Prediction of nocturnal hypoglycemia from continuous glucose monitoring data in people with type 1 diabetes: a proof-of-concept study

Research output: Contribution to journalJournal articleResearchpeer-review

15 Citations (Scopus)

Abstract

BACKGROUND: Intensive insulin therapy has documented benefits but may also come at the expense of a higher risk of hypoglycemia. Hypoglycemia is associated with higher all-cause mortality and nocturnal hypoglycemia has been associated with the sudden dead-in-bed syndrome. This proof-of-concept study sought to investigate if nocturnal hypoglycemia can be predicted.

METHOD: Continuous glucose monitoring, meal, insulin, and demographics data from 463 people with type 1 diabetes were obtained from a clinical trial. A total of 4721 nights without or with hypoglycemia (429) were available including data from three consecutive days before the night. Thirty-two features were calculated based on these data. Data were split into 20% participants for evaluation and 80% for training. The optimal feature subset was found from forward selection of the 80% participants with linear discriminant analysis as basis for the classifier.

RESULTS: The forward selection resulted in a feature subset of four features. The evaluation resulted in an area under the receiver operating characteristics curve (ROC-AUC) of 0.79 leading to a sensitivity and a specificity of, e.g., 75% and 70%.

CONCLUSIONS: It was possible to predict nocturnal hypoglycemic episodes with a ROC-AUC of 0.79. A warning at bedtime about nocturnal hypoglycemia could be of great help for people with diabetes to enable preventive actions. Further development of the proposed algorithm is needed for implementation in everyday practice.

Original languageEnglish
JournalJournal of Diabetes Science and Technology
Volume14
Issue number2
Pages (from-to)250-256
Number of pages7
ISSN1932-2968
DOIs
Publication statusPublished - Mar 2020

Keywords

  • algorithm
  • continuous glucose monitoring
  • diabetes
  • flash glucose monitoring
  • hypoglycemia
  • prediction

Fingerprint

Dive into the research topics of 'Prediction of nocturnal hypoglycemia from continuous glucose monitoring data in people with type 1 diabetes: a proof-of-concept study'. Together they form a unique fingerprint.

Cite this