Time-Aware Cross-Attention for Multi-Modal Sensor-Based Blood Glucose Forecasting

Abstract

Accurate blood glucose forecasting enables proactive management of metabolic health, particularly when leveraging data from wearable sensors that capture data about physiological and behavioral health. However, existing models struggle with integrating multimodal time-series data with inconsistent sampling rates. This paper proposes a novel forecasting framework that incorporates a time-aware cross-attention mechanism with an LSTM architecture to predict blood glucose levels using continuous glucose monitoring (CGM) data alongside physiological and behavioral signals, such as heart rate (HR), electrodermal activity, accelerometry, and dietary intake. The proposed method dynamically encodes temporal features without the need for preprocessing and employs gated multi-head cross-attention layers to fuse sensor modalities effectively. We evaluate our approach on a newly constructed dataset involving 12 participants. Our method outperforms the baseline and state-of-the-art GlySim models across multiple prediction horizons ranging from 5 minutes to 90 minutes, achieving up to 17.8% improvement in Root Mean Squared Error (RMSE) values.

Aashritha Machiraju

Graduate Researcher

I am an MS student at Arizona State University.

Shovito Barua Soumma

Graduate Research Associate
PhD Candidate

Currently I am working on building and optimizing deep learning models for wearable sensors data.