Automatic Blood Glucose Prediction with Confidence Using Recurrent Neural Networks

J. Martinsson, A. Schliep, B. Eliasson, C. Meijner, S. Persson and O. Mogren

In Proceedings of the 3rd International Workshop on Knowledge Discovery in Healthcare Data co-located with the 27th International Joint Conference on Artificial Intelligence and the 23rd European Conference on Artificial Intelligence (IJCAI-ECAI), 64–68, Jul 2018.

Low-cost sensors continuously measuring blood glucose levels in intervals of a few minutes and mobile platforms combined with machinelearning (ML) solutions enable personalized precision health and disease management. ML solutions must be adapted to different sensor technologies, analysis tasks and individuals. This raises the issue of scale for creating such adapted ML solutions. We present an approach for predicting blood glucose levels for diabetics up to one hour into the future. The approach is based on recurrent neural networks trained in an end-to-end fashion, requiring nothing but the glucose level history for the patient. The model outputs the prediction along with an estimate of its certainty, helping users to interpret the predicted levels. The approach needs no feature engineering or data pre-processing, and is computationally inexpensive.

A reprint is available as PDF.

Further publications by Alexander Schliep, John Martinsson.