Google is harnessing artificial intelligence (AI) to enhance its core model for predicting early signs of illness using audio signals.

The company’s AI division uses bioacoustics, which blends biology and sounds, to assist researchers in understanding how pathogens like bacteria and other infections impact the human voice.

Google says this technology could serve as a valuable alternative in areas where access to quality healthcare is limited. It requires users to use only a smartphone microphone.

According to Google, the AI model, known as Health Acoustic Representations, has been applied to 300 million two-second audio samples, which include coughing, sneezing, and breathing patterns. Google added that this model can detect subtle differences in patients’ cough patterns, enabling it to identify early indicators of disease improvement or deterioration.

Source: Saudi Press Agency