HAD-Net: Hybrid Attention-based Diffusion Network for Glucose Level Forecast
This work addresses the need for interpretable glucose forecasting in diabetes management, though it appears incremental as it builds on existing hybrid approaches.
The paper tackled the problem of glucose level forecasting for type-2 diabetes patients by introducing HAD-Net, a hybrid model that combines deep learning with physiological models, achieving competitive performance and providing plausible insights into insulin and carbohydrates diffusion.
Data-driven models for glucose level forecast often do not provide meaningful insights despite accurate predictions. Yet, context understanding in medicine is crucial, in particular for diabetes management. In this paper, we introduce HAD-Net: a hybrid model that distills knowledge into a deep neural network from physiological models. It models glucose, insulin and carbohydrates diffusion through a biologically inspired deep learning architecture tailored with a recurrent attention network constrained by ODE expert models. We apply HAD-Net for glucose level forecast of patients with type-2 diabetes. It achieves competitive performances while providing plausible measurements of insulin and carbohydrates diffusion over time.