Identifying unique spectral fingerprints in cough sounds for diagnosing respiratory ailments
Abstract Coughing, a prevalent symptom of many illnesses, including COVID-19, has led researchers to explore the potential of cough sound signals for cost-effective disease diagnosis. Traditional diagnostic methods, which can be expensive and require specialized personnel, contrast with the more acc...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-50371-2 |
| _version_ | 1797363285784264704 |
|---|---|
| author | Syrine Ghrabli Mohamed Elgendi Carlo Menon |
| author_facet | Syrine Ghrabli Mohamed Elgendi Carlo Menon |
| author_sort | Syrine Ghrabli |
| collection | DOAJ |
| description | Abstract Coughing, a prevalent symptom of many illnesses, including COVID-19, has led researchers to explore the potential of cough sound signals for cost-effective disease diagnosis. Traditional diagnostic methods, which can be expensive and require specialized personnel, contrast with the more accessible smartphone analysis of coughs. Typically, coughs are classified as wet or dry based on their phase duration. However, the utilization of acoustic analysis for diagnostic purposes is not widespread. Our study examined cough sounds from 1183 COVID-19-positive patients and compared them with 341 non-COVID-19 cough samples, as well as analyzing distinctions between pneumonia and asthma-related coughs. After rigorous optimization across frequency ranges, specific frequency bands were found to correlate with each respiratory ailment. Statistical separability tests validated these findings, and machine learning algorithms, including linear discriminant analysis and k-nearest neighbors classifiers, were employed to confirm the presence of distinct frequency bands in the cough signal power spectrum associated with particular diseases. The identification of these acoustic signatures in cough sounds holds the potential to transform the classification and diagnosis of respiratory diseases, offering an affordable and widely accessible healthcare tool. |
| first_indexed | 2024-03-08T16:19:10Z |
| format | Article |
| id | doaj.art-26b4fb4197364b4ba6283240c74c2e93 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-08T16:19:10Z |
| publishDate | 2024-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-26b4fb4197364b4ba6283240c74c2e932024-01-07T12:26:26ZengNature PortfolioScientific Reports2045-23222024-01-011411810.1038/s41598-023-50371-2Identifying unique spectral fingerprints in cough sounds for diagnosing respiratory ailmentsSyrine Ghrabli0Mohamed Elgendi1Carlo Menon2Biomedical and Mobile Health Technology Lab, ETH ZurichBiomedical and Mobile Health Technology Lab, ETH ZurichBiomedical and Mobile Health Technology Lab, ETH ZurichAbstract Coughing, a prevalent symptom of many illnesses, including COVID-19, has led researchers to explore the potential of cough sound signals for cost-effective disease diagnosis. Traditional diagnostic methods, which can be expensive and require specialized personnel, contrast with the more accessible smartphone analysis of coughs. Typically, coughs are classified as wet or dry based on their phase duration. However, the utilization of acoustic analysis for diagnostic purposes is not widespread. Our study examined cough sounds from 1183 COVID-19-positive patients and compared them with 341 non-COVID-19 cough samples, as well as analyzing distinctions between pneumonia and asthma-related coughs. After rigorous optimization across frequency ranges, specific frequency bands were found to correlate with each respiratory ailment. Statistical separability tests validated these findings, and machine learning algorithms, including linear discriminant analysis and k-nearest neighbors classifiers, were employed to confirm the presence of distinct frequency bands in the cough signal power spectrum associated with particular diseases. The identification of these acoustic signatures in cough sounds holds the potential to transform the classification and diagnosis of respiratory diseases, offering an affordable and widely accessible healthcare tool.https://doi.org/10.1038/s41598-023-50371-2 |
| spellingShingle | Syrine Ghrabli Mohamed Elgendi Carlo Menon Identifying unique spectral fingerprints in cough sounds for diagnosing respiratory ailments Scientific Reports |
| title | Identifying unique spectral fingerprints in cough sounds for diagnosing respiratory ailments |
| title_full | Identifying unique spectral fingerprints in cough sounds for diagnosing respiratory ailments |
| title_fullStr | Identifying unique spectral fingerprints in cough sounds for diagnosing respiratory ailments |
| title_full_unstemmed | Identifying unique spectral fingerprints in cough sounds for diagnosing respiratory ailments |
| title_short | Identifying unique spectral fingerprints in cough sounds for diagnosing respiratory ailments |
| title_sort | identifying unique spectral fingerprints in cough sounds for diagnosing respiratory ailments |
| url | https://doi.org/10.1038/s41598-023-50371-2 |
| work_keys_str_mv | AT syrineghrabli identifyinguniquespectralfingerprintsincoughsoundsfordiagnosingrespiratoryailments AT mohamedelgendi identifyinguniquespectralfingerprintsincoughsoundsfordiagnosingrespiratoryailments AT carlomenon identifyinguniquespectralfingerprintsincoughsoundsfordiagnosingrespiratoryailments |