New artificial intelligence can diagnose pneumonia by listening to someone cough

If it is rolled out widely, scientists say people will be able to diagnose themselves with the illness without going to the doctor

AI could help diagnose conditions, it’s claimed (Getty Images/iStockphoto)

New artificial intelligence-based technology can diagnose pneumonia by listening to someone cough.

If it is rolled out widely, scientists say people will be able to diagnose themselves with the illness without going to the doctor and costs for the NHS should fall.

The method uses artificial intelligence to work out whether the sound of a cough suggests someone is suffering from the deadly respiratory condition.

Every room and recording device is different, which means the devices have been fitted with room impulse responses.

These measure how the acoustics of a space react to different sound frequencies.

By combining this information with the recorded cough sounds, the algorithm can work in any environment.

Plans are already in place to apply the algorithm so patients can be monitored at home.

The team are also looking to develop an app based on it for social care at home.

Researcher Jin Yong Jeon from Hanyang University in South Korea said: “Automatically diagnosing a health condition through information on coughing sounds that occur continuously during daily life will facilitate non-face-to-face treatment.

“It will also be possible to reduce overall medical costs.

“Our research team is planning to automate each step-by-step process that is currently performed manually to improve convenience and applicability.”

Pneumonia affects eight in every 100,000 Brits every year, according to the NHS, and particularly impacts older people and very young children.

It is crucial that the disease is caught as early as possible in order to give sufferers the best chance of recovering.

Existing ways of diagnosing it consist of a range of blood tests and chest scans, and a doctor needs to suspect someone has pneumonia before treatment can begin.

The findings were presented at the 183rd meeting of the of the Acoustical Society of America in Nashville, Tennessee.