Robust classification between a healthy subject and a patient with pulmonary emphysema using lung sound samples based on a stochastic approach

我们的研究目的是开发一种家用仪器，通过检测异常的呼吸音来高精度地识别呼吸系统疾病。可以假设呼吸音中噪声的出现是随机的，而非定音则在连续的吸气/呼气阶段反复出现。因此，我们提出了一种在一系列呼吸音中考虑非定音和噪声发生趋势的分类方法。此外，我们提出的方法在诊断患者时考虑了来自多个听诊点的肺音样本。在计算每个呼吸期的声学似然后，根据患者与健康受试者之间所有听诊点的平均似然进行患者诊断。我们的分类方法显著提高了分类性能。

The objective of our study is to develop a home-use device to identify respiratory illness by detecting abnormal respiratory sounds with high accuracy. It can be assumed that the occurrence of noise in respiratory sounds is random, whereas adventitious sounds occur repeatedly in successive inspiratory/expiratory phases. Therefore, we proposed a classification method considering the occurrence tendency of adventitious sounds and noise in a series of respiratory sounds.Furthermore, our proposed method took into account lung sound samples from multiple auscultation points in diagnosing a patient. After the calculation of the acoustic likelihood for each respiratory phase, patient diagnosis was carried out based on the comparison of the average likelihood of all auscultation points between a patient and a healthy subject. Our classification method significantly increased the classification performance.