Deep learning-based evaluation of the severity of mitral regurgitation in canine myxomatous mitral valve disease patients using digital stethoscope recordings.

IF 2.3 2区 农林科学 Q1 VETERINARY SCIENCES
Soh-Yeon Lee, Sully Lee, Se-Hoon Kim, HyeSun Chang, Won-Yang Cho, Min-Ok Ryu, Jihye Choi, Hwa-Young Yoon, Kyoung-Won Seo
{"title":"Deep learning-based evaluation of the severity of mitral regurgitation in canine myxomatous mitral valve disease patients using digital stethoscope recordings.","authors":"Soh-Yeon Lee, Sully Lee, Se-Hoon Kim, HyeSun Chang, Won-Yang Cho, Min-Ok Ryu, Jihye Choi, Hwa-Young Yoon, Kyoung-Won Seo","doi":"10.1186/s12917-025-04802-z","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Myxomatous mitral valve disease (MMVD) represents the most prevalent cardiac disorder in dogs, frequently resulting in mitral regurgitation (MR) and congestive heart failure. Although echocardiography is the gold standard for diagnosis, it is an expensive tool that involves significant clinical training to ensure consistent application. Deep learning models offer an innovative approach to assessing MR using digital stethoscopic recordings, enabling early screening and precise prediction. Thus, in this study, we evaluated the effectiveness of a convolutional neural network 6 (CNN6) in providing an objective alternative to traditional methods for assessing MR. This study, conducted at the Seoul National University Veterinary Medicine Teaching Hospital, included 460 dogs with MMVD, classified according to the American College of Veterinary Internal Medicine guidelines. Phonocardiogram signals were recorded using digital stethoscopes and analyzed using the deep models CNN6, patch-mix audio spectrogram transformer (PaSST), and residual neural network (ResNET38), which were trained to categorize MR severity into mild, moderate, and severe based on MINE score. Performance metrics were calculated to evaluate model effectiveness.</p><p><strong>Results: </strong>The CNN6-Fbank model achieved an accuracy of 94.12% [95% confidence interval (CI): 94.11-93.12], specificity of 97.30% (95% CI: 97.30-97.34), sensitivity of 94.12% (95% CI: 93.74-94.50), precision of 92.63% (95% CI: 92.29-92.97), and F1 score of 93.32% (95% CI: 93.05-93.59), outperforming the PaSST and ResNet38 models overall and demonstrating robust performance across most metrics.</p><p><strong>Conclusions: </strong>Deep learning models, particularly CNN6, can effectively assess MR severity in dogs with MMVD using digital stethoscope recordings. This approach provides a rapid, noninvasive, and reliable adjunct to echocardiography, potentially enhancing diagnosis and outcomes. Future studies should focus on broader clinical validation and real-time application of this technology.</p>","PeriodicalId":9041,"journal":{"name":"BMC Veterinary Research","volume":"21 1","pages":"326"},"PeriodicalIF":2.3000,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12060408/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMC Veterinary Research","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1186/s12917-025-04802-z","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"VETERINARY SCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Myxomatous mitral valve disease (MMVD) represents the most prevalent cardiac disorder in dogs, frequently resulting in mitral regurgitation (MR) and congestive heart failure. Although echocardiography is the gold standard for diagnosis, it is an expensive tool that involves significant clinical training to ensure consistent application. Deep learning models offer an innovative approach to assessing MR using digital stethoscopic recordings, enabling early screening and precise prediction. Thus, in this study, we evaluated the effectiveness of a convolutional neural network 6 (CNN6) in providing an objective alternative to traditional methods for assessing MR. This study, conducted at the Seoul National University Veterinary Medicine Teaching Hospital, included 460 dogs with MMVD, classified according to the American College of Veterinary Internal Medicine guidelines. Phonocardiogram signals were recorded using digital stethoscopes and analyzed using the deep models CNN6, patch-mix audio spectrogram transformer (PaSST), and residual neural network (ResNET38), which were trained to categorize MR severity into mild, moderate, and severe based on MINE score. Performance metrics were calculated to evaluate model effectiveness.

Results: The CNN6-Fbank model achieved an accuracy of 94.12% [95% confidence interval (CI): 94.11-93.12], specificity of 97.30% (95% CI: 97.30-97.34), sensitivity of 94.12% (95% CI: 93.74-94.50), precision of 92.63% (95% CI: 92.29-92.97), and F1 score of 93.32% (95% CI: 93.05-93.59), outperforming the PaSST and ResNet38 models overall and demonstrating robust performance across most metrics.

Conclusions: Deep learning models, particularly CNN6, can effectively assess MR severity in dogs with MMVD using digital stethoscope recordings. This approach provides a rapid, noninvasive, and reliable adjunct to echocardiography, potentially enhancing diagnosis and outcomes. Future studies should focus on broader clinical validation and real-time application of this technology.

基于深度学习的数字听诊器对犬二尖瓣黏液瘤患者二尖瓣反流严重程度的评估。
背景:黏液瘤状二尖瓣疾病(MMVD)是犬中最常见的心脏疾病,经常导致二尖瓣反流(MR)和充血性心力衰竭。虽然超声心动图是诊断的金标准,但它是一种昂贵的工具,需要大量的临床培训才能确保一致的应用。深度学习模型提供了一种利用数字听诊器记录评估MR的创新方法,实现了早期筛查和精确预测。因此,在这项研究中,我们评估了卷积神经网络6 (CNN6)在提供传统mr评估方法的客观替代方面的有效性。这项研究在首尔国立大学兽医教学医院进行,包括460只MMVD犬,根据美国兽医内科学院指南进行分类。使用数字听诊器记录心音图信号,并使用深度模型CNN6、patch-mix音频谱图转换器(PaSST)和残差神经网络(ResNET38)进行分析,训练后根据MINE评分将MR严重程度分为轻度、中度和重度。计算性能指标以评估模型的有效性。结果:CNN6-Fbank模型的准确率为94.12%[95%置信区间(CI): 94.11-93.12],特异性为97.30% (95% CI: 97.30-97.34),灵敏度为94.12% (95% CI: 93.74-94.50),精度为92.63% (95% CI: 92.29-92.97), F1评分为93.32% (95% CI: 93.05-93.59),总体上优于PaSST和ResNet38模型,在大多数指标上表现稳健。结论:深度学习模型,特别是CNN6,可以通过数字听诊器记录有效评估MMVD犬的MR严重程度。这种方法为超声心动图提供了一种快速、无创、可靠的辅助手段,有可能提高诊断和预后。未来的研究应侧重于该技术的更广泛的临床验证和实时应用。
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
BMC Veterinary Research
BMC Veterinary Research VETERINARY SCIENCES-
CiteScore
4.80
自引率
3.80%
发文量
420
审稿时长
3-6 weeks
期刊介绍: BMC Veterinary Research is an open access, peer-reviewed journal that considers articles on all aspects of veterinary science and medicine, including the epidemiology, diagnosis, prevention and treatment of medical conditions of domestic, companion, farm and wild animals, as well as the biomedical processes that underlie their health.
×
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