Smartphone-Enabled Cough Detection in Severely Exacerbated COPD: An Exploratory Pilot Study

Chronic obstructive pulmonary disease (COPD) shows rising incidence worldwide. Progressive decline in lung function is characteristic for the disease and results in various signature COPD symptoms. A significant part of COPD-associated morbidity and mortality is due to acute exacerbations, which often require hospital usage, thus disproportionately impacting healthcare expenses. Novel digital health technologies allowing remote patient monitoring are desirable to improve COPD management by tailoring treatment- and follow-up strategies. We here tested the feasibility and biomarker potential of smartphone-enabled cough monitoring during and after AECOPD in hospitalized patients. The study was designed as a single-center, prospective, longitudinal, observational cohort study and enrolled 23 subjects. A contact-free, near real-time, smartphone-enabled cough detection system was used for automated cough detection and quantification based on audio recordings. Cough counts were correlated to various clinical and biochemical markers. Cough levels were highest at study enrollment (approx. 15 coughs per hour) and gradually declined over time toward recovery (to below 5 coughs per hour) (incidence rate ratio (IRR): 0.97 [0.95–0.98], p p p Automated, contact-free, smartphone-enabled cough detection was feasible in COPD patients hospitalized for AECOPD. Cough counts declined over time and were associated with relevant clinical and biochemical markers. Our approach enables telemonitoring of AECOPD in near real-time and warrants further development to possibly establish cough count as an early digital biomarker for emerging AECOPD, allowing swift intervention and associated cost reductions.