HAD-Net: Hybrid Attention-based Diffusion Network for Glucose Level Forecast

TL;DR

HAD-Net is a hybrid deep learning model that combines physiological knowledge and attention mechanisms to improve glucose level forecasting and interpretability in diabetes management.

Contribution

The paper introduces HAD-Net, a novel biologically inspired deep neural network that integrates physiological models with attention mechanisms for better glucose prediction and insight.

Findings

Achieves competitive glucose forecasting accuracy.

Provides plausible diffusion measurements of insulin and carbohydrates.

Integrates physiological models with deep learning for interpretability.

Abstract

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.