Integrating Biological-Informed Recurrent Neural Networks for Glucose-Insulin Dynamics Modeling
By: Stefano De Carli , Nicola Licini , Davide Previtali and more
Potential Business Impact:
Helps artificial pancreases better control blood sugar.
Type 1 Diabetes (T1D) management is a complex task due to many variability factors. Artificial Pancreas (AP) systems have alleviated patient burden by automating insulin delivery through advanced control algorithms. However, the effectiveness of these systems depends on accurate modeling of glucose-insulin dynamics, which traditional mathematical models often fail to capture due to their inability to adapt to patient-specific variations. This study introduces a Biological-Informed Recurrent Neural Network (BIRNN) framework to address these limitations. The BIRNN leverages a Gated Recurrent Units (GRU) architecture augmented with physics-informed loss functions that embed physiological constraints, ensuring a balance between predictive accuracy and consistency with biological principles. The framework is validated using the commercial UVA/Padova simulator, outperforming traditional linear models in glucose prediction accuracy and reconstruction of unmeasured states, even under circadian variations in insulin sensitivity. The results demonstrate the potential of BIRNN for personalized glucose regulation and future adaptive control strategies in AP systems.
Similar Papers
Physics-Informed Neural Networks vs. Physics Models for Non-Invasive Glucose Monitoring: A Comparative Study Under Realistic Synthetic Conditions
Image and Video Processing
Makes a needle-free glucose monitor work outside.
IRNN: Innovation-driven Recurrent Neural Network for Time-Series Data Modeling and Prediction
Machine Learning (CS)
Improves predictions by learning from past mistakes.
A Physiologically-Constrained Neural Network Digital Twin Framework for Replicating Glucose Dynamics in Type 1 Diabetes
Quantitative Methods
Helps predict blood sugar for diabetes treatment.