Fitbit is about to get some major AI upgrades, powered by Google’s ‘Personal Health’ LLM

Wearables track important biometric data that can tell you about your personal health, habits, and more. However, interpreting this data takes time, so Google Research and Fitbit are partnering to use artificial intelligence (AI) to make the analysis process easier. 

On Tuesday, at The Check Up, Google Health’s annual event, Google Research and Fitbit announced they are working together to build a Personal Health Large Language model (LLM) that gives users more insights and recommendations based on their data in the Fitbit mobile app. 

Also: The best Fitbit fitness trackers: Expert tested and reviewed

The model will give Fitbit users personalized coaching and actionable insights that help them achieve their fitness and health goals. For example, the LLM could analyze variations in your sleep patterns and suggest recommendations on changes to your workout intensity to improve your sleep quality, Google says in a press release.

The LLM is being built on Google’s Gemini models and fine-tuned on “a de-identified, diverse set of health signals from high-quality research case studies.” To ensure that the models are capable of profound reasoning from the data, accredited coaches and wellness experts are validating the studies, according to the release. 

The model is still being built and Google says it will share more research soon. This model follows another major AI Fitbit update announced last year — Fitbit Labs. 

Also: I tried the AI robot massage coming to Equinox. It was surprisingly relaxing

With Fitbit Labs, Premium users will get early access to experimental AI features, including the ability to conversationally ask questions regarding their health data and even have the AI create charts to visualize their data better. Fitbit Labs will be available later this year. 

Whoop recently introduced a similar feature, Whoop Coach, a GPT-4-supported conversational chatbot that can deliver personalized recommendations and fitness coaching based on the user’s data. I tested the Whoop Coach and was impressed with how integrating your biometric data with a chatbot can help you understand your health information. 

Wearables track important biometric data that can tell you about your personal health, habits, and more. However, interpreting this data takes time, so Google Research and Fitbit are partnering to use artificial intelligence (AI) to make the analysis process easier. 

On Tuesday, at The Check Up, Google Health’s annual event, Google Research and Fitbit announced they are working together to build a Personal Health Large Language model (LLM) that gives users more insights and recommendations based on their data in the Fitbit mobile app. 

Also: The best Fitbit fitness trackers: Expert tested and reviewed

The model will give Fitbit users personalized coaching and actionable insights that help them achieve their fitness and health goals. For example, the LLM could analyze variations in your sleep patterns and suggest recommendations on changes to your workout intensity to improve your sleep quality, Google says in a press release.

The LLM is being built on Google’s Gemini models and fine-tuned on “a de-identified, diverse set of health signals from high-quality research case studies.” To ensure that the models are capable of profound reasoning from the data, accredited coaches and wellness experts are validating the studies, according to the release. 

The model is still being built and Google says it will share more research soon. This model follows another major AI Fitbit update announced last year — Fitbit Labs. 

Also: I tried the AI robot massage coming to Equinox. It was surprisingly relaxing

With Fitbit Labs, Premium users will get early access to experimental AI features, including the ability to conversationally ask questions regarding their health data and even have the AI create charts to visualize their data better. Fitbit Labs will be available later this year. 

Whoop recently introduced a similar feature, Whoop Coach, a GPT-4-supported conversational chatbot that can deliver personalized recommendations and fitness coaching based on the user’s data. I tested the Whoop Coach and was impressed with how integrating your biometric data with a chatbot can help you understand your health information.