EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

High-accuracy lung sound classification for healthy versus unhealthy diagnosis using artificial neural network

Weiwei Zhang, Xinyu Li, Qiao Liu, Xiangyang Zheng, Yisu Ge, Xiaotian Pan, Yu Zhou

Frontiers in Bioengineering and Biotechnology · 02.07.2025 · 13

DOI: 10.3389/fbioe.2025.1583416 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Bioengineering and Biotechnology, online erschienen am 02.07.2025. Verfasst von Weiwei Zhang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Infectious Disease Department, The Third Affiliated Hospital of Wenzhou Medical University, Wenzhou, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

In recent years, advancements in machine learning and electronic stethoscope technology have enabled high-precision recording and analysis of lung sounds, significantly enhancing pulmonary disease diagnosis.

Methods

This study presents a comprehensive approach to classify lung sounds into healthy and unhealthy categories using a dataset collected from 112 subjects, comprising 35 healthy individuals and 77 patients with various pulmonary conditions, such as asthma, heart failure, pneumonia, bronchitis, pleural effusion, lung fibrosis, and chronic obstructive pulmonary disease (COPD), grouped as unhealthy. The dataset was obtained using a 3M Littmann® Electronic Stethoscope Model 3,200, employing three types of filters (Bell, Diaphragm, and Extended) to capture sounds across different frequency ranges. We extracted five key audio features—Spectral Centroid, Power, Energy, Zero Crossing Rate, and Mel-Frequency Cepstral Coefficients (MFCCs)—from each recording to form a feature matrix. A Multi-Layer Perceptron (MLP) neural network was trained for binary classification.

Results

The MLP neural network achieved accuracies of 98%, 100%, and 94% on the training, validation, and testing sets, respectively. This partitioning ensured the model’s robustness and accuracy.

Discussion

The high classification accuracy achieved by the MLP neural network suggests that this approach is a valuable decision-support tool for identifying healthy versus unhealthy lung sounds in clinical settings, facilitating early intervention while maintaining computational efficiency for offline implementation. The combination of detailed feature extraction and an optimized MLP neural network resulted in a reliable method for automated binary classification of lung sounds.

Schlagwörter

Stichwörter der Autor:innen

electronic stethoscopefeature extractionlung soundsmachine learningmulti-layer perceptronpulmonary disease classification

Autor:innen und Institutionen

  • Infectious Disease Department, The Third Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
  • China Telecom Corporation Limited Zhejiang Branch, Hangzhou, China.
  • Information Technology Center, Wenzhou Medical University, Wenzhou, China.
  • School of Data Science and Artificial Intelligence, Wenzhou University of Technology, Wenzhou, China.
  • College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China.
  • Institute of Intelligent Media Computing, Hangzhou Dianzi University, Hangzhou, China.

Zitieren

APA

Zhang, W., Li, X., Liu, Q., Zheng, X., Ge, Y., Pan, X., & Zhou, Y. (2025). High-accuracy lung sound classification for healthy versus unhealthy diagnosis using artificial neural network. Frontiers in Bioengineering and Biotechnology, 13. https://doi.org/10.3389/fbioe.2025.1583416

Vancouver

Zhang W, Li X, Liu Q, Zheng X, Ge Y, Pan X, et al. High-accuracy lung sound classification for healthy versus unhealthy diagnosis using artificial neural network. Frontiers in Bioengineering and Biotechnology. 2025;13. doi:10.3389/fbioe.2025.1583416

BibTeX
@article{Zhang2025,
  author = {Zhang, Weiwei and Li, Xinyu and Liu, Qiao and Zheng, Xiangyang and Ge, Yisu and Pan, Xiaotian and Zhou, Yu},
  title = {High-accuracy lung sound classification for healthy versus unhealthy diagnosis using artificial neural network},
  journal = {Frontiers in Bioengineering and Biotechnology},
  year = {2025},
  volume = {13},
  doi = {10.3389/fbioe.2025.1583416}
}
Kostenlos starten →