Trained on around 300 million pieces of audio data, and in particular around 100 million cough sounds, HeAR is expected to help the Indian startup roll out tuberculosis screening more widely across the country.
“Compared to blood tests and imaging, sound is by far the most accessible information we can get about a person,” Sujay Kakarmath, a product manager at Google Research, said in a statement. “HeAR can detect findings in chest X-rays, tuberculosis, and even detect Covid from cough sounds.”
“With HeAR, we hope that researchers will be able to discover new acoustic biomarkers much faster,” Kakarmath said.
Salcit Technologies aims to use HeAR to leverage research for its Swaasa product, which has a track record of using machine learning to help detect diseases early, bridging the gap in accessibility, affordability and scalability by offering a device-free, location-neutral respiratory health assessment.
HeAR, which is set to be unveiled publicly in March 2024, is designed to help researchers build models that can hear human sounds and detect early signs of disease.
Discover the stories that interest you
“We found that, on average, HeAR ranks higher than other models across a wide range of tasks and for generalizing across microphones, demonstrating its superior ability to capture meaningful patterns in health-related acoustic data,” said Shravya Shetty, director and engineering lead for Health AIat Google Research. Shetty said the HeAR-trained models also achieved high performance with less training data, a crucial factor in the often data-sparse world of healthcare research.
“Our goal is to enable further research into models for specific conditions and populations, even if data are sparse or there are cost or processing barriers,” he said.
Google invited researchers interested in exploring the potential of HeAR to apply for access to the HeAR API.
Through its research, Google said it hopes to continue to help advance the development of future diagnostic tools and monitoring solutions that will help improve health outcomes for communities around the world.
Disclaimer:
The information contained in this post is for general information purposes only. We make no representations or warranties of any kind, express or implied, about the completeness, accuracy, reliability, suitability or availability with respect to the website or the information, products, services, or related graphics contained on the post for any purpose.
We respect the intellectual property rights of content creators. If you are the owner of any material featured on our website and have concerns about its use, please contact us. We are committed to addressing any copyright issues promptly and will remove any material within 2 days of receiving a request from the rightful owner.