Acoustic surveillance of cough for detecting respiratory disease using artificial intelligence
Research question Can smartphones be used to detect individual and population-level changes in cough frequency that correlate with the incidence of coronavirus disease 2019 (COVID-19) and other respiratory infections? Methods This was a prospective cohort study carried out in Pamplona (Spain) betwee...
Main Authors: | , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
European Respiratory Society
2022-05-01
|
Series: | ERJ Open Research |
Online Access: | http://openres.ersjournals.com/content/8/2/00053-2022.full |
_version_ | 1797809440088391680 |
---|---|
author | Juan C. Gabaldón-Figueira Eric Keen Gerard Giménez Virginia Orrillo Isabel Blavia Dominique Hélène Doré Nuria Armendáriz Juliane Chaccour Alejandro Fernandez-Montero Javier Bartolomé Nita Umashankar Peter Small Simon Grandjean Lapierre Carlos Chaccour |
author_facet | Juan C. Gabaldón-Figueira Eric Keen Gerard Giménez Virginia Orrillo Isabel Blavia Dominique Hélène Doré Nuria Armendáriz Juliane Chaccour Alejandro Fernandez-Montero Javier Bartolomé Nita Umashankar Peter Small Simon Grandjean Lapierre Carlos Chaccour |
author_sort | Juan C. Gabaldón-Figueira |
collection | DOAJ |
description | Research question
Can smartphones be used to detect individual and population-level changes in cough frequency that correlate with the incidence of coronavirus disease 2019 (COVID-19) and other respiratory infections?
Methods
This was a prospective cohort study carried out in Pamplona (Spain) between 2020 and 2021 using artificial intelligence cough detection software. Changes in cough frequency around the time of medical consultation were evaluated using a randomisation routine; significance was tested by comparing the distribution of cough frequencies to that obtained from a model of no difference. The correlation between changes of cough frequency and COVID-19 incidence was studied using an autoregressive moving average analysis, and its strength determined by calculating its autocorrelation function (ACF). Predictors for the regular use of the system were studied using a linear regression. Overall user experience was evaluated using a satisfaction questionnaire and through focused group discussions.
Results
We followed-up 616 participants and collected >62 000 coughs. Coughs per hour surged around the time cohort subjects sought medical care (difference +0.77 coughs·h−1; p=0.00001). There was a weak temporal correlation between aggregated coughs and the incidence of COVID-19 in the local population (ACF 0.43). Technical issues affected uptake and regular use of the system.
Interpretation
Artificial intelligence systems can detect changes in cough frequency that temporarily correlate with the onset of clinical disease at the individual level. A clearer correlation with population-level COVID-19 incidence, or other respiratory conditions, could be achieved with better penetration and compliance with cough monitoring. |
first_indexed | 2024-03-13T06:52:50Z |
format | Article |
id | doaj.art-7eb9a91decc0483cbb0e2d7ddd49623e |
institution | Directory Open Access Journal |
issn | 2312-0541 |
language | English |
last_indexed | 2024-03-13T06:52:50Z |
publishDate | 2022-05-01 |
publisher | European Respiratory Society |
record_format | Article |
series | ERJ Open Research |
spelling | doaj.art-7eb9a91decc0483cbb0e2d7ddd49623e2023-06-07T13:30:09ZengEuropean Respiratory SocietyERJ Open Research2312-05412022-05-018210.1183/23120541.00053-202200053-2022Acoustic surveillance of cough for detecting respiratory disease using artificial intelligenceJuan C. Gabaldón-Figueira0Eric Keen1Gerard Giménez2Virginia Orrillo3Isabel Blavia4Dominique Hélène Doré5Nuria Armendáriz6Juliane Chaccour7Alejandro Fernandez-Montero8Javier Bartolomé9Nita Umashankar10Peter Small11Simon Grandjean Lapierre12Carlos Chaccour13 Dept of Microbiology and Infectious Diseases, Clinica Universidad de Navarra, Pamplona, Spain Research and Development Dept, Hyfe Inc, Wilmington, DE, USA Research and Development Dept, Hyfe Inc, Wilmington, DE, USA School of Pharmacy and Nutrition, University of Navarra, Pamplona, Spain School of Pharmacy and Nutrition, University of Navarra, Pamplona, Spain Immunopathology Axis, Research Center of the University of Montreal Hospital Center, Montréal, QC, Canada Primary Healthcare, Navarra Health Service-Osasunbidea, Zizur Mayor, Spain Dept of Microbiology and Infectious Diseases, Clinica Universidad de Navarra, Pamplona, Spain Dept of Occupational Medicine – COVID-19 Area, Clinica Universidad de Navarra, Pamplona, Spain Primary Healthcare, Navarra Health Service-Osasunbidea, Zizur Mayor, Spain Fowler College of Business, San Diego State University, San Diego, CA, USA Research and Development Dept, Hyfe Inc, Wilmington, DE, USA Immunopathology Axis, Research Center of the University of Montreal Hospital Center, Montréal, QC, Canada Dept of Microbiology and Infectious Diseases, Clinica Universidad de Navarra, Pamplona, Spain Research question Can smartphones be used to detect individual and population-level changes in cough frequency that correlate with the incidence of coronavirus disease 2019 (COVID-19) and other respiratory infections? Methods This was a prospective cohort study carried out in Pamplona (Spain) between 2020 and 2021 using artificial intelligence cough detection software. Changes in cough frequency around the time of medical consultation were evaluated using a randomisation routine; significance was tested by comparing the distribution of cough frequencies to that obtained from a model of no difference. The correlation between changes of cough frequency and COVID-19 incidence was studied using an autoregressive moving average analysis, and its strength determined by calculating its autocorrelation function (ACF). Predictors for the regular use of the system were studied using a linear regression. Overall user experience was evaluated using a satisfaction questionnaire and through focused group discussions. Results We followed-up 616 participants and collected >62 000 coughs. Coughs per hour surged around the time cohort subjects sought medical care (difference +0.77 coughs·h−1; p=0.00001). There was a weak temporal correlation between aggregated coughs and the incidence of COVID-19 in the local population (ACF 0.43). Technical issues affected uptake and regular use of the system. Interpretation Artificial intelligence systems can detect changes in cough frequency that temporarily correlate with the onset of clinical disease at the individual level. A clearer correlation with population-level COVID-19 incidence, or other respiratory conditions, could be achieved with better penetration and compliance with cough monitoring.http://openres.ersjournals.com/content/8/2/00053-2022.full |
spellingShingle | Juan C. Gabaldón-Figueira Eric Keen Gerard Giménez Virginia Orrillo Isabel Blavia Dominique Hélène Doré Nuria Armendáriz Juliane Chaccour Alejandro Fernandez-Montero Javier Bartolomé Nita Umashankar Peter Small Simon Grandjean Lapierre Carlos Chaccour Acoustic surveillance of cough for detecting respiratory disease using artificial intelligence ERJ Open Research |
title | Acoustic surveillance of cough for detecting respiratory disease using artificial intelligence |
title_full | Acoustic surveillance of cough for detecting respiratory disease using artificial intelligence |
title_fullStr | Acoustic surveillance of cough for detecting respiratory disease using artificial intelligence |
title_full_unstemmed | Acoustic surveillance of cough for detecting respiratory disease using artificial intelligence |
title_short | Acoustic surveillance of cough for detecting respiratory disease using artificial intelligence |
title_sort | acoustic surveillance of cough for detecting respiratory disease using artificial intelligence |
url | http://openres.ersjournals.com/content/8/2/00053-2022.full |
work_keys_str_mv | AT juancgabaldonfigueira acousticsurveillanceofcoughfordetectingrespiratorydiseaseusingartificialintelligence AT erickeen acousticsurveillanceofcoughfordetectingrespiratorydiseaseusingartificialintelligence AT gerardgimenez acousticsurveillanceofcoughfordetectingrespiratorydiseaseusingartificialintelligence AT virginiaorrillo acousticsurveillanceofcoughfordetectingrespiratorydiseaseusingartificialintelligence AT isabelblavia acousticsurveillanceofcoughfordetectingrespiratorydiseaseusingartificialintelligence AT dominiquehelenedore acousticsurveillanceofcoughfordetectingrespiratorydiseaseusingartificialintelligence AT nuriaarmendariz acousticsurveillanceofcoughfordetectingrespiratorydiseaseusingartificialintelligence AT julianechaccour acousticsurveillanceofcoughfordetectingrespiratorydiseaseusingartificialintelligence AT alejandrofernandezmontero acousticsurveillanceofcoughfordetectingrespiratorydiseaseusingartificialintelligence AT javierbartolome acousticsurveillanceofcoughfordetectingrespiratorydiseaseusingartificialintelligence AT nitaumashankar acousticsurveillanceofcoughfordetectingrespiratorydiseaseusingartificialintelligence AT petersmall acousticsurveillanceofcoughfordetectingrespiratorydiseaseusingartificialintelligence AT simongrandjeanlapierre acousticsurveillanceofcoughfordetectingrespiratorydiseaseusingartificialintelligence AT carloschaccour acousticsurveillanceofcoughfordetectingrespiratorydiseaseusingartificialintelligence |