GARNN: An Interpretable Graph Attentive Recurrent Neural Network for Predicting Blood Glucose Levels via Multivariate Time Series

TL;DR

GARNN is an interpretable graph attentive recurrent neural network designed for accurate blood glucose level prediction from multivariate time series data, providing both high accuracy and meaningful interpretability for diabetes management.

Contribution

This paper introduces GARNN, a novel interpretable deep learning model that combines graph attention and recurrent networks for blood glucose prediction, enhancing trust and understanding in clinical applications.

Findings

GARNN outperforms 12 baseline methods in prediction accuracy.

GARNN provides high-quality temporal interpretability.

Effective in diverse clinical scenarios for blood glucose prediction.

Abstract

Accurate prediction of future blood glucose (BG) levels can effectively improve BG management for people living with diabetes, thereby reducing complications and improving quality of life. The state of the art of BG prediction has been achieved by leveraging advanced deep learning methods to model multi-modal data, i.e., sensor data and self-reported event data, organised as multi-variate time series (MTS). However, these methods are mostly regarded as ``black boxes'' and not entirely trusted by clinicians and patients. In this paper, we propose interpretable graph attentive recurrent neural networks (GARNNs) to model MTS, explaining variable contributions via summarizing variable importance and generating feature maps by graph attention mechanisms instead of post-hoc analysis. We evaluate GARNNs on four datasets, representing diverse clinical scenarios. Upon comparison with twelve well-established baseline methods, GARNNs not only achieve the best prediction accuracy but also provide high-quality temporal interpretability, in particular for postprandial glucose levels as a result of corresponding meal intake and insulin injection. These findings underline the potential of GARNN as a robust tool for improving diabetes care, bridging the gap between deep learning technology and real-world healthcare solutions.