Google scientists are zoning in on health care products and innovations powered by artificial intelligence, including a tool that could detect a health condition based on audio of coughing and breathing.
The AI system called Health Acoustic Representations (HeAR) was trained on millions of audio clips of human sounds from the YouTube database and could one day be used by physicians to diagnose diseases or gauge the function of a person’s lungs, according to the science and technology journal Nature.
The journal said using sound as a biomarker for diseases was a concept born during the pandemic when research groups found it possible to detect COVID-19 through the audio of a person’s cough. But there is currently no tool approved by the Food and Drug Administration to diagnose different health conditions using sound.
What’s unique about Google’s HeAR technology is how it can be fine-tuned to perform multiple tasks through something called supervised learning, Nature said.
The Google research team converted over 300 million sound clips of coughing, throat-clearing, laughing and other human noises into spectrograms, which are visual representations of audio frequencies. By blocking out certain segments of the spectrograms, the researchers were able to train HeAR to predict the missing portions.
“This is similar to how the large language model that underlies chatbot ChatGPT was taught to predict the next word in a sentence after being trained on myriad examples of human text,” said Nature.
HeAR’s ability to detect diseases like tuberculosis through cough sounds could particularly benefit patients in communities where chest X-rays are scarce or unavailable, the scientists said.
The research has not been peer-reviewed yet and it's still too soon to know whether or not HeAR will become a commercial product.
During Google Health’s annual “Check Up” event, the company highlighted other technology tools it is using to apply AI to the world of health care and expand access to health information.
Google Lens can now be used in over 150 countries to help determine what abnormalities on your skin could be with the simplicity of snapping a photo of the condition.
A new AI-powered translation tool, Aloud, streamlines the process of translating videos from English to Spanish, making it easier to provide potentially lifesaving information to more people through YouTube videos, Google said. Additionally, the platform will offer free, animation-style courses on the Stanford Medicine Continuing Medical Education YouTube channel in Spanish.
Lastly, the Google-owned Fitbit activity tracker can now use generative AI to provide more “tailored and personalized health insights based on a user's unique needs and preferences.”
A new skin test is being used to help diagnose Parkinson's
Traditionally, doctors diagnosed Parkinson’s first by symptoms: freezing when walking, stiffness and tremors.
