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.

JP7864697B2Active Publication Date: 2026-05-25DEXCOM INC
View PDF 6 Cites 0 Cited by

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

Technical Problem

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.

Method used

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.

Benefits of technology

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.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007864697000061
    Figure 0007864697000061
  • Figure 0007864697000062
    Figure 0007864697000062
  • Figure 0007864697000063
    Figure 0007864697000063
Patent Text Reader

Abstract

A method for predicting future blood glucose concentrations for an individual patient includes selecting an individualized nonlinear physiological model of glucose-insulin dynamics, the selected model having a plurality of model parameters for which values ​​are determined; estimating values ​​for each of the model parameters in the plurality of model parameters, a first subset of the model parameters having values ​​estimated from a priori population data and a second subset of the model parameters having values ​​personalized for the individual patient by applying a parameter estimation technique to a priori information and data for the individual patient to obtain posterior information; and applying a nonlinear prediction technique to the selected model using the estimated values ​​for each of the model parameters to obtain a predicted blood glucose concentration for the individual patient at a future time.
Need to check novelty before this filing date? Find Prior Art