基于心肺音智能听诊的呼吸音量化分析与应用评价  

Quantitative analysis and application evaluation of respiratory sounds based on intelligent auscultation of cardiopulmonary sounds

作　　者：赵峰 胡南 陈燕 蔡盛盛[3] ZHAO Feng;HU Nan;CHEN Yan;CAI Shengsheng(Department of Anesthesiology,First Medical Center,PLA General Hospital,Beijing 100853,China;School of Electronic and Information Engineering,Soochow University;Center for Intelligent Acoustics and Signal Processing,Huzhou Research Institute,Zhejiang University)

机构地区：[1]中国人民解放军总医院第一医学中心麻醉科,北京100853 [2]苏州大学电子与信息工程学院 [3]浙江大学湖州研究院智能声学与信号处理中心

出　　处：《中国数字医学》2024年第8期74-78,共5页China Digital Medicine

基　　金：国家自然科学基金(82172185)。

摘　　要：目的:提出一种从心肺音信号中分离肺音做定量分析的方法,实现对呼吸率和呼吸强度的实时测量。方法:使用电子听诊器采集患者主动脉瓣第二听诊区的心肺音,通过蓝牙将信号传输至手机端,App显示波形,并将数据存储于云端。采用非负矩阵分解,结合经验模态分析算法将心肺音进行分离,根据肺音计算呼吸率及呼吸强度。以阻抗法测定的呼吸率为对照,评价通过肺音计算呼吸率的准确性。结果:通过肺音计算呼吸率与阻抗法测定的呼吸率有显著相关性(P<0.05),两种方法测量结果有良好的一致性。结论:该方法在监测心音的同时能准确监测呼吸功能,为临床便携式呼吸监测提供了一种新方法,在床旁或远程生命体征监测中具有良好的转化前景。Objective To propose a method for quantitative analysis of separating pulmonary sounds from cardiopulmonary sounds signals,so as to measure respiratory rate and respiratory intensity in real time.Methods An electronic stethoscope was used to collect the cardiopulmonary sound in the second stethoscope area of the patient’s aortic valve,and the signals were transmitted to the mobile phone via Bluetooth,the App displayed the waveforms,and the data was stored in the cloud.The heart and pulmonary sounds were separated by non-negative matrix decomposition and empirical modal analysis algorithm,and the respiratory rate and respiratory intensity were calculated based on the lung sounds.The accuracy of respiratory rate calculated by pulmonary sounds was evaluated by comparing with respiratory rate measured by impedance method as a control.Results There was a significant correlation between respiratory rate calculated from the pulmonary sounds and the respiratory rate measured by impedance method(P<0.05),and there was good agreement between the two methods.Conclusion Respiratory function can be accurately monitored while heart sound monitoring,which provides a new method for clinical portable respiratory monitoring.This method shows a good translational prospect for bedside or remote vital signs monitoring.

关 键 词：心肺音听诊 人工智能 呼吸音 定量分析 

分 类 号：R197.32[医药卫生—卫生事业管理] R319[医药卫生—公共卫生与预防医学]