Integrating Bayesian Approaches and Expert Knowledge for Forecasting Continuous Glucose Monitoring Values in Type 2 Diabetes Mellitus

TL;DR

This paper presents a novel Bayesian and expert knowledge integrated system for forecasting blood glucose levels in Type 2 diabetes, demonstrating improved accuracy and personalized management potential.

Contribution

It introduces a new forecasting framework combining Bayesian networks and structural time series models tailored for T2DM, utilizing expert knowledge and diverse data sources.

Findings

Mean absolute error of 6.41 mg/dL for 15-minute forecasts

First application of ShanghaiT2DM dataset for glucose prediction

Forecasting accuracy supports personalized diabetes management

Abstract

Precise and timely forecasting of blood glucose levels is essential for effective diabetes management. While extensive research has been conducted on Type 1 diabetes mellitus, Type 2 diabetes mellitus (T2DM) presents unique challenges due to its heterogeneity, underscoring the need for specialized blood glucose forecasting systems. This study introduces a novel blood glucose forecasting system, applied to a dataset of 100 patients from the ShanghaiT2DM study. Our study uniquely integrates knowledge-driven and data-driven approaches, leveraging expert knowledge to validate and interpret the relationships among diabetes-related variables and deploying the data-driven approach to provide accurate forecast blood glucose levels. The Bayesian network approach facilitates the analysis of dependencies among various diabetes-related variables, thus enabling the inference of continuous glucose monitoring (CGM) trajectories in similar individuals with T2DM. By incorporating past CGM data including inference CGM trajectories, dietary records, and individual-specific information, the Bayesian structural time series (BSTS) model effectively forecasts glucose levels across time intervals ranging from 15 to 60 minutes. Forecast results show a mean absolute error of 6.41 mg/dL, a root mean square error of 8.29 mg/dL, and a mean absolute percentage error of 5.28%, for a 15-minute prediction horizon. This study makes the first application of the ShanghaiT2DM dataset for glucose level forecasting, considering the influences of diabetes-related variables. Its findings establish a foundational framework for developing personalized diabetes management strategies, potentially enhancing diabetes care through more accurate and timely interventions.