Imagine if your body's reaction to a sandwich was like a unique fingerprint. Instead of one-size-fits-all diets, this work uses wearable sensors and AI to group people by how their blood sugar actually behaves. It helps figure out why some people crash while others spike, allowing for a custom meal plan that fits your specific biology.
Current diabetes diets are generic and often fail because patients have different biological subtypes. This leads to poor glycemic control and ineffective prevention strategies for high-risk individuals.
AI models and analytical methods that identify 'glucotypes' from CGM data and link them to dietary patterns and molecular markers.
If you are a health-tech app developer dealing with low user retention due to generic diet plans — this project developed glucotype identification using generative AI that provides personalized dietary strategies based on individual metabolic heterogeneity.
If you are a CGM manufacturer dealing with a need to move from raw data to actionable insights — this project developed analytical methodologies to link high-temporal glucose data with long-term outcomes like HbA1c.
If you are a nutrition service provider dealing with inconsistent client results — this project developed a way to link macronutrient profiles and meal timing to specific glucose responses, enabling a proof-of-concept precision diet.
Based on available project data, no specific pricing or cost structures are provided as the project is currently in the research and proof-of-concept phase.
The project uses high-throughput molecular analyses and machine learning, which are scalable; however, it is currently moving toward a proof-of-concept clinical study.
Based on available project data, specific licensing terms are not mentioned, though the project involves a consortium of 7 partners including 2 SMEs.
The system integrates directly with Continuous Glucose Monitoring (CGM) wearable technologies to collect high-temporal data.
The project period runs from 2024-10-01 to 2028-09-30, suggesting that commercial readiness will follow the 2028 conclusion.
The consortium is heavily academic, with 5 universities and 1 research institute, reflecting the deep scientific nature of the work. However, the inclusion of 2 SMEs and a 14% industry ratio indicates a clear intent to translate these AI-driven glucose patterns into commercial health products.
Contact the University of Copenhagen (Kobenhavns Universitet) regarding the GLUCOTYPES project.
Contact SciTransfer to connect with the GLUCOTYPES consortium for licensing AI-driven nutrition models.
