A Neural Network-Based Method for Respiratory Sound Analysis and Lung Disease Detection
Background: Respiratory sound analysis represents a research topic of growing interest in recent times. In fact, in this area, there is the potential to automatically infer the abnormalities in the preliminary stages of a lung dysfunction. Methods: In this paper, we propose a method to analyse respi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/8/3877 |
| _version_ | 1797437044060848128 |
|---|---|
| author | Luca Brunese Francesco Mercaldo Alfonso Reginelli Antonella Santone |
| author_facet | Luca Brunese Francesco Mercaldo Alfonso Reginelli Antonella Santone |
| author_sort | Luca Brunese |
| collection | DOAJ |
| description | Background: Respiratory sound analysis represents a research topic of growing interest in recent times. In fact, in this area, there is the potential to automatically infer the abnormalities in the preliminary stages of a lung dysfunction. Methods: In this paper, we propose a method to analyse respiratory sounds in an automatic way. The aim is to show the effectiveness of machine learning techniques in respiratory sound analysis. A feature vector is gathered directly from breath audio and, thus, by exploiting supervised machine learning techniques, we detect if the feature vector is related to a patient affected by a lung disease. Moreover, the proposed method is able to characterise the lung disease in asthma, bronchiectasis, bronchiolitis, chronic obstructive pulmonary disease, pneumonia, and lower or upper respiratory tract infection. Results: A retrospective experimental analysis on 126 patients with 920 recording sessions showed the effectiveness of the proposed method. Conclusion: The experimental analysis demonstrated that it is possible to detect lung disease by exploiting machine learning techniques. We considered several supervised machine learning algorithms, obtaining the most interesting performance with the neural network model, with an F-Measure of 0.983 in lung disease detection and equal to 0.923 in lung disease characterisation, increasing the state-of-the-art performance. |
| first_indexed | 2024-03-09T11:12:18Z |
| format | Article |
| id | doaj.art-bdd06f7324784a3ba90f4624c3db62b9 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T11:12:18Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-bdd06f7324784a3ba90f4624c3db62b92023-12-01T00:40:39ZengMDPI AGApplied Sciences2076-34172022-04-01128387710.3390/app12083877A Neural Network-Based Method for Respiratory Sound Analysis and Lung Disease DetectionLuca Brunese0Francesco Mercaldo1Alfonso Reginelli2Antonella Santone3Department of Medicine and Health Sciences “Vincenzo Tiberio”, University of Molise, 86100 Campobasso, ItalyDepartment of Medicine and Health Sciences “Vincenzo Tiberio”, University of Molise, 86100 Campobasso, ItalyDepartment of Precision Medicine, University of Campania “Luigi Vanvitelli”, 80100 Napoli, ItalyDepartment of Medicine and Health Sciences “Vincenzo Tiberio”, University of Molise, 86100 Campobasso, ItalyBackground: Respiratory sound analysis represents a research topic of growing interest in recent times. In fact, in this area, there is the potential to automatically infer the abnormalities in the preliminary stages of a lung dysfunction. Methods: In this paper, we propose a method to analyse respiratory sounds in an automatic way. The aim is to show the effectiveness of machine learning techniques in respiratory sound analysis. A feature vector is gathered directly from breath audio and, thus, by exploiting supervised machine learning techniques, we detect if the feature vector is related to a patient affected by a lung disease. Moreover, the proposed method is able to characterise the lung disease in asthma, bronchiectasis, bronchiolitis, chronic obstructive pulmonary disease, pneumonia, and lower or upper respiratory tract infection. Results: A retrospective experimental analysis on 126 patients with 920 recording sessions showed the effectiveness of the proposed method. Conclusion: The experimental analysis demonstrated that it is possible to detect lung disease by exploiting machine learning techniques. We considered several supervised machine learning algorithms, obtaining the most interesting performance with the neural network model, with an F-Measure of 0.983 in lung disease detection and equal to 0.923 in lung disease characterisation, increasing the state-of-the-art performance.https://www.mdpi.com/2076-3417/12/8/3877lungmachine learningneural networkclassificationartificial intelligence |
| spellingShingle | Luca Brunese Francesco Mercaldo Alfonso Reginelli Antonella Santone A Neural Network-Based Method for Respiratory Sound Analysis and Lung Disease Detection Applied Sciences lung machine learning neural network classification artificial intelligence |
| title | A Neural Network-Based Method for Respiratory Sound Analysis and Lung Disease Detection |
| title_full | A Neural Network-Based Method for Respiratory Sound Analysis and Lung Disease Detection |
| title_fullStr | A Neural Network-Based Method for Respiratory Sound Analysis and Lung Disease Detection |
| title_full_unstemmed | A Neural Network-Based Method for Respiratory Sound Analysis and Lung Disease Detection |
| title_short | A Neural Network-Based Method for Respiratory Sound Analysis and Lung Disease Detection |
| title_sort | neural network based method for respiratory sound analysis and lung disease detection |
| topic | lung machine learning neural network classification artificial intelligence |
| url | https://www.mdpi.com/2076-3417/12/8/3877 |
| work_keys_str_mv | AT lucabrunese aneuralnetworkbasedmethodforrespiratorysoundanalysisandlungdiseasedetection AT francescomercaldo aneuralnetworkbasedmethodforrespiratorysoundanalysisandlungdiseasedetection AT alfonsoreginelli aneuralnetworkbasedmethodforrespiratorysoundanalysisandlungdiseasedetection AT antonellasantone aneuralnetworkbasedmethodforrespiratorysoundanalysisandlungdiseasedetection AT lucabrunese neuralnetworkbasedmethodforrespiratorysoundanalysisandlungdiseasedetection AT francescomercaldo neuralnetworkbasedmethodforrespiratorysoundanalysisandlungdiseasedetection AT alfonsoreginelli neuralnetworkbasedmethodforrespiratorysoundanalysisandlungdiseasedetection AT antonellasantone neuralnetworkbasedmethodforrespiratorysoundanalysisandlungdiseasedetection |