New AI-powered technology can diagnose pneumonia by listening to someone cough.
If it spreads, scientists say people will be able to self-diagnose the disease without consulting a doctor and NHS costs should come down.
The method uses artificial intelligence to figure out if the sound of a cough indicates someone has the deadly respiratory disease.
Every room and every recording device is different, so the devices were equipped with room impulse responses.
These measure how the acoustics of a room react to different sound frequencies.
Combining this information with recorded cough sounds allows the algorithm to work in any environment.
There are already plans to roll out the algorithm so patients can be monitored at home.
The team also wants to develop an app based on it for home social care.
Researcher Jin Yong Jeon of Hanyang University in South Korea said, “Automatically diagnosing a health condition based on information about cough sounds that occur continuously in daily life will facilitate face-to-face treatment.”
“It will also be possible to reduce overall medical costs.
“Our research team plans to automate each step-by-step process currently done manually to improve convenience and applicability.”
Pneumonia affects eight out of 100,000 Britons every year, according to the NHS, and particularly affects the elderly and very young children.
It is crucial that the disease is detected as early as possible to give those affected the best chance of recovery.
Existing ways to diagnose consist of a series of blood tests and chest scans, and a doctor must suspect someone has pneumonia before treatment can begin.
The findings were presented at the 183rd meeting of the Acoustical Society of America in Nashville, Tennessee.