> ## Content Index
> Fetch the complete content index at: https://www.ai-360.online/llms.txt
> Use this file to discover other available public pages before exploring further.

# Google’s HeAR AI model detects disease from cough sounds
- URL: https://www.ai-360.online/googles-ai-model-detects-disease-through-cough-sounds/
- Published: 2024-08-22T04:50:00.000Z
- Updated: 2026-11-04T10:55:26.000Z
- Description: Google’s HeAR bioacoustic model, trained on 300 million audio clips including about 100 million coughs, could help detect diseases such as TB.
- Author: AI-360
- Tags: 1. Enterprise AI, News, google, healthcare

Google researchers have developed an AI model that can detect diseases, by analysing cough sounds, potentially assisting early disease detection and healthcare accessibility.

The Health Acoustic Representations (HeAR) model, a bioacoustic foundation model, was trained on 300 million pieces of audio data, including approximately 100 million cough sounds. This extensive training enables HeAR to discern subtle patterns in health-related sounds, creating a powerful foundation for medical audio analysis.

"Every missed case of tuberculosis is a tragedy; every late diagnosis, a heartbreak," said Sujay Kakarmath, a product manager at Google Research working on HeAR. "Acoustic biomarkers offer the potential to rewrite this narrative."

## Sign up for AI-360

AI from all perspectives: Where business & innovation meets application & regulation.

Subscribe 

Email sent! Check your inbox to complete your signup. 

No spam. Unsubscribe anytime.

The model's potential is particularly promising for diseases like tuberculosis (TB), which often goes undiagnosed due to limited access to healthcare services. In India, Salcit Technologies is exploring HeAR's capabilities to enhance their Swaasa® product, which uses AI to analyse cough sounds and assess lung health.

Google's research team found that HeAR outperforms other models across various tasks and generalises well across different microphones. Importantly, models trained using HeAR achieved high performance with less training data, a crucial factor in healthcare research where data can be scarce.

The StopTB Partnership, a United Nations-hosted organisation, has expressed support for this approach. Zhi Zhen Qin, digital health specialist with the partnership, stated, "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."

Google has made HeAR available to researchers, aiming to accelerate the development of custom bioacoustic models for specific conditions and populations. This initiative could lead to significant advancements in diagnostic tools and monitoring solutions for TB, chest, lung, and other diseases.

The technology could hold the promise of improving health outcomes for communities worldwide, particularly in areas with limited access to traditional healthcare resources.

---

[To read more articles like this, and be notified of new content published each week, Sign Up to our FREE newsletter](#/portal/signup/free)

---