Google’s HeAR AI model can hear if you’re sick

A new model of artificial intelligence is being developed by Google GOOGLE could make diagnosing tuberculosis (TB) and other respiratory conditions as easy as recording a voice note.

Google is preparing one of its fundamental AI models listen for signs of illness using sound signals such as coughing, sneezing and sniffing. This technology, which would work using people’s smartphone microphones, could revolutionize diagnostics for communities where advanced diagnostic tools are hard to come by.

The tech giant is partnering with Indian respiratory healthcare AI startup Salcit Technologies. The technology, which was introduced earlier this year as Health Acoustic Representations, or HeAR, is what’s known as a bioacoustic foundation model.

HeAR was then trained on 300 million audio data, including 100 million cough sounds, to learn to identify patterns in the sounds.

Salcit then uses this AI model in combination with its own Swaasa product, which uses AI to analyze cough sounds and assess lung health, to help research and improve early detection of TB based solely on cough sounds.

Between three and four million cases of TB remains unreportedaccording to the non-profit organization supported by the United Nations, The Stop TB Partnership. If untreated, the death rate from TB is greater than 50%.

“Every missed case of tuberculosis is a tragedy; every late diagnosis, a heartache,” Sujay Kakarmath, a product manager at Google Research who works on HeAR, said in a statement. “Acoustic biomarkers offer the potential to rewrite this narrative.”

The advent of AI has produced new opportunities for the early detection and diagnosis of a wide range of diseases. From identifying signs of chronic diseases, to identifying previously unknown types of endometrial cancer, to early detection of Parkinson’s disease, researchers around the world they have already found Extremely useful classic AI – and the technology is still in its infancy.

Most recently, UCLA said it is developing a new AI-enhanced test that could help speed up the process for diagnosis of Lyme diseasethe university said Monday.