Blood Glucose Level Prediction: A Graph-based Explainable Method with Federated Learning

TL;DR

This paper presents a novel graph-based explainable model for blood glucose prediction that uses federated learning to protect privacy and dynamically models attribute relationships, improving interpretability and accuracy.

Contribution

We introduce a graph attentive memory (GAM) model combining GAT and GRU, enabling explainable attribute correlation modeling in blood glucose prediction with federated learning for privacy.

Findings

Model achieves stable and accurate blood glucose predictions.

Attention weights provide dynamic, interpretable attribute importance.

Federated learning ensures privacy in multi-participant data analysis.

Abstract

In the UK, approximately 400,000 people with type 1 diabetes (T1D) rely on insulin delivery due to insufficient pancreatic insulin production. Managing blood glucose (BG) levels is crucial, with continuous glucose monitoring (CGM) playing a key role. CGM, tracking BG every 5 minutes, enables effective blood glucose level prediction (BGLP) by considering factors like carbohydrate intake and insulin delivery. Recent research has focused on developing sequential models for BGLP using historical BG data, incorporating additional attributes such as carbohydrate intake, insulin delivery, and time. These methods have shown notable success in BGLP, with some providing temporal explanations. However, they often lack clear correlations between attributes and their impact on BGLP. Additionally, some methods raise privacy concerns by aggregating participant data to learn population patterns. Addressing these limitations, we introduced a graph attentive memory (GAM) model, combining a graph attention network (GAT) with a gated recurrent unit (GRU). GAT applies graph attention to model attribute correlations, offering transparent, dynamic attribute relationships. Attention weights dynamically gauge attribute significance over time. To ensure privacy, we employed federated learning (FL), facilitating secure population pattern analysis. Our method was validated using the OhioT1DM'18 and OhioT1DM'20 datasets from 12 participants, focusing on 6 key attributes. We demonstrated our model's stability and effectiveness through hyperparameter impact analysis.