Can Google’s AI Detect Signs Of Sickness Through Listening?

Google’s Health Acoustic Representstions Model uses bioacoustics as a way to analyse sounds such as coughs and breathing as a way to detect early signs of health conditions like TB and COPD.

Using smartphone microphones, this tech brings accessible solutions for those who are in remote areas, for example, where medical equipment may not be available. The model, with a database of 300 million audio clips, recognises health-related patterns that could indicate disease.

Google shared on their blog post, “HeAR is now available to researchers to help accelerate 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.”

How Is Google’s AI Being Used To Fight Tuberculosis?

Google’s HeAR model specialises in detecting TB by differentiating between cough sounds. In collaboration with a company, Salcit Technologies in India, HeAR is used in the Swaasa app, which has shown a 94% accuracy rate in TB screening.

“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,” shared Sujay Kakarmath, a product manager at Google Research, who is working on HeAR.

What Other Health Conditions Could Google’s AI Help Detect?

Google’s HeAR model is also being tested for detecting other conditions, such as picking out the early stages of breast cancer. They intend on looking at the use of ultrasound in combination with HeAR for breast cancer screening, for cost-effective diagnostic options.

This is an exciting development because the use of smartphones, a gadget that about 60% of the population owns, makes detection that much more possible and accessible around the world.

Who Else Is Google Partnering With?

Google is partnering with companies like Salcit Technologies and Apollo Hospitals to bring more tech and infrastructure to remote areas for better health care in areas where it isn’t usually accessible.

Also, support from organisations such as the StopTB Partnership will also help with this. “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.

While there are a few more things that need to be worked on. Maintaining the quality of audio samples is essential for its operation, particularly in noisy environments.

The technology is great with how beneficial it can be, but it must be introduced carefully alongside existing healthcare practices. Users also need clear guidance on how to effectively use these digital tools. Properly applied, this technology can complement and extend traditional healthcare services. Google had concluded, “We 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 around the globe through our research.”