Detection of COVID-19 in smartphone-based breathing recordings: A pre-screening deep learning tool.
This study was sought to investigate the feasibility of using smartphone-based breathing sounds within a deep learning framework to discriminate between COVID-19, including asymptomatic, and healthy subjects. A total of 480 breathing sounds (240 shallow and 240 deep) were obtained from a publicly av...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0262448 |
| _version_ | 1818715562952359936 |
|---|---|
| author | Mohanad Alkhodari Ahsan H Khandoker |
| author_facet | Mohanad Alkhodari Ahsan H Khandoker |
| author_sort | Mohanad Alkhodari |
| collection | DOAJ |
| description | This study was sought to investigate the feasibility of using smartphone-based breathing sounds within a deep learning framework to discriminate between COVID-19, including asymptomatic, and healthy subjects. A total of 480 breathing sounds (240 shallow and 240 deep) were obtained from a publicly available database named Coswara. These sounds were recorded by 120 COVID-19 and 120 healthy subjects via a smartphone microphone through a website application. A deep learning framework was proposed herein that relies on hand-crafted features extracted from the original recordings and from the mel-frequency cepstral coefficients (MFCC) as well as deep-activated features learned by a combination of convolutional neural network and bi-directional long short-term memory units (CNN-BiLSTM). The statistical analysis of patient profiles has shown a significant difference (p-value: 0.041) for ischemic heart disease between COVID-19 and healthy subjects. The Analysis of the normal distribution of the combined MFCC values showed that COVID-19 subjects tended to have a distribution that is skewed more towards the right side of the zero mean (shallow: 0.59±1.74, deep: 0.65±4.35, p-value: <0.001). In addition, the proposed deep learning approach had an overall discrimination accuracy of 94.58% and 92.08% using shallow and deep recordings, respectively. Furthermore, it detected COVID-19 subjects successfully with a maximum sensitivity of 94.21%, specificity of 94.96%, and area under the receiver operating characteristic (AUROC) curves of 0.90. Among the 120 COVID-19 participants, asymptomatic subjects (18 subjects) were successfully detected with 100.00% accuracy using shallow recordings and 88.89% using deep recordings. This study paves the way towards utilizing smartphone-based breathing sounds for the purpose of COVID-19 detection. The observations found in this study were promising to suggest deep learning and smartphone-based breathing sounds as an effective pre-screening tool for COVID-19 alongside the current reverse-transcription polymerase chain reaction (RT-PCR) assay. It can be considered as an early, rapid, easily distributed, time-efficient, and almost no-cost diagnosis technique complying with social distancing restrictions during COVID-19 pandemic. |
| first_indexed | 2024-12-17T19:05:21Z |
| format | Article |
| id | doaj.art-d68cbfd05b6c4a19a5e817537f423c94 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-17T19:05:21Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-d68cbfd05b6c4a19a5e817537f423c942022-12-21T21:36:00ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-01171e026244810.1371/journal.pone.0262448Detection of COVID-19 in smartphone-based breathing recordings: A pre-screening deep learning tool.Mohanad AlkhodariAhsan H KhandokerThis study was sought to investigate the feasibility of using smartphone-based breathing sounds within a deep learning framework to discriminate between COVID-19, including asymptomatic, and healthy subjects. A total of 480 breathing sounds (240 shallow and 240 deep) were obtained from a publicly available database named Coswara. These sounds were recorded by 120 COVID-19 and 120 healthy subjects via a smartphone microphone through a website application. A deep learning framework was proposed herein that relies on hand-crafted features extracted from the original recordings and from the mel-frequency cepstral coefficients (MFCC) as well as deep-activated features learned by a combination of convolutional neural network and bi-directional long short-term memory units (CNN-BiLSTM). The statistical analysis of patient profiles has shown a significant difference (p-value: 0.041) for ischemic heart disease between COVID-19 and healthy subjects. The Analysis of the normal distribution of the combined MFCC values showed that COVID-19 subjects tended to have a distribution that is skewed more towards the right side of the zero mean (shallow: 0.59±1.74, deep: 0.65±4.35, p-value: <0.001). In addition, the proposed deep learning approach had an overall discrimination accuracy of 94.58% and 92.08% using shallow and deep recordings, respectively. Furthermore, it detected COVID-19 subjects successfully with a maximum sensitivity of 94.21%, specificity of 94.96%, and area under the receiver operating characteristic (AUROC) curves of 0.90. Among the 120 COVID-19 participants, asymptomatic subjects (18 subjects) were successfully detected with 100.00% accuracy using shallow recordings and 88.89% using deep recordings. This study paves the way towards utilizing smartphone-based breathing sounds for the purpose of COVID-19 detection. The observations found in this study were promising to suggest deep learning and smartphone-based breathing sounds as an effective pre-screening tool for COVID-19 alongside the current reverse-transcription polymerase chain reaction (RT-PCR) assay. It can be considered as an early, rapid, easily distributed, time-efficient, and almost no-cost diagnosis technique complying with social distancing restrictions during COVID-19 pandemic.https://doi.org/10.1371/journal.pone.0262448 |
| spellingShingle | Mohanad Alkhodari Ahsan H Khandoker Detection of COVID-19 in smartphone-based breathing recordings: A pre-screening deep learning tool. PLoS ONE |
| title | Detection of COVID-19 in smartphone-based breathing recordings: A pre-screening deep learning tool. |
| title_full | Detection of COVID-19 in smartphone-based breathing recordings: A pre-screening deep learning tool. |
| title_fullStr | Detection of COVID-19 in smartphone-based breathing recordings: A pre-screening deep learning tool. |
| title_full_unstemmed | Detection of COVID-19 in smartphone-based breathing recordings: A pre-screening deep learning tool. |
| title_short | Detection of COVID-19 in smartphone-based breathing recordings: A pre-screening deep learning tool. |
| title_sort | detection of covid 19 in smartphone based breathing recordings a pre screening deep learning tool |
| url | https://doi.org/10.1371/journal.pone.0262448 |
| work_keys_str_mv | AT mohanadalkhodari detectionofcovid19insmartphonebasedbreathingrecordingsaprescreeningdeeplearningtool AT ahsanhkhandoker detectionofcovid19insmartphonebasedbreathingrecordingsaprescreeningdeeplearningtool |