A Deep Learning Approach to Diabetic Blood Glucose Prediction

• Published in: Frontiers in applied mathematics and statistics Vol. 3
• Main Authors: Mhaskar, Hrushikesh N., Pereverzyev, Sergei V., van der Walt, Maria D.
• Format: Journal Article
• Language: English
• Published: Frontiers Media S.A 14-07-2017
• Subjects: blood glucose prediction; continuous glucose monitoring; deep learning; deep neural network; diffusion geometry
• ISSN: 2297-4687; 2297-4687
• DOI: 10.3389/fams.2017.00014

We consider the question of 30-min 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.