UCSD computer scientists trained the FitRec program using data from 1,000 runners’ more than 250,000 total workouts. The algorithm is able to analyze the impact of certain routes’ terrain and lengths, and use past speed and heart rate measures to predict future performance; FitRec can then recommend specific routes to help runners achieve a target heart rate or avoid exceeding a desired maximum rate.
The tool is powered using a type of deep learning called long short-term memory networks, which produces a model that is built on a vast set of previous, more generalized data, but is also capable of analyzing, learning from and making predictions based on a much smaller set of hyper-personalized data from a single user.
More articles about AI:
FDA approves AI-enabled wearable device for at-home vital sign tracking
AI startup streamlining electronic medical billing process receives investment from Northwestern Mutual
Member of Google’s disbanded AI ethics team claims she faces retaliation for walkout
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.