
A new study has revealed that a tool long used to diagnose COPD and asthma could be effective in pre-screening patients for other respiratory infections, including COVID-19.
Sonde Health, a health monitoring technology company, reports that the study, which was published in the Journal of Medical Internet Research, suggests that its respiratory responsive vocal biomarker (RRVB) machine learning model can differentiate patients with COVID-19 from healthy individuals with about 70% accuracy.
The study, conducted in collaboration with Montefiore Health System, Brigham and Women’s Hospital, UC San Diego Health System, and Deenanath Mangeshkar Hospital in Pune, India, found that the model achieved 73% sensitivity and 63% specificity for the entire COVID-19 population that was tested. And it detected 66% of asymptomatic COVID-19 subjects using only a six-second recording of an “aah” vowel sound on patient smartphones.
Erik Larsen, PhD, senior vice president of clinical development and customer success at Sonde Health, said these findings suggest that the tool could be used to uncover multiple respiratory conditions including COVID, COPD and other illnesses before symptoms arise.
“We have shown that the same technology originally developed for asthma and COPD can be applied to pre-screen for COVID-19 with meaningful sensitivity and specificity,” Dr. Larsen said. “This study demonstrates the robustness of our tool across conditions, geographies, and languages, paving the way for broader respiratory disease monitoring and surveillance efforts going forward.”
Sunit Jariwala, MD, professor of medicine and director of clinical research and innovation in the Department of Medicine at Einstein College of Medicine and Montefiore Health System, served as principal investigator for the study.
"This study highlights the potential of vocal biomarkers to improve access and outcomes for diverse and varied populations with respiratory diseases,” he said. “By utilizing a digital tool that is non-invasive and can be easily scaled and distributed, we can effectively monitor respiratory health and identify individuals’ levels of symptoms and risk.”