SCIENCE & TECHNOLOGY NEWS
Amid the ongoing advancements in artificial intelligence, Google is making headway with an innovative approach that uses audio signals to predict early signs of illness.
Sound waves – artistic impression. Image credit: Copilot Designer / Alius Noreika
According to a report by Bloomberg, Google has trained its AI foundation model using 300 million audio samples, including sounds such as coughs, sniffles, and labored breathing, to detect indicators of diseases like tuberculosis. Now, Google has partnered with Salcit Technologies, a respiratory healthcare AI startup based in India, to integrate this technology into smartphones. This could be a game-changer for high-risk communities in regions with limited access to healthcare.
This isn’t Google’s first attempt at digitizing human senses. The company’s venture arm has previously invested in startups using AI to detect diseases through scent. This expansion into bioacoustics—a field that merges biology with acoustics—highlights how AI is increasingly being leveraged to derive valuable insights from sounds produced by humans and animals.
Generative AI, the same technology that powered the rapid adoption of ChatGPT by over 200 million users, is now providing new capabilities in healthcare by enhancing the field of bioacoustics.
Google’s AI model, known as HeAR (Health Acoustic Representations), uses sound signals to predict early symptoms of illness, offering a novel tool in medical diagnostics. This technology can be easily deployed on smartphones, enabling it to track and screen high-risk populations in areas lacking access to expensive diagnostic equipment like X-ray machines.
The practicality of this approach lies in its ability to provide healthcare solutions in remote locations, using just a phone’s built-in microphone and AI software.
Tuberculosis, the world’s leading infectious disease killer, claims nearly 4,500 lives and infects around 30,000 people each day, according to the World Health Organization. While it is treatable, millions of cases remain undiagnosed. In India alone, tuberculosis results in nearly a quarter-million deaths annually, underscoring the importance of early detection.
Google’s AI was trained using a vast dataset of 300 million audio clips from around the globe, including coughs and breathing sounds. These sounds were sourced from non-copyrighted, publicly available materials like YouTube videos and recordings from TB screenings in hospitals in Zambia.
The AI tool, integrated into a smartphone, can be taken to the most remote locations to screen for the disease. By analyzing subtle differences in cough patterns, the AI system can identify early signs of tuberculosis, facilitating early intervention and treatment.
Google’s partnership with Salcit Technologies aims to enhance the accuracy of tuberculosis diagnosis and lung health assessments. Salcit is incorporating Google’s AI model with its own machine learning technology called Swaasa—an AI system named after the Sanskrit word for breath. This collaboration is expected to bring significant improvements in respiratory health monitoring and disease management, particularly in areas with limited access to healthcare professionals and diagnostic tools.
The use of AI to detect diseases through sound represents a significant technological breakthrough with the potential to revolutionize healthcare delivery. As AI models like HeAR become more sophisticated, they could expand beyond tuberculosis detection to identify other respiratory illnesses and even cardiovascular conditions based on sound analysis.
The development of such tools is particularly important in a world where healthcare accessibility remains a challenge for millions of people. By utilizing the existing infrastructure of smartphones, these AI-driven solutions can be scaled rapidly and deployed in both urban and rural settings, making healthcare more inclusive and accessible.
Written by Alius Noreika
Leave a Reply