Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform.
Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform.
复制标题
通过数字听诊器平台自动检测心脏杂音的深度学习算法。
DOI：
10.1161/jaha.120.019905
复制
发表时间：
2021-05-04
影响因子：
5.4
通讯作者：
Thomas JD
中科院分区：
文献类型：
--
作者：
Chorba JS;Shapiro AM;Le L;Maidens J;Prince J;Pham S;Kanzawa MM;Barbosa DN;Currie C;Brooks C;White BE;Huskin A;Paek J;Geocaris J;Elnathan D;Ronquillo R;Kim R;Alam ZH;Mahadevan VS;Fuller SG;Stalker GW;Bravo SA;Jean D;Lee JJ;Gjergjindreaj M;Mihos CG;Forman ST;Venkatraman S;McCarthy PM;Thomas JD
临床医生在心脏听诊中检测杂音和识别潜在病理特征的能力差异很大。深度学习方法通过将收集的数据转换为临床重要信息，在医学上显示出了希望。本研究的目的是评估深度学习算法的性能，以使用商业数字听诊器平台的记录来检测杂音和临床显著的心脏瓣膜病。使用超过34小时的先前获取和注释的心音记录，我们训练了一个深度神经网络来检测杂音。为了测试该算法，我们在临床研究中招募了962名患者，并收集了4个主要听诊位置的记录。使用患者超声心动图和3名心脏病专家的注释建立了基础事实。检测杂音的算法性能的灵敏度和特异性分别为76.3%和91.4%。通过忽略较柔和的杂音，强度为1级的患者敏感性增加至90.0%。在适当的解剖听诊位置应用该算法可检测到中度至重度或重度主动脉瓣狭窄，灵敏度为93.2%，特异性为86.0%，以及中度至重度或重度二尖瓣返流，灵敏度为66.2%，特异性为94.6%。基于我们数据库的注释子集，深度学习算法检测杂音和临床显著主动脉瓣狭窄和二尖瓣返流的能力与心脏病专家相当。研究结果表明，这些算法将作为一线临床支持工具，帮助临床医生筛查由心脏瓣膜病引起的心脏杂音。URL：https://clinicaltrials.gov;唯一标识符：NCT 03458806。
Clinicians vary markedly in their ability to detect murmurs during cardiac auscultation and identify the underlying pathological features. Deep learning approaches have shown promise in medicine by transforming collected data into clinically significant information. The objective of this research is to assess the performance of a deep learning algorithm to detect murmurs and clinically significant valvular heart disease using recordings from a commercial digital stethoscope platform. Using >34 hours of previously acquired and annotated heart sound recordings, we trained a deep neural network to detect murmurs. To test the algorithm, we enrolled 962 patients in a clinical study and collected recordings at the 4 primary auscultation locations. Ground truth was established using patient echocardiograms and annotations by 3 expert cardiologists. Algorithm performance for detecting murmurs has sensitivity and specificity of 76.3% and 91.4%, respectively. By omitting softer murmurs, those with grade 1 intensity, sensitivity increased to 90.0%. Application of the algorithm at the appropriate anatomic auscultation location detected moderate‐to‐severe or greater aortic stenosis, with sensitivity of 93.2% and specificity of 86.0%, and moderate‐to‐severe or greater mitral regurgitation, with sensitivity of 66.2% and specificity of 94.6%. The deep learning algorithm’s ability to detect murmurs and clinically significant aortic stenosis and mitral regurgitation is comparable to expert cardiologists based on the annotated subset of our database. The findings suggest that such algorithms would have utility as front‐line clinical support tools to aid clinicians in screening for cardiac murmurs caused by valvular heart disease. URL: https://clinicaltrials.gov; Unique Identifier: NCT03458806.