Diabetes Management Through Glucose Dynamics Analysis Network: A Novel Approach for Accurate Blood Glucose Level...

Accurate real-time prediction of blood glucose (BG) levels is essential for improving insulin-dosing decision support systems, including closed-loop insulin delivery and bolus calculators. However, existing deep learning models often suffer from high computational complexity, limited utilization of physiological factors, and inadequate handling of temporal glucose dependencies.

This study proposes Glucose Dynamics Analysis Network (GlucoDiaNet), a hybrid framework for BG prediction integrating spline interpolation for missing value handling, a Dilated Convolutional Residual Network (DilaConv-ResNet) for spatial-temporal feature extraction, Adamax optimization for feature selection and hyperparameter tuning, and a Bidirectional Long Short-Term Memory network for bidirectional sequence learning. The model was evaluated using the OhioT1DM dataset across multiple prediction horizons ranging from 30 to 60 min.

At the 30-min prediction horizon, GlucoDiaNet achieved a Root Mean Squared Error (RMSE) of 5.2435 mg/dL, Mean Absolute Error (MAE) of 4.3622 mg/dL, R ² value of 0.9948, and Mean Squared Error (MSE) of 29.3056. The proposed model consistently outperformed baseline models including LSTM, GRU, and TCN across both short- and long-term forecasting tasks while maintaining robust predictive performance at extended prediction intervals.

GlucoDiaNet effectively enhances blood glucose prediction by integrating efficient preprocessing, deep temporal modeling, and optimization strategies. The proposed framework demonstrates strong potential for future deployment in real-time and wearable diabetes monitoring systems, subject to further hardware-level validation and computational efficiency analysis.