Hypoglycemia event prediction from CGM using ensemble learning

Jesper Fleischer; Troels Krarup Hansen; Simon Lebech Cichosz

doi:10.3389/fcdhc.2022.1066744

Hypoglycemia event prediction from CGM using ensemble learning

Front Clin Diabetes Healthc. 2022 Dec 9:3:1066744. doi: 10.3389/fcdhc.2022.1066744. eCollection 2022.

Authors

Jesper Fleischer^{1

2}, Troels Krarup Hansen¹, Simon Lebech Cichosz³

Affiliations

¹ Steno Diabetes Center Aarhus, Aarhus, Denmark.
² Steno Diabetes Center Zealand, Holbæk, Denmark.
³ Department of Health Science and Technology, Aalborg University, Aalborg, Denmark.

Abstract

This work sought to explore the potential of using standalone continuous glucose monitor (CGM) data for the prediction of hypoglycemia utilizing a large cohort of type 1 diabetes patients during free-living. We trained and tested an algorithm for the prediction of hypoglycemia within 40 minutes on 3.7 million CGM measurements from 225 patients using ensemble learning. The algorithm was also validated using 11.5 million synthetic CGM data. The results yielded a receiver operating characteristic area under the curve (ROC AUC) of 0.988 and a precision-recall area under the curve (PR AUC) of 0.767. In an event-based analysis for predicting hypoglycemic events, the algorithm had a sensitivity of 90%, a lead-time of 17.5 minutes and a false-positive rate of 38%. In conclusion, this work demonstrates the potential of using ensemble learning to predict hypoglycemia, using only CGM data. This could help alarm patients of a future hypoglycemic event so countermeasures can be initiated.

Keywords: Dexcom G4 platinum; blood glucose (BG); continuous glucose monitoring (CGM); diabetes; event prediction; hypoglycaemia; machine learning; type 1 diabetes.