They analyze the sound of cough to identify the severity of patients with COVID-19

2023-09-22 16:45:15

Although most people affected by COVID-19 now have milder symptoms and recover within a few weeks, the global pandemic caused by the SARS-CoV-2 virus remains a major health problem. Some affected people end up developing more severe illness and pneumonia, which often has a worse prognosis.

Although protocols have been developed to assess patient risk, diagnostic and prognostic tools are mainly based on expensive and difficult to access imaging methods, such as radiography, ultrasound or computed tomography. Thus, there is a need to develop a simpler and more easily accessible prognostic tool that allows healthcare providers to identify patients who have developed or are at risk of developing serious illness. In this way, patient management and early intervention would be facilitated even at home or in primary care centers.

Now, scientists have carried out a study based on the analysis and interpretation of cough sounds in the initial phases of COVID-19. This method is presented as a potential, simple and accessible predictive tool to assess the risk of suffering from severe pneumonia.

The research was carried out by a team led by the Institute of Bioengineering of Catalonia (IBEC) and the Hospital del Mar in Barcelona, ​​with the collaboration of the Polytechnic University of Catalonia (UPC), the Center for Biomedical Research in Bioengineering Network, Biomaterials and Nanomedicine (CIBERBBN) and the Network Biomedical Research Center for Respiratory Diseases (CIBERES), in Spain. The team has been led by Clare Davidson, from IBEC.

The research was conducted using smartphone recordings of voluntary coughing sounds in 70 patients with SARS-CoV-2 infection disease within the first 24 hours after arrival at the hospital. The acoustic analysis of these recordings carried out by the IBEC made it possible to detect significant differences between the sounds of the patients depending on the severity of the respiratory pathology, which was previously confirmed with imaging tests and the need for supplemental oxygen. The results show that this analysis could be used to classify patients with COVID-19 as mild, moderate or severe and monitor patients with persistent COVID. The work was carried out with data collected between April 2020 and May 2021 at the Hospital del Mar.

Cough frequency: a key parameter

Raimon Jané, professor at the UPC and principal investigator at IBEC and CIBERBBN, leads the Biomedical Signal Processing and Interpretation (BIOSPIN) group at IBEC, which has developed the methodology and algorithms for acoustic analysis of cough signals acquired with smart phones. Using a statistical model known as a linear mixed model, the team found five parameters, based on sound frequencies, that were significantly different in the coughs of patients with different levels of disease severity and pneumonia progression. Thus, these differences may reflect the progressive alterations of the respiratory system in patients with COVID-19.

New research indicates that an analysis of the sound of a patient’s cough may be a quick, easy and inexpensive way to identify the severity of COVID-19 or another respiratory illness. (Illustration: Amazings/NCYT)

“Although acoustic cough analysis methods have been proposed in the past to diagnose respiratory diseases, we wanted to go one step further and specifically explore the relationship between the acoustic characteristics of cough and the different levels of severity of pneumonia in patients with COVID-19,” details Jané, one of the authors of the study.

The authors of the study explain that the use of cough can serve both to detect patients with severe COVID-19 early and to monitor their evolution, evaluating possible complications, even remotely. Now, however, work will have to continue with data from more patients to confirm the results of this cross-sectional study, which allows cough analysis to be used as a diagnostic tool in patients with COVID-19 or other respiratory diseases.

For this reason, Dr. Joaquim Gea, emeritus head of the Pulmonology Service, researcher at HMRI (Hospital del Mar Research Institute) and co-author of the work, indicates that his conclusions can be useful “in areas with insufficient medical infrastructure or in emergency situations.” , helping to identify and isolate COVID-19 patients in a timely manner, facilitating appropriate medical care and the implementation of control measures.”

Another notable element is that, although the study has focused on COVID-19, it opens the door to using this model in other respiratory pathologies.

The study is entitled “Differences in acoustic features of cough by pneumonia severity in patients with COVID-19: a cross-sectional study”. And it has been published in the academic journal European Respiratory Journal. (Source: IBEC)