This technology is a non-invasive, wearable device that uses machine learning to automatically monitor dietary intake and provide real-time data for nutrition tracking.
Current methods for monitoring nutrition and weight management rely heavily on manual logging and can be inaccurate, time-consuming, and prone to user error. Currently, there are no robust and reliable methods for tracking nutrition and monitoring biometric data for individuals struggling with diabetes, eating disorders, cardiovascular diseases, and other nutrition-related conditions. Further, commonly used approaches for wearable sensing critical for the management of diabetes, such as glucose monitoring, are limited in their function due to sensor placement errors, connectivity issues, and the need for periodic calibrations.
This technology is a device that estimates a user’s nutrition state by capturing biometric data such as heart rate, respiratory rate, oxygen saturation, and movement patterns. The device uses a machine learning algorithm to accurately and reliably monitor dietary information and eliminates the need for manual logging. The technology was designed to function independently of separate hardware while also integrating with existing health applications, enhancing usability. The device can also be used to monitor activity levels, providing a personalized solution for patients struggling with a wide range of nutrition-related conditions.
Alexander Goldberg, M.D., Ph.D. Candidate
IR CU25198
Licensing Contact: Jerry Kokoshka