Deep Personalized Glucose Level Forecasting Using Attention-based Recurrent Neural Networks
This addresses the critical problem of predicting abnormal glucose levels to warn diabetes patients, potentially preventing serious health complications, but it appears incremental as it builds on existing deep learning methods with personalization and attention enhancements.
The paper tackles blood glucose forecasting for diabetes patients by proposing a deep personalized model that learns both patient-specific and global models, using attention mechanisms and time features to capture long-term dependencies, and achieves empirical efficacy on a real dataset.
In this paper, we study the problem of blood glucose forecasting and provide a deep personalized solution. Predicting blood glucose level in people with diabetes has significant value because health complications of abnormal glucose level are serious, sometimes even leading to death. Therefore, having a model that can accurately and quickly warn patients of potential problems is essential. To develop a better deep model for blood glucose forecasting, we analyze the data and detect important patterns. These observations helped us to propose a method that has several key advantages over existing methods: 1- it learns a personalized model for each patient as well as a global model; 2- it uses an attention mechanism and extracted time features to better learn long-term dependencies in the data; 3- it introduces a new, robust training procedure for time series data. We empirically show the efficacy of our model on a real dataset.