Automatic blood glucose prediction with confidence using recurrent neural networks
Paper i proceeding, 2018

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 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.


John Martinsson

Chalmers, Data- och informationsteknik, Datavetenskap

Alexander Schliep

Göteborgs universitet

Björn Eliasson

Sahlgrenska universitetssjukhuset

Christian Meijner

Student vid Chalmers

Simon Persson

Student vid Chalmers

Olof Mogren

RISE Research Institutes of Sweden

CEUR Workshop Proceedings

16130073 (ISSN)

Vol. 2148 64-68

3rd International Workshop on Knowledge Discovery in Healthcare Data, KDH@IJCAI-ECAI 2018
Stockholm, Sweden,


Annan data- och informationsvetenskap

Datavetenskap (datalogi)


Mer information

Senast uppdaterat