Get started
Work

ConvLSTM-Based Time Series Prediction of Blood Glucose Levels Using SimGlucose Simulation Data

Year: 2025
Type: article
Abstract: Accurate short-term prediction of blood glucose levels is crucial for effective diabetesmanagement, enabling timely interventions to prevent hypo- and hyperglycemic events and optimizeinsulin therapy. Glucose dynamics are inherently nonlinear and influenced by factors such as meal intake,insulin dosing, and individual metabolic variability, making accurate forecasting challenging. This studypresents a Convolutional Long Short-Term Memory (ConvLSTM) deep learning framework for bloodglucose prediction using simulated data from the SimGlucose environment, which providesphysiologically realistic glucose–insulin dynamics across virtual patients in different age groups. TheConvLSTM model captures both local and temporal patterns by dividing input sequences into 12subsequences of 12 time steps each. Convolutional layers extract features from each subsequence, whileLSTM layers model sequential dependencies across the full sequence. The model was trained oncontinuous glucose monitoring (CGM) data and evaluated using Root Mean Square Error (RMSE) andMean Squared Error (MSE). Across six test subjects, RMSE values ranged from 1.605 ± 0.562 mg/dL to3.282 ± 1.074 mg/dL, demonstrating accurate and consistent predictions across children, adolescents, andadults. These findings indicate that the ConvLSTM architecture effectively learns complex glucosepatterns and benefits from simulation-based datasets, which overcome the limitations of real-world CGMdata such as scarcity, noise, and variability. By enabling controlled experimentation and reproducibleevaluation, this approach supports the development of reliable, multi-step glucose forecasting models.Overall, the study highlights the potential of ConvLSTM networks combined with simulation-driven datafor intelligent, data-driven diabetes management systems.
Language: English
Field: Medicine
Open Access status: diamond
OpenAlex ID: W7132600595
FWCI:
Cites:
Cited by:
Related to: