Lightweight Sequential Transformers for Blood Glucose Level Prediction in Type-1 Diabetes

TL;DR

The paper tackles blood glucose level prediction in Type 1 Diabetes under edge-computing constraints. It introduces a Lightweight Sequential Transformer that fuses Transformer attention with sequential processing to capture long- and short-term dependencies while maintaining a small model footprint, suitable for wearables. A balanced MSE loss is proposed to counteract the imbalance between normal and adverse hypo/hyperglycemic events, improving detection of critical events. Evaluations on OhioT1DM and DiaTrend demonstrate competitive or superior predictive accuracy and adverse-event detection with a favorable edge-deployment profile, highlighting practical potential for real-world T1D management at the device level.

Abstract

Type 1 Diabetes (T1D) affects millions worldwide, requiring continuous monitoring to prevent severe hypo- and hyperglycemic events. While continuous glucose monitoring has improved blood glucose management, deploying predictive models on wearable devices remains challenging due to computational and memory constraints. To address this, we propose a novel Lightweight Sequential Transformer model designed for blood glucose prediction in T1D. By integrating the strengths of Transformers' attention mechanisms and the sequential processing of recurrent neural networks, our architecture captures long-term dependencies while maintaining computational efficiency. The model is optimized for deployment on resource-constrained edge devices and incorporates a balanced loss function to handle the inherent data imbalance in hypo- and hyperglycemic events. Experiments on two benchmark datasets, OhioT1DM and DiaTrend, demonstrate that the proposed model outperforms state-of-the-art methods in predicting glucose levels and detecting adverse events. This work fills the gap between high-performance modeling and practical deployment, providing a reliable and efficient T1D management solution.

Figures (3)

• Figure 1: The architecture of the proposed Sequential Transformer $\mathcal{M}$.
• Figure 2: Time Sequence Encoder $\mathcal{E}$.
• Figure 3: Time Sequence Forecaster $\mathcal{F}$.