Department of Pediatrics, Tokai University Hachioji Hospital, Hachioji, Japan.
Department of Pediatrics, Tokai University School of Medicine, Shimokasuya 143, Isehara, Kanagawa, 259-1193, Japan.
BMC Pulm Med. 2024 Aug 14;24(1):394. doi: 10.1186/s12890-024-03210-7.
Lung sound analysis parameters have been reported to be useful biomarkers for evaluating airway condition. We developed an automatic lung sound analysis software program for infants and children based on lung sound spectral curves of frequency and power by leveraging machine learning (ML) technology.
To put this software program into clinical practice, in Study 1, the reliability and reproducibility of the software program using data from younger children were examined. In Study 2, the relationship between lung sound parameters and respiratory flow (L/s) was evaluated using data from older children. In Study 3, we conducted a survey using the ATS-DLD questionnaire to evaluate the clinical usefulness. The survey focused on the history of wheezing and allergies, among healthy 3-year-old infants, and then measured lung sounds. The clinical usefulness was evaluated by comparing the questionnaire results with the results of the new lung sound parameters.
In Studies 1 and 2, the parameters of the new software program demonstrated excellent reproducibility and reliability, and were not affected by airflow (L/s). In Study 3, infants with a history of wheezing showed lower FAP and RPF (p < 0.001 and p = 0.025, respectively) and higher PAP (p = 0.001) than healthy infants. Furthermore, infants with asthma/asthma-like bronchitis showed lower FAP (p = 0.002) and higher PAP (p = 0.001) than healthy infants.
Lung sound parameters obtained using the ML algorithm were able to accurately assess the respiratory condition of infants. These parameters are useful for the early detection and intervention of childhood asthma.
肺部声音分析参数已被报道为评估气道状况的有用生物标志物。我们利用机器学习 (ML) 技术，基于频率和功率的肺部声音频谱曲线，为婴儿和儿童开发了一种自动肺部声音分析软件程序。
为了将该软件程序应用于临床实践，在研究 1 中，我们使用年龄较小的儿童的数据检查了该软件程序的可靠性和可重复性。在研究 2 中，我们使用年龄较大的儿童的数据评估了肺部声音参数与呼吸流量 (L/s) 之间的关系。在研究 3 中，我们使用 ATS-DLD 问卷进行了一项调查，以评估其临床实用性。该调查侧重于健康 3 岁婴儿的喘息和过敏史，然后测量肺部声音。通过将问卷结果与新的肺部声音参数的结果进行比较，评估了临床实用性。
在研究 1 和 2 中，新软件程序的参数表现出极好的可重复性和可靠性，不受气流 (L/s) 的影响。在研究 3 中，有喘息史的婴儿的 FAP 和 RPF 较低（p<0.001 和 p=0.025，分别），而 PAP 较高（p=0.001）。此外，患有哮喘/哮喘样支气管炎的婴儿的 FAP 较低（p=0.002），而 PAP 较高（p=0.001）。
使用 ML 算法获得的肺部声音参数能够准确评估婴儿的呼吸状况。这些参数对于儿童哮喘的早期发现和干预很有用。
