Acoustery System for Differential Diagnosing of Coronavirus COVID-19 Disease
<italic>Goal:</italic> Because of the outbreak of coronavirus infection, healthcare systems are faced with the lack of medical professionals. We present a system for the differential diagnosis of coronavirus disease, based on deep learning techniques, which can be implemented in clinics....
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Open Journal of Engineering in Medicine and Biology |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9611002/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850093669862866944 |
|---|---|
| author | Anastasia Mitrofanova Dmitry Mikhaylov Ilman Shaznaev Vera Chumanskaia Valeri Saveliev |
| author_facet | Anastasia Mitrofanova Dmitry Mikhaylov Ilman Shaznaev Vera Chumanskaia Valeri Saveliev |
| author_sort | Anastasia Mitrofanova |
| collection | DOAJ |
| description | <italic>Goal:</italic> Because of the outbreak of coronavirus infection, healthcare systems are faced with the lack of medical professionals. We present a system for the differential diagnosis of coronavirus disease, based on deep learning techniques, which can be implemented in clinics. <italic>Methods:</italic> A recurrent network with a convolutional neural network as an encoder and an attention mechanism is used. A database of about 3000 records of coughing was collected. The data was collected through the Acoustery mobile application in hospitals in Russia, Belarus, and Kazakhstan from April 2020 to October 2020. <italic>Results:</italic> The model classification accuracy reaches 85%. Values of precision and recall metrics are 78.5% and 73%. <italic>Conclusions:</italic> We reached satisfactory results in solving the problem. The proposed model is already being tested by doctors to understand the ways of improvement. Other architectures should be considered that use a larger training sample and all available patient information. |
| format | Article |
| id | doaj-art-44a16b8a286e435495eae5a877354f95 |
| institution | DOAJ |
| issn | 2644-1276 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Engineering in Medicine and Biology |
| spelling | doaj-art-44a16b8a286e435495eae5a877354f952025-08-20T02:41:51ZengIEEEIEEE Open Journal of Engineering in Medicine and Biology2644-12762021-01-01229930310.1109/OJEMB.2021.31270789611002Acoustery System for Differential Diagnosing of Coronavirus COVID-19 DiseaseAnastasia Mitrofanova0Dmitry Mikhaylov1Ilman Shaznaev2Vera Chumanskaia3Valeri Saveliev4https://orcid.org/0000-0003-2488-275XBauman Moscow State Technical University, Moscow, RussiaLebedev Physical Institute, Russian Academy of Sciences, Moscow, RussiaShanghai Jiau Tong University, Shanghai, ChinaImmanuel Kant Baltic Federal University, Kaliningrad, RussiaHuazhong University of Science and Technology, Wuhan, Hubei, China<italic>Goal:</italic> Because of the outbreak of coronavirus infection, healthcare systems are faced with the lack of medical professionals. We present a system for the differential diagnosis of coronavirus disease, based on deep learning techniques, which can be implemented in clinics. <italic>Methods:</italic> A recurrent network with a convolutional neural network as an encoder and an attention mechanism is used. A database of about 3000 records of coughing was collected. The data was collected through the Acoustery mobile application in hospitals in Russia, Belarus, and Kazakhstan from April 2020 to October 2020. <italic>Results:</italic> The model classification accuracy reaches 85%. Values of precision and recall metrics are 78.5% and 73%. <italic>Conclusions:</italic> We reached satisfactory results in solving the problem. The proposed model is already being tested by doctors to understand the ways of improvement. Other architectures should be considered that use a larger training sample and all available patient information.https://ieeexplore.ieee.org/document/9611002/Attention mechanismconvolutional neural networkCOVID-19preliminary diagnosisrecurrent neural network |
| spellingShingle | Anastasia Mitrofanova Dmitry Mikhaylov Ilman Shaznaev Vera Chumanskaia Valeri Saveliev Acoustery System for Differential Diagnosing of Coronavirus COVID-19 Disease IEEE Open Journal of Engineering in Medicine and Biology Attention mechanism convolutional neural network COVID-19 preliminary diagnosis recurrent neural network |
| title | Acoustery System for Differential Diagnosing of Coronavirus COVID-19 Disease |
| title_full | Acoustery System for Differential Diagnosing of Coronavirus COVID-19 Disease |
| title_fullStr | Acoustery System for Differential Diagnosing of Coronavirus COVID-19 Disease |
| title_full_unstemmed | Acoustery System for Differential Diagnosing of Coronavirus COVID-19 Disease |
| title_short | Acoustery System for Differential Diagnosing of Coronavirus COVID-19 Disease |
| title_sort | acoustery system for differential diagnosing of coronavirus covid 19 disease |
| topic | Attention mechanism convolutional neural network COVID-19 preliminary diagnosis recurrent neural network |
| url | https://ieeexplore.ieee.org/document/9611002/ |
| work_keys_str_mv | AT anastasiamitrofanova acousterysystemfordifferentialdiagnosingofcoronaviruscovid19disease AT dmitrymikhaylov acousterysystemfordifferentialdiagnosingofcoronaviruscovid19disease AT ilmanshaznaev acousterysystemfordifferentialdiagnosingofcoronaviruscovid19disease AT verachumanskaia acousterysystemfordifferentialdiagnosingofcoronaviruscovid19disease AT valerisaveliev acousterysystemfordifferentialdiagnosingofcoronaviruscovid19disease |