kengo Kasuga, Hirohito Tanaka, Shiko Kuribayashi, Yoji Takeuchi, Toshio Uraoka\",\"doi\":\"10.1136/bmjgast-2024-001553\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objective: </strong>Computer-aided diagnosis (CAD) using artificial intelligence (AI) is expected to support the characterisation of colorectal lesions, which is clinically relevant for efficient colorectal cancer prevention. We conducted this study to assess the diagnostic performance of commercially available CAD systems.</p><p><strong>Methods: </strong>This was a multicentre, prospective performance evaluation study. The endoscopist diagnosed polyps using white light imaging, followed by non-magnified blue light imaging (non-mBLI) and mBLI. AI subsequently assessed the lesions using non-mBLI (non-mAI), followed by mBLI (mAI). Eventually, endoscopists made the final diagnosis by integrating the AI diagnosis (AI+endoscopist). The primary endpoint was the accuracy of the AI diagnosis of neoplastic lesions. The diagnostic performance of each modality (sensitivity, specificity and accuracy) and confidence levels were also assessed.</p><p><strong>Results: </strong>Overall, 380 lesions from 139 patients were included in the analysis. The accuracy of non-mAI was 83%, 95% CI (79% to 87%), which was inferior to that of mBLI (89%, 95% CI (85% to 92%)) and mAI (89%, 95% CI (85% to 92%)). The accuracy (95% CI) of diagnosis by expert endoscopists using mAI (91%, 95% CI (87% to 94%)) was comparable to that of expert endoscopists using mBLI (91%, 95% CI (87% to 94%)) but better than that of non-expert endoscopists using mAI (83%, 95% CI (75% to 90%)). The level of confidence in making a correct diagnosis was increased when using magnification and AI.</p><p><strong>Conclusions: </strong>The diagnostic performance of mAI for differentiating colonic lesions is comparable to that of endoscopists, regardless of their experience. However, it can be affected by the use of magnification as well as the endoscopists' level of experience.</p>\",\"PeriodicalId\":9235,\"journal\":{\"name\":\"BMJ Open Gastroenterology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.3000,\"publicationDate\":\"2024-10-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11499753/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"BMJ Open Gastroenterology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1136/bmjgast-2024-001553\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"GASTROENTEROLOGY & HEPATOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMJ Open Gastroenterology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1136/bmjgast-2024-001553","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GASTROENTEROLOGY & HEPATOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

目的:使用人工智能(AI)的计算机辅助诊断(CAD)有望支持结直肠病变的特征描述,这对有效预防结直肠癌具有临床意义。我们开展了这项研究,以评估市售计算机辅助诊断系统的诊断性能:这是一项多中心、前瞻性的性能评估研究。内镜医师使用白光成像诊断息肉,然后进行非放大蓝光成像(non-mBLI)和 mBLI。随后,人工智能使用非放大蓝光成像(non-mAI)评估病变,再使用放大蓝光成像(mBLI)评估病变。最后,内镜医师综合人工智能诊断(人工智能+内镜医师)做出最终诊断。主要终点是人工智能诊断肿瘤病变的准确性。此外,还评估了每种方法的诊断性能(敏感性、特异性和准确性)和置信度:共有 139 名患者的 380 个病灶被纳入分析。非 mAI 的准确率为 83%,95% CI(79% 至 87%),低于 mBLI(89%,95% CI(85% 至 92%))和 mAI(89%,95% CI(85% 至 92%))。使用 mAI 的内镜专家诊断的准确率(95% CI)(91%,95% CI(87% 至 94%))与使用 mBLI 的内镜专家诊断的准确率(91%,95% CI(87% 至 94%))相当,但优于使用 mAI 的非专业内镜专家诊断的准确率(83%,95% CI(75% 至 90%))。使用放大镜和人工智能时,做出正确诊断的信心水平会提高:结论:无论内镜医师的经验如何,mAI 在区分结肠病变方面的诊断性能都与内镜医师相当。然而,放大镜的使用以及内镜医师的经验水平都会影响诊断效果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Multicentre study to assess the performance of an artificial intelligence instrument to support qualitative diagnosis of colorectal polyps.

Objective: Computer-aided diagnosis (CAD) using artificial intelligence (AI) is expected to support the characterisation of colorectal lesions, which is clinically relevant for efficient colorectal cancer prevention. We conducted this study to assess the diagnostic performance of commercially available CAD systems.

Methods: This was a multicentre, prospective performance evaluation study. The endoscopist diagnosed polyps using white light imaging, followed by non-magnified blue light imaging (non-mBLI) and mBLI. AI subsequently assessed the lesions using non-mBLI (non-mAI), followed by mBLI (mAI). Eventually, endoscopists made the final diagnosis by integrating the AI diagnosis (AI+endoscopist). The primary endpoint was the accuracy of the AI diagnosis of neoplastic lesions. The diagnostic performance of each modality (sensitivity, specificity and accuracy) and confidence levels were also assessed.

Results: Overall, 380 lesions from 139 patients were included in the analysis. The accuracy of non-mAI was 83%, 95% CI (79% to 87%), which was inferior to that of mBLI (89%, 95% CI (85% to 92%)) and mAI (89%, 95% CI (85% to 92%)). The accuracy (95% CI) of diagnosis by expert endoscopists using mAI (91%, 95% CI (87% to 94%)) was comparable to that of expert endoscopists using mBLI (91%, 95% CI (87% to 94%)) but better than that of non-expert endoscopists using mAI (83%, 95% CI (75% to 90%)). The level of confidence in making a correct diagnosis was increased when using magnification and AI.

Conclusions: The diagnostic performance of mAI for differentiating colonic lesions is comparable to that of endoscopists, regardless of their experience. However, it can be affected by the use of magnification as well as the endoscopists' level of experience.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
BMJ Open Gastroenterology
BMJ Open Gastroenterology GASTROENTEROLOGY & HEPATOLOGY-
CiteScore
5.90
自引率
3.20%
发文量
68
审稿时长
2 weeks
期刊介绍: BMJ Open Gastroenterology is an online-only, peer-reviewed, open access gastroenterology journal, dedicated to publishing high-quality medical research from all disciplines and therapeutic areas of gastroenterology. It is the open access companion journal of Gut and is co-owned by the British Society of Gastroenterology. The journal publishes all research study types, from study protocols to phase I trials to meta-analyses, including small or specialist studies. Publishing procedures are built around continuous publication, publishing research online as soon as the article is ready.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信