‍

Blake, Wm. Christ Healing the Woman With an Issue of Blood. 1780.

‍

Researchers have engineered an AI-powered app that can distinguish tuberculosis from other diseases by the sound of the patient’s cough, providing a far simpler and cheaper method of detection than what doctors conventionally use.

The research team trained and tested their smartphone-based diagnostic tool on recordings of coughs collected in a healthcare center, analyzing 33,000 spontaneous coughs. Right now, the app isn’t foolproof, but it could nevertheless prove useful in low-income countries as a screening tool, helping to catch cases and interrupt transmission.

Scientists are most excited by the consequences of this technology down the road. Coughs and other body sounds could be used as “acoustic biomarkers,” indicating changes in health. Using AI, these sounds could be analyzed to rapidly detect health problems and provide care to areas lacking hospitals.

“It’s a sea change to have a common device, the smartphone, which everyone has sitting by their bedside or in their pocket to help observe your coughs,” said Jamie Rogers, product manager at Google Health. Google’s newest Pixel phones have cough and snore detection available.