一种基于AI算法、可实现准确实时的肺音监测及自动喘鸣检测的可穿戴听诊器

工程（英文） ›› 2025, Vol. 53 ›› Issue (10) : 116 -129. DOI: 10.1016/j.eng.2024.12.031

研究论文

Kyoung-Ryul Lee ^a^,^# ,
Taewi Kim ^b^,^# ,
Sunghoon Im ^b^,^# ,
Yi Jae Lee ^a ,
Seongeun Jeong ^a ,
Hanho Shin ^a ,
Hana Cho ^a ,
Sang-Heon Park ^a ,
Minho Kim ^b ,
Jin Goo Lee ^b ,
Dohyeong Kim ^c ,
Gil-Soon Choi ^d ,
Daeshik Kang ^b^,^* ,
SungChul Seo ^e^,^* ,
Soo Hyun Lee ^a^,^*

作者信息 +

A Wearable Stethoscope for Accurate Real-Time Lung Sound Monitoring and Automatic Wheezing Detection Based on an AI Algorithm

Kyoung-Ryul Lee ^a^,^# ,
Taewi Kim ^b^,^# ,
Sunghoon Im ^b^,^# ,
Yi Jae Lee ^a ,
Seongeun Jeong ^a ,
Hanho Shin ^a ,
Hana Cho ^a ,
Sang-Heon Park ^a ,
Minho Kim ^b ,
Jin Goo Lee ^b ,
Dohyeong Kim ^c ,
Gil-Soon Choi ^d ,
Daeshik Kang ^b^,^* ,
SungChul Seo ^e^,^* ,
Soo Hyun Lee ^a^,^*

Author information +

文章历史 +

Received	Accepted	Published
2024-06-17	2025-12-16
Issue Date
2025-04-22

PDF

Abstract

The various bioacoustics signals obtained with auscultation contain complex clinical information that has been traditionally used as biomarkers, however, they are not extensively used in clinical studies owing to their spatiotemporal limitations. In this study, we developed a wearable stethoscope for wireless, skin-attachable, low-power, continuous, real-time auscultation using a lung-sound-monitoring-patch (LSMP). LSMP can monitor respiratory function through a mobile app and classify normal and adventitious breathing by comparing their unique acoustic characteristics. The human heart and breathing sounds from humans can be distinguished from complex sound signals consisting of a mixture of bioacoustic signals and external noise. The performance of the LSMP sensor was further demonstrated in pediatric patients with asthma and elderly chronic obstructive pulmonary disease (COPD) patients where wheezing sounds were classified at specific frequencies. In addition, we developed a novel method for counting wheezing events based on a two-dimensional convolutional neural network deep-learning model constructed de novo and trained with our augmented fundamental lung-sound data set. We implemented a counting algorithm to identify wheezing events in real-time regardless of the respiratory cycle. The artificial intelligence-based adventitious breathing event counter distinguished > 80% of the events (especially wheezing) in long-term clinical applications in patients with COPD.

关键词

Key words

Wearable stethoscope / Lung sound / Real-time monitoring / Automatic wheeze detection / AI algorithm

引用本文

引用格式 ▾

Kyoung-Ryul Lee,Taewi Kim,Sunghoon Im,Yi Jae Lee,Seongeun Jeong,Hanho Shin,Hana Cho,Sang-Heon Park,Minho Kim,Jin Goo Lee,Dohyeong Kim,Gil-Soon Choi,Daeshik Kang,SungChul Seo,Soo Hyun Lee. 一种基于AI算法、可实现准确实时的肺音监测及自动喘鸣检测的可穿戴听诊器[J]. 工程（英文）, 2025, 53(10): 116-129 DOI:10.1016/j.eng.2024.12.031