{"title":"DeepFusion: early diagnosis of COPD, asthma, and pneumonia using lung sound analysis with a multimodal BiGRU network.","authors":"Prakash Sahu, Santosh Kumar, Ajoy Kumar Behera","doi":"10.1080/10255842.2025.2511228","DOIUrl":null,"url":null,"abstract":"<p><p>The key component of pulmonary disease is the structure of respiratory sound (RS) auscultation and its analysis, which provide symptomatic information about a patient's lung. The overlap in symptoms complicates early diagnosis, making timely and accurate differentiation essential for effective treatment. This study aims to develop a multimodal framework for distinguishing and early diagnosis of COPD, asthma, and pneumonia. Descriminative features are extracted from pre-processed lung sound signal using FBSE, Spectrogram, and MFCCs. These features are integrated through a weighted multimodal fusion method and classified using BiGRU network. The framework achieved 94.1% precision overall, with strong accuracy in pairwise disease distinction- 81.73%(COPD-Asthma), 94.41% (COPD- pneumonia), and 97.40%(Asthma- pneumonia).</p>","PeriodicalId":50640,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering","volume":" ","pages":"1-14"},"PeriodicalIF":1.7000,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Methods in Biomechanics and Biomedical Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1080/10255842.2025.2511228","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0
Abstract
The key component of pulmonary disease is the structure of respiratory sound (RS) auscultation and its analysis, which provide symptomatic information about a patient's lung. The overlap in symptoms complicates early diagnosis, making timely and accurate differentiation essential for effective treatment. This study aims to develop a multimodal framework for distinguishing and early diagnosis of COPD, asthma, and pneumonia. Descriminative features are extracted from pre-processed lung sound signal using FBSE, Spectrogram, and MFCCs. These features are integrated through a weighted multimodal fusion method and classified using BiGRU network. The framework achieved 94.1% precision overall, with strong accuracy in pairwise disease distinction- 81.73%(COPD-Asthma), 94.41% (COPD- pneumonia), and 97.40%(Asthma- pneumonia).
期刊介绍:
The primary aims of Computer Methods in Biomechanics and Biomedical Engineering are to provide a means of communicating the advances being made in the areas of biomechanics and biomedical engineering and to stimulate interest in the continually emerging computer based technologies which are being applied in these multidisciplinary subjects. Computer Methods in Biomechanics and Biomedical Engineering will also provide a focus for the importance of integrating the disciplines of engineering with medical technology and clinical expertise. Such integration will have a major impact on health care in the future.