Your diagnosis is just a cough away with Google's new AI model
This year, the tech giant introduced Health Acoustic Representations, or HeAR — a bioacoustic foundation model — to help researchers build models that can analyse sound patterns and produce health insights.
The HeAR model, currently available for researchers, has been trained using “300 million pieces of audio data curated from a diverse and de-identified dataset,” and “roughly 100 million cough sounds.”
It captures meaningful patterns in health-related acoustic data and creates a powerful foundation for medical audio analysis, the Google Research Team said, ranking this AI system higher than other models on a wide range of tasks and for generalising across microphones.
An India-based respiratory healthcare company — Salcit Technologies — has designed Swassa, an AI-powered tool that assesses lung health by analysing cough sounds.
The company is planning to integrate HeAR into Swaasa which can help extend its capabilities. To start with, they are using Google’s AI system to enhance its ability to detect TB early.
“Every missed case of TB (tuberculosis) is a tragedy; every late diagnosis, a heartbreak,” says Sujay Kakarmath, a product manager at Google Research working on HeAR. “Acoustic biomarkers offer the potential to rewrite this narrative. I am deeply grateful for the role HeAR can play in this transformative journey.”
Despite being curable, TB often goes undiagnosed due to limited access to affordable healthcare. Researchers believe that AI can play an important role in improving detection and helping make care more accessible and affordable for people around the world.
With HeAR, the India-based healthcare company sees an opportunity to extend screening for TB more widely across India.
Google is also partnering with organisations like the Stop TB Partnership to bring together experts and affected communities with a goal to end TB by 2030.
“Solutions like HeAR will enable AI-powered acoustic analysis to break new ground in tuberculosis screening and detection, offering a potentially low-impact, accessible tool to those who need it most," said Zhi Zhen Qin, digital health specialist with the Stop TB Partnership.
Comments
Post a Comment