Cough App

Researchers are using the power of smartphone technology and artificial intelligence (AI) to analyze and monitor cough sounds. The technique could potentially provide early detection of respiratory illness — a leading cause of death and disability worldwide. It may also one day help to predict future outbreaks of diseases such as COVID-19 or tuberculosis.

In a preliminary trial last year, the cough detection algorithm was used to examine nearly 700,000 sound samples with a sensitivity and specificity of more than 96 percent. The system can distinguish between a variety of cough-related conditions including COVID-19, influenza, asthma, chronic obstructive pulmonary disease (COPD), and gastroesophageal reflux.

Known as Hyfe AI, the system provides important diagnostic information in real time so that cough sounds can be detected, monitored, and classified objectively. Subtle changes that could be important for determining the long-term impact of therapy or the onset of new symptoms can also be tracked. The availability of reliable metadata — such as location, time, and frequency — allows these additional variables to be identified and correlated. But, perhaps more importantly, Hyfe AI can be deployed at any scale anywhere in the world for improved screening and risk management.