Guo Ling, Khobragade Nivedita, Kieu Spencer, Ilyas Suleman, Nicely Preston N, Asiedu Emmanuel K, Lima Fabio V, Currie Caroline, Lastowski Emileigh, Choudhary Gaurav
Eko Health Inc. Emeryville CA USA.
Warren Alpert Medical School Brown University Providence RI USA.
J Am Heart Assoc. 2025 Feb 4;14(3):e036882. doi: 10.1161/JAHA.124.036882. Epub 2025 Feb 3.
Despite the poor outcomes related to the presence of pulmonary hypertension, it often goes undiagnosed in part because of low suspicion and screening tools not being easily accessible such as echocardiography. A new readily available screening tool to identify elevated pulmonary artery systolic pressures is needed to help with the prognosis and timely treatment of underlying causes such as heart failure or pulmonary vascular remodeling. We developed a deep learning-based method that uses phonocardiograms (PCGs) for the detection of elevated pulmonary artery systolic pressure, an indicator of pulmonary hypertension.
Approximately 6000 PCG recordings with the corresponding echocardiogram-based estimated pulmonary artery systolic pressure values, as well as ≈169 000 PCG recordings without associated echocardiograms, were used for training a deep convolutional network to detect pulmonary artery systolic pressures ≥40 mm Hg in a semisupervised manner. Each 15-second PCG, recorded using a digital stethoscope, was processed to generate 5-second mel-spectrograms. An additional labeled data set of 196 patients was used for testing. GradCAM++ was used to visualize high importance segments contributing to the network decision.
An average area under the receiver operator characteristic curve of 0.79 was obtained across 5 cross-validation folds. The testing data set gave a sensitivity of 0.71 and a specificity of 0.73, with pulmonic and left subclavicular locations having higher sensitivities. GradCAM++ technique highlighted physiologically meaningful PCG segments in example pulmonary hypertension recordings.
We demonstrated the feasibility of using digital stethoscopes in conjunction with deep learning algorithms as a low-cost, noninvasive, and easily accessible screening tool for early detection of pulmonary hypertension.
尽管肺动脉高压会导致不良后果，但它常常未被诊断出来，部分原因是怀疑度低，且诸如超声心动图等筛查工具不易获得。需要一种新的易于获得的筛查工具来识别肺动脉收缩压升高，以帮助对心力衰竭或肺血管重塑等潜在病因进行预后评估和及时治疗。我们开发了一种基于深度学习的方法，该方法使用心音图（PCG）来检测肺动脉收缩压升高，这是肺动脉高压的一个指标。
大约6000份带有基于超声心动图估计的相应肺动脉收缩压值的心音图记录，以及约169000份无相关超声心动图的心音图记录，用于训练深度卷积网络，以半监督方式检测肺动脉收缩压≥40 mmHg。使用数字听诊器记录的每段15秒的心音图被处理以生成5秒的梅尔频谱图。另外196名患者的标记数据集用于测试。使用GradCAM++来可视化对网络决策有重要贡献的高重要性片段。
在5次交叉验证中，受试者操作特征曲线下的平均面积为0.79。测试数据集的灵敏度为0.71，特异度为0.73，肺动脉和左锁骨下位置的灵敏度更高。GradCAM++技术在肺动脉高压记录示例中突出显示了具有生理意义的心音图片段。
我们证明了将数字听诊器与深度学习算法结合使用作为一种低成本、非侵入性且易于获得的筛查工具用于早期检测肺动脉高压的可行性。
