PosterPDF Available

Preliminary results of an exploratory, observational cohort study on smartphone-enabled cough detection in patients with COVID-19

Authors:
  • Resmonics AG

Figures

Content may be subject to copyright.
www.kssg.ch
Preliminary results of an exploratory, observational cohort study
on smartphone-enabled cough detection in patients with COVID-19
Frank Rassouli1, Maximilian Boesch1, Florent Baty1, Peter Tinschert2,3,4, Filipe Barata2,3, Iris Shih2,3,4, David Cleres2,3, Tobias Kowatsch2,3, Elgar Fleisch2,3,
Martin H. Brutsche1
1Lung Center, Cantonal Hospital St. Gallen, 2Department of Management, Technology, and Economy, ETH Zurich, 3Centre for Digital Health Interventions, ETH Zurich & University of St. Gallen,
4Resmonics AG, Zurich
Introduction
COVID-19 mainly manifests as a respiratory disease, and cough is a major symptom. Age and certain comorbidities are recognized risk factors for severe disease and hospitalization.
Mobile technology could help to more precisely predict the course of disease. We set out to detect cough frequencies in hospitalized patients with COVID-19-and non-COVID-19-
pneumonia and correlate these data to a variety of clinical parameters.
Methods
Smartphone-enabled detection of coughs technically based on a convolutional neural network-based model was used in 33 patients with COVID-19-pneumonia and 12 patients with
non-COVID-19-pneumonia in a non-ICU setting. Clinical data were extracted from medical records and correlated to cough frequencies.
Results
The technology reliably detected coughing events in all COVID-19-and non-COVID-19-patients over extended periods of time (Figure 1). Hourly cough counts decreased with
hospitalization length (Figure 2). In contrast to non-COVID-19, significant positive correlations between cough counts and CRP, body temperature, FiO2 and breathing rate were
found in COVID-19-pneumonia. In contrast, no correlation with markers of clotting or tissue damage was found (Table 1).
Conclusion
Smartphone-enabled quantification of cough is feasible in hospitalized patients with COVID-19- and non-COVID-19-pneumonia. Although cough frequencies varied greatly between
individuals, significant associations of cough counts with surrogate markers of COVID-19 disease activity were found. The smartphone-based detection of coughing rates could assist
in monitoring and predicting the course of disease.
Figure 2 cough counts decrease with the length of hospital
stay both in COVID-19- and non-COVID-19-pneumonia
Figure 1 case numbers and descriptive statistics Table 1 clinical correlates
of cough counts in COVID-19
Clinical
p
arameter
Correlation
coefficient
Significance
level
CRP
0.32
p<0.05
Body
temperature
0.21
p<0.01
FiO
2
0.33
p<0.001
Breathing rate
0.23
p<0.05
D
-Dimer
-0.003
n.s.
LDH
0.14
n.s.
ERS International Congress 2021
ResearchGate has not been able to resolve any citations for this publication.
ResearchGate has not been able to resolve any references for this publication.