Earlier this year, Google introduced Health Acoustic Representations, or HeAR, a bioacoustic foundation model designed to help researchers build models that can listen to human sounds and flag early signs of disease. The Google Research team trained HeAR on 300 million pieces of audio data curated from a diverse and de-identified dataset, and they trained the cough model, in particular, using roughly 100 million cough sounds.
HeAR Enables Efficient Bioacoustic Data Analysis
According to Google, HeAR learns to discern patterns within health-related sounds, creating a robust foundation for medical audio analysis. The company claims that, on average, HeAR ranks higher than other models on a wide range of tasks and for generalizing across microphones, demonstrating its superior ability to capture meaningful patterns in health-related acoustic data. Models trained using HeAR also achieved high performance with less training data, a crucial factor in the often data-scarce world of healthcare research, Google said in an official statement.
HeAR is now available to researchers to help accelerate the development of custom bioacoustic models with less data, setup and computation. “Our goal is to enable further research into models for specific conditions and populations, even if data is sparse or if cost or compute barriers exist”, they added.
HeAR Enhances Swaasa’s AI-Powered Cough Analysis
Salcit Technologies, an India-based respiratory healthcare company, has built a product called Swaasa® that uses AI to analyze cough sounds and assess lung health. Google stated that the company is now exploring how HeAR can help expand the capabilities of its bioacoustic AI models. Swaasa® is using HeAR to support research and enhance the early detection of TB based on cough sounds, according to Google’s blog post.
Though tuberculosis (TB) is curable, millions of cases go undetected each year, frequently due to a lack of convenient access to healthcare. The eradication of tuberculosis (TB) depends on accurate diagnosis, and artificial intelligence (AI) can significantly contribute to improved detection and increased accessibility and affordability of care for people worldwide. Google claims that Swaasa® has a history of using machine learning to help detect diseases early, bridging the gap with accessibility, affordability and scalability by offering location-independent, equipment-free respiratory health assessment. “With HeAR, they see an opportunity to extend screening for TB more widely across India by building on this research”, Google opined.
A product manager at Google Research working on HeAR, Sujay Kakarmath said, “Every missed case of tuberculosis is a tragedy; every late diagnosis, a heartbreak”. “Acoustic biomarkers offer the potential to rewrite this narrative. I am deeply grateful for the role HeAR can play in this transformative journey.”
UN-Backed Partnership Aims to Revolutionize TB Screening with HeAR
Google explained how the approach is supported by organizations, including The StopTB Partnership, a United Nations-hosted organization that brings together TB experts and affected communities 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,” opined digital health specialist with the Stop TB Partnership Zhi Zhen Qin.
According to Google, HeAR represents a significant step forward in acoustic health research. They hope to advance the development of future diagnostic tools and monitoring solutions in TB, chest, lung, and other disease areas, and help improve health outcomes for communities worldwide through our research. Researchers interested in exploring HeAR can learn more and request access to the HeAR API.
