Published on
updated on
Reading 1 min.
Google has developed a new form of artificial intelligence based on bioacoustics. The idea is to be able to detect diseases by capturing the sounds produced by the human body, using a smartphone’s microphone.
The sounds emitted by the human body, whether breathing, speaking or of course coughing, can provide a lot of information about our health. It was based on this observation that it was decided to develop a solution capable of detecting and monitoring certain diseases, starting with tuberculosis or chronic obstructive pulmonary disease (COPD).
This is how it was born Health Acoustic Representations (HeAR), a bioacoustic baseline model specifically designed to help researchers build models that can listen to human sounds and spot early signs of disease. HeAR was trained with nearly 300 million audio data points, a third of which were cough sounds.
An Indian start-up, Salcit Technologies, specializing in respiratory care, has used it to develop a product capable of analyzing coughing sounds. Called Swaasa, it uses Google AI to assess potential health problems. The idea is to be able to detect tuberculosis as early as possible, by simply studying the sounds of the patient’s cough. A sound sample of around ten seconds is already enough to obtain an accurate diagnosis in more than 90% of cases.
In a country like India, tuberculosis is wreaking havoc, due in part to a lack of access to care for a large part of the population. Improving diagnosis is therefore essential if we hope to eradicate this disease one day.
In 2022, according to the latest figures from the World Health Organization (WHO), around 1.3 million people died from tuberculosis.