The following article is a part of conference coverage from CHEST 2021, being held virtually from October 17 to October 20, 2021. The team at Pulmonology Advisor will be reporting on the latest news and research conducted by leading experts in the field. Check back for more from CHEST 2021.
Changes in voice and breath are significantly correlated with changes in symptoms scores for chronic obstructive pulmonary disease (COPD), with voice signatures detectable even before the symptoms are present. This was among the findings of research presented at the CHEST 2021 Annual Meeting, held virtually October 17 to 20.
Study investigators sought to create a voice-based early warning system for COPD exacerbation, building upon previous research supporting voice-based prediction of changes in lung function values. The prospective cohort study correlated voice and breath samples with COPD assessment test (CAT) scores in 9 participants aged 42 to 75.
Biweekly voice and breath samples and self-reported CAT scores from participants were analyzed over 1 year (418 sessions total). CAT scores were weighted to give emphasis to questions pertaining to cough, sputum, wheezing, and chest tightness. Audio samples were recorded via smart tablet. Researchers conducted regression analysis to predict deviation in the weighted CAT score from baseline and created a retrospective prediction algorithm to predict clinically important increases in CAT scores up to 7 days in advance.
Findings indicated that changes in voice and breath correlated strongly with changes in symptoms scores (R2 = 0.97; mean absolute error = 0.45) and that voice signatures can be detected before the symptoms present themselves (2 point or more weighted CAT score increase up to 7 days in advance) with 94.23% sensitivity and 94.41% specificity.
Investigators concluded that voice-based, noninvasive monitoring of COPD using mobile phone technology is feasible, practical, and cost-effective. “This technique offers the promise of early interventions to reduce exacerbation frequency and severity, advancing personalized medicine for chronic and acute respiratory care,” they noted.
Disclosure: Multiple authors declared affiliations with the medical device and pharmaceutical industry. Please refer to the original article for a full list of disclosures.
Khan MMDA, Naval PP, Kulshreshtha R, Venneti S, Singh A. Voice-based monitoring of COPD. Presented at: CHEST 2021; October 17-20, 2021; Orlando, FL/Virtual. Abstract A2173-A2174.