Google develops bioacoustic healthcare AI model “HeAR” that can detect tuberculosis by analyzing patients’ coughs – GIGAZINE

Google’s research organization “Google Research” has developed an AI model ” that can detect early symptoms of diseases such as tuberculosis by training it using 100 million cough sounds.Health Acoustic Representations(HeAR)” was released.

[2403.02522] HeAR — Health Acoustic Representations
https://arxiv.org/abs/2403.02522

Can we hear disease before we see it? – YouTube

Researchers built an AI model to detect diseases based on coughs
https://blog.google/technology/health/ai-model-cough-disease-detection/

Google and Others Are Developing AI That Can Hear Signs of Sickness – Bloomberg
https://www.bloomberg.com/news/newsletters/2024-08-29/google-and-others-are-developing-ai-that-can-hear-signs-of-sickness

Indian AI startupsSalcit TechnologiesDeveloped in partnership with , HeAR was trained on over 300 million sniffles, coughs, sneezes, and breathing sounds from Zambian hospitals and YouTube videos, with approximately 100 million cough sounds included in the training data.

HeAR uses information from countless data to identify health-related sound patterns. According to Google, HeAR outperforms similar models in a variety of tasks and has been shown to have superior performance in capturing patterns in health-related acoustic data. Google says, “HeAR is an important component in the world of healthcare research, where data is often scarce.”

In addition, Google is working with HeAR and Salcit Technologies to developSwaasa” Swaasa is a model that uses AI to analyze the sounds of a patient’s cough to assess the health of the lungs, and is capable of diagnosing the disease with approximately 94% accuracy using 10-second recordings.

Tuberculosis, once considered an incurable disease, is now treatable thanks to advances in medical technology. However, millions of patients around the world are left untreated every year because they are unable to access medical services due to poverty and other issues. Organizations such as the WHO are working to eradicate tuberculosis.ActivitiesBut improved diagnosis is essential to eradicating TB, and that’s where AI like HeAR comes in. AI can play a key role not only to improve the TB detection process, but also to make treatment more accessible and affordable for people around the world.

“It’s heartbreaking whenever we see a TB diagnosis delayed for any reason. But acoustic biomarkers such as HeAR have the potential to put an end to this sad story. We’re incredibly grateful for the role HeAR can play in the fight against TB,” said Sujay Kakarmath, product manager at Google Research.StopTB Partnership“Solutions like HeAR enable AI-powered acoustic analysis, breaking new ground in TB screening and detection,” said Qin Zhizhen, Digital Health Specialist at TB Healthcare. “This could make the tool more accessible to people in poor countries where TB is endemic, without imposing a financial burden on them.”

“HeAR is a major step forward in acoustic health research. We hope to advance the development of future diagnostic tools and monitoring solutions for tuberculosis, chest, pulmonary and other disease areas, and contribute to improving the health of communities around the world through our research,” Google Research reported.