Indian startup to detect TB based on cough sounds with Google’s AI model

New Delhi, Aug 20: In a bid to fight the rising burden of tuberculosis (TB) in India, Indian startup Salcit Technologies is exploring to use of Google’s Health Acoustic Representations (HeAR) model to enhance early detection of TB based on cough sounds, the tech giant said on Tuesday.

In a blog post, Google said that its HeAR bioacoustic foundation model is trained on approximately 300 million pieces of audio data, and in particular roughly 100 million cough sounds. It can help extend screening for TB more widely across India, the company said.

The Hyderabad-based Salcit Technologies will use the HeAR model to build on research for its product Swaasa, it noted.

Launched in 2020, Swaasa uses an AI-driven algorithm that can assess if human lungs are abnormal.

HeAR was introduced in March 2024 and is designed to help researchers build models that can listen to human sounds and flag early signs of disease.

“Compared to blood tests and imaging, sound is by far the most accessible piece of information that we can get about a person. HeAR can pick up chest x-ray findings, tuberculosis, and even detect Covid from cough sounds,” said Sujay Kakarmath, a product manager at Google Research.

“In places where access to advanced medical resources is scarce, we can imagine a future where a healthcare professional with a machine learning model and a phone can collect a sample of your sound and inform clinical care. With HeAR, we hope that researchers will be able to discover new acoustic biomarkers a lot faster,” he added.