To the top

Page Manager: Webmaster
Last update: 9/11/2012 3:13 PM

Tell a friend about this page
Print version

Automatic Blood Glucose P… - University of Gothenburg, Sweden Till startsida
To content Read more about how we use cookies on

Automatic Blood Glucose Prediction with Confidence Using Recurrent Neural Networks

Conference paper
Authors John Martinsson
Alexander Schliep
Björn Eliasson
Christian Meijner
Simon Persson
Olof Mogren
Published 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} 2018
Publisher CEUR
Publication year 2018
Published at Department of Computer Science and Engineering, Computing Science (GU)
Language en
Subject categories Bioinformatics (Computational Biology)


Low-cost sensors continuously measuring blood glucose levels in intervals of a few minutes and mobile platforms combined with machine- learning (ML) solutions enable personalized pre- cision health and disease management. ML solu- tions must be adapted to different sensor technolo- gies, analysis tasks and individuals. This raises the issue of scale for creating such adapted ML solu- tions. 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, requir- ing nothing but the glucose level history for the pa- tient. The model outputs the prediction along with an estimate of its certainty, helping users to inter- pret the predicted levels. The approach needs no feature engineering or data pre-processing, and is computationally inexpensive.

Page Manager: Webmaster|Last update: 9/11/2012

The University of Gothenburg uses cookies to provide you with the best possible user experience. By continuing on this website, you approve of our use of cookies.  What are cookies?