EUVIMEDEUVIMED entdecken
Validierungsstudie

Development and Validation of a Machine Learning Model to Predict Weekly Risk of Hypoglycemia in Patients with Type 1 Diabetes Based on Continuous Glucose Monitoring

Simon Lebech Cichosz iD, Morten Hasselstrøm Jensen iD, Søren Schou Olesen

Diabetes Technology & Therapeutics · 2024-07 · 26 (7) · 457-466

DOI: 10.1089/dia.2023.0532 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Diabetes Technology & Therapeutics, online erschienen am 12.07.2024. Verfasst von Simon Lebech Cichosz und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Health Science and Technology, Aalborg University, Aalborg, Denmark. Hauptthemen laut MEDLINE: Diabetes Mellitus, Type 1, Hypoglycemia, Machine Learning, Blood Glucose Self-Monitoring. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 44 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aim

The aim of this study was to develop and validate a prediction model based on continuous glucose monitoring (CGM) data to identify a week-to-week risk profile of excessive hypoglycemia.

Methods

We analyzed, trained, and internally tested two prediction models using CGM data from 205 type 1 diabetes patients with long-term CGM monitoring. A binary classification approach (XGBoost) combined with feature engineering deployed on the CGM signals was utilized to predict excessive hypoglycemia risk defined by two targets (time below range [TBR] >4% and the upper TBR 90th percentile limit) of TBR the following week. The models were validated in two independent cohorts with a total of 253 additional patients.

Results

A total of 61,470 weeks of CGM data were included in the analysis. The XGBoost models had an area under the receiver operating characteristic curve (ROC-AUC) of 0.83–0.87 (95% confidence interval; 0.83–0.88) in the test dataset. The external validation showed ROC-AUCs of 0.81–0.90. The most discriminative features included the low blood glucose index, the glycemic risk assessment diabetes equation (GRADE), hypoglycemia, the TBR, waveform length, the coefficient of variation and mean glucose during the previous week. This highlights that the pattern of hypoglycemia combined with glucose variability during the past week contains information on the risk of future hypoglycemia.

Conclusion

Prediction models based on real-world CGM data can be used to predict the risk of hypoglycemia in the forthcoming week. The models showed good performance in both the internal and external validation cohorts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Diabetes Mellitus, Type 1HypoglycemiaMachine LearningBlood Glucose Self-MonitoringBlood GlucoseHumansMaleFemaleAdultMiddle AgedRisk AssessmentHypoglycemic AgentsContinuous Glucose Monitoring

Stichwörter der Autor:innen

Continuous glucose monitoringHypoglycemiaMachine learningPredictionRisk modelType 1 diabetesXGBoost

Substanzen

Blood GlucoseHypoglycemic Agents

Autor:innen und Institutionen

  • Department of Health Science and Technology, Aalborg University, Aalborg, Denmark.
  • Department of Clinical Medicine, Aalborg University Hospital, Aalborg, Denmark.
  • Department of Gastroenterology and Hepatology, Centre for Pancreatic Diseases and Mech-Sense, Aalborg University Hospital, Aalborg, Denmark.

ORCID-Profile: Simon Lebech Cichosz, Morten Hasselstrøm Jensen

Zitieren

APA

Lebech Cichosz, S., Hasselstrøm Jensen, M., & Schou Olesen, S. (2024). Development and Validation of a Machine Learning Model to Predict Weekly Risk of Hypoglycemia in Patients with Type 1 Diabetes Based on Continuous Glucose Monitoring. Diabetes Technology & Therapeutics, 26(7), 457-466. https://doi.org/10.1089/dia.2023.0532

Vancouver

Lebech Cichosz S, Hasselstrøm Jensen M, Schou Olesen S. Development and Validation of a Machine Learning Model to Predict Weekly Risk of Hypoglycemia in Patients with Type 1 Diabetes Based on Continuous Glucose Monitoring. Diabetes Technology & Therapeutics. 2024;26(7):457-466. doi:10.1089/dia.2023.0532

BibTeX
@article{LebechCichosz2024,
  author = {Lebech Cichosz, Simon and Hasselstrøm Jensen, Morten and Schou Olesen, Søren},
  title = {Development and Validation of a Machine Learning Model to Predict Weekly Risk of Hypoglycemia in Patients with Type 1 Diabetes Based on Continuous Glucose Monitoring},
  journal = {Diabetes Technology & Therapeutics},
  year = {2024},
  volume = {26},
  number = {7},
  pages = {457--466},
  doi = {10.1089/dia.2023.0532}
}
Kostenlos starten →