A deep learning approach to diabetic blood glucose prediction
This addresses personalized diabetes management by enabling cross-patient glucose prediction, though it appears incremental as it builds on existing deep learning methods.
The paper tackles 30-minute blood glucose prediction from continuous glucose monitoring data using a deep learning approach that works across patients without recalibration, demonstrating that deep networks outperform shallow networks in this task.
We consider the question of 30-minute prediction of blood glucose levels measured by continuous glucose monitoring devices, using clinical data. While most studies of this nature deal with one patient at a time, we take a certain percentage of patients in the data set as training data, and test on the remainder of the patients; i.e., the machine need not re-calibrate on the new patients in the data set. We demonstrate how deep learning can outperform shallow networks in this example. One novelty is to demonstrate how a parsimonious deep representation can be constructed using domain knowledge.