Deep Multi-Output Forecasting: Learning to Accurately Predict Blood Glucose Trajectories

TL;DR

This paper introduces multi-output deep learning models for multi-step blood glucose forecasting, effectively capturing signal dynamics and improving prediction accuracy over existing methods in a large real-world dataset.

Contribution

It proposes novel multi-output deep architectures that explicitly model the distribution of future signals for improved multi-step forecasting in clinical applications.

Findings

Proposed models outperform shallow and deep baselines in blood glucose prediction.

Combining models yields a significant reduction in absolute percentage error.

Approach effectively captures the underlying dynamics of blood glucose levels.

Abstract

In many forecasting applications, it is valuable to predict not only the value of a signal at a certain time point in the future, but also the values leading up to that point. This is especially true in clinical applications, where the future state of the patient can be less important than the patient's overall trajectory. This requires multi-step forecasting, a forecasting variant where one aims to predict multiple values in the future simultaneously. Standard methods to accomplish this can propagate error from prediction to prediction, reducing quality over the long term. In light of these challenges, we propose multi-output deep architectures for multi-step forecasting in which we explicitly model the distribution of future values of the signal over a prediction horizon. We apply these techniques to the challenging and clinically relevant task of blood glucose forecasting. Through a series of experiments on a real-world dataset consisting of 550K blood glucose measurements, we demonstrate the effectiveness of our proposed approaches in capturing the underlying signal dynamics. Compared to existing shallow and deep methods, we find that our proposed approaches improve performance individually and capture complementary information, leading to a large improvement over the baseline when combined (4.87 vs. 5.31 absolute percentage error (APE)). Overall, the results suggest the efficacy of our proposed approach in predicting blood glucose level and multi-step forecasting more generally.