According to new research, recent advances in acoustic engineering and artificial intelligence have “shown promise” in the identification of respiratory conditions based on sound analysis, which may thus reduce dependence on support services and clinical expertise.
According to new research, recent advances in acoustic engineering and artificial intelligence have “shown promise” in the identification of respiratory conditions based on sound analysis, which may thus reduce dependence on support services and clinical expertise. In a study published in Respiratory Research, investigators reported on the findings of a diagnostic accuracy study for pediatric respiratory disease using an automated cough-sound analyzer available as an app on a smart phone.
In developing the app, the study authors recorded cough sounds that are identifiers of 5 different respiratory diseases. Included within the technology is compliance with existing standard-of-care clinical diagnosis. The app was then used to categorize the coughs of 585 children aged 29 days to 12 years. Results were then compared between the automated cough analyzer diagnoses and consensus clinical diagnoses reached by a panel of pediatricians after reviewing imaging, laboratory findings, and hospital charts.
“The study results show that the performance of the automated algorithm was not inferior to pre-specified endpoints for diagnosis asthma, croup, pneumonia, and lower respiratory tract disease from a group of mixed pediatric respiratory disorder,” the authors wrote.
Specifically, the investigators found that the app had an accuracy of 97% for diagnosing asthma, 85% for croup, 87% for pneumonia, and 83% for lower respiratory tract disease. Based on these results, the authors concluded that the app delivers good diagnostic accuracy in detecting common childhood respiratory diseases. The technology is readily available and can be downloaded onto smartphones to be used in a variety of settings, such as hospitals, ambulatory care, and notably, telehealth services, particularly in rural areas where providers can be difficult for patients to get to.
The algorithm’s diagnostic accuracy may be improved with the additional input of clinical signs such as respiratory rate or chest recessions. The authors note that this will be examined in a future study.
Porter P, Abeyratne U, Swarnkar V, et al. A prospective multicenter study testing the diagnostic accuracy of an automated cough sound centred analytic system for the identification of common respiratory disorders in children [published June 6, 2019]. Respir Res. doi: 10.1186/s12931-019-1046-6.