Google announced it is building a new large-scale language model that will provide health and fitness tips on Tuesday, part of a broader push across the company to develop artificial intelligence health algorithms and robotic doctor tools.
Fitbit (a Google subsidiary) is working with Google Research on the project, which the company calls a “big language model of personal health.” Google said in a press release that it is fine-tuning its algorithms to provide personalized recommendations based on data collected by Fitbit and Pixel devices. Thanks to the latest generation of artificial intelligence chatbot technology, the new Fitbit health coach will be able to use a language-based interface to send “actionable” messages and guidance to users.
“For example, the model might be able to analyze changes in your sleep patterns and sleep quality and then make recommendations on how to change the intensity of your workouts based on those insights,” said Yossi Matias, global head of artificial intelligence at Google. Blog post Health, Climate & Education .
According to Google, the new chatty health robot has already performed well in practice tests based on sleep medicine certification exams. The new tool will run on the company’s Gemini AI model. Google said it is collecting anonymized data from real human case studies collected by certified coaches and health experts to train the AI. The company didn’t reveal a release date for the project, but promised an update “soon.”
Fitbit AI is just one of Google’s many health-related AI projects.Last week, Google began rolling out an artificial intelligence tool called MedLM for chest X-rays, helping doctors with screening surgeries, radiology exams, and diagnoses. The company also announced that the specially customized Gemini model scored 91.1% in a benchmark test based on the U.S. Medical Licensing Examination.Earlier this year, Google researchers published a study showing Their AI has a better clinical attitude and makes better diagnoses than human doctors.
Google also announced a partnership with an Indian company called Apollo Radiology International to provide AI-driven screening for tuberculosis, breast and lung cancer over the next decade, and a partnership with Stanford University School of Medicine to develop a new photo dataset of skin conditions. To help dermatologists train new skin scanning tools for diagnosis.