A Bayesian framework for identifying personalized models and predicting future blood glucose levels in type 1 diabetes using easily accessible patient data.
A personalized nonlinear physiological model with MCMC Bayesian estimation and particle filtering enhances blood glucose prediction accuracy in type 1 diabetes by accounting for patient-specific dynamics and residual errors, addressing the limitations of existing methods.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- DEXCOM INC
- Filing Date
- 2021-11-12
- Publication Date
- 2026-05-25
AI Technical Summary
Existing methods for predicting blood glucose levels in type 1 diabetes are inadequate due to high inter-patient and intra-patient variability and the complexity of glucose-insulin dynamics, with physiological models being either too simplistic or difficult to personalize effectively.
A personalized nonlinear physiological model using a Markov Chain Monte Carlo (MCMC) Bayesian estimator to determine model parameters, combined with a particle filter for real-time prediction, and a residual error model to account for inaccuracies, based on patient-specific data such as insulin infusion and carbohydrate intake.
The method significantly improves the accuracy of predicting future blood glucose levels, outperforming baseline models in terms of root mean square error, coefficient of determination, and time gain, particularly at longer prediction horizons.
Smart Images

Figure 0007864697000061 
Figure 0007864697000062 
Figure 0007864697000063