Shekhar Raj, Vanama Ganesh, John Titus, Issac James, Arjoune Youness, Doroshow Robin W
Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Hospital, Washington, DC, United States.
AusculTech Dx, Silver Spring, MD, United States.
Front Pediatr. 2022 Sep 21;10:923956. doi: 10.3389/fped.2022.923956. eCollection 2022.
Still's murmur is the most prevalent innocent heart murmur of childhood. Auscultation is the primary clinical tool to identify this murmur as innocent. Whereas pediatric cardiologists routinely perform this task, primary care providers are less successful in distinguishing Still's murmur from the murmurs of true heart disease. This results in a large number of children with a Still's murmur being referred to pediatric cardiologists.
To develop a computer algorithm that can aid primary care providers to identify the innocent Still's murmur at the point of care, to substantially decrease over-referral.
The study included Still's murmurs, pathological murmurs, other innocent murmurs, and normal (i.e., non-murmur) heart sounds of 1,473 pediatric patients recorded using a commercial electronic stethoscope. The recordings with accompanying clinical diagnoses provided by a pediatric cardiologist were used to train and test the convolutional neural network-based algorithm.
A comparative analysis showed that the algorithm using only the murmur sounds recorded at the lower left sternal border achieved the highest accuracy. The developed algorithm identified Still's murmur with 90.0% sensitivity and 98.3% specificity for the default decision threshold. The area under the receiver operating characteristic curve was 0.943.
Still's murmur can be identified with high accuracy with the algorithm we developed. Using this approach, the algorithm could help to reduce the rate of unnecessary pediatric cardiologist referrals and use of echocardiography for a common benign finding.
Still 杂音是儿童时期最常见的生理性心脏杂音。听诊是将这种杂音识别为生理性杂音的主要临床手段。虽然儿科心脏病专家经常进行这项工作，但初级保健提供者在区分 Still 杂音与真正心脏病的杂音方面成功率较低。这导致大量患有 Still 杂音的儿童被转诊至儿科心脏病专家处。
开发一种计算机算法，以帮助初级保健提供者在床边识别生理性 Still 杂音，大幅减少过度转诊。
该研究纳入了使用商用电子听诊器记录的 1473 名儿科患者的 Still 杂音、病理性杂音、其他生理性杂音和正常（即无杂音）心音。由儿科心脏病专家提供的带有临床诊断的记录用于训练和测试基于卷积神经网络的算法。
一项对比分析表明，仅使用在胸骨左缘下部记录的杂音声音的算法具有最高的准确性。对于默认决策阈值，所开发的算法识别 Still 杂音的灵敏度为 90.0%，特异度为 98.3%。受试者工作特征曲线下面积为 0.943。
我们开发的算法能够高精度地识别 Still 杂音。采用这种方法，该算法有助于降低不必要的儿科心脏病专家转诊率以及针对常见良性发现进行超声心动图检查的使用率。
