Explainable Machine-Learning Models to Predict Weekly Risk of Hyperglycemia, Hypoglycemia, and Glycemic Variability in Patients With Type 1 Diabetes Based on Continuous Glucose Monitoring

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: ROC-AUC 0.9 (hyperglycemia), 0.89 (hypoglycemia), 0.8 (glycemic variability)

• Primary Outcome: Weekly prediction accuracy for glycemic events using ROC-AUC

• Nnt Or Sensitivity: Sensitivity and specificity not reported; only ROC-AUC values provided

• Confidence Interval: 95% CI: 0.89-0.91, 0.88-0.9, 0.79-0.81 respectively

Clinical Application

Requires CGM technology, data processing infrastructure, and integration with clinical workflows; feasible in well-resourced diabetes centres Relevant for PBS-subsidised CGM users (FreeStyle Libre, Dexcom); aligns with RACGP diabetes management guidelines emphasising technology integration; requires TGA-approved CGM devices Adults with type 1 diabetes using continuous glucose monitoring systems in routine clinical care

Abstract

BACKGROUND AND OBJECTIVE: The aim of this study was to develop and validate explainable prediction models based on continuous glucose monitoring (CGM) and baseline data to identify a week-to-week risk of CGM key metrics (hyperglycemia, hypoglycemia, glycemic variability). By having a weekly prediction of CGM key metrics, it is possible for the patient or health care personnel to take immediate preemptive action. METHODS: We analyzed, trained, and internally tested three prediction models (Logistic regression, XGBoost, and TabNet) using CGM data from 187 type 1 diabetes patients with long-term CGM monitoring. A binary classification approach combined with feature engineering deployed on the CGM signals was used to predict hyperglycemia, hypoglycemia, and glycemic variability based on consensus targets (time above range ≥5%, time below range ≥4%, coefficient of variation ≥36%). The models were validated in two independent cohorts with a total of 223 additional patients of varying ages. RESULTS: A total of 46 593 weeks of CGM data were included in the analysis. For the best model (XGBoost), the area under the receiver operating characteristic curve (ROC-AUC) was 0.9 [95% confidence interval (CI) = 0.89-0.91], 0.89 [95% CI = 0.88-0.9], and 0.8 [95% CI = 0.79-0.81] for predicting hyperglycemia, hypoglycemia, and glycemic variability in the interval validation, respectively. The validation test showed good generalizability of the models with ROC-AUC of 0.88 to 0.95, 0.84 to 0.89, and 0.80 to 0.82 for predicting the glycemic outcomes. CONCLUSION: Prediction models based on real-world CGM data can be used to predict the risk of unstable glycemic control in the forthcoming week. The models showed good performance in both internal and external validation cohorts.

References

1. 1.Cichosz, S. L., Olesen, S. S., & Jensen, M. H. (2024). Explainable machine-learning models to predict weekly risk of hyperglycemia, hypoglycemia, and glycemic variability in patients with type 1 diabetes based on continuous glucose monitoring. Journal of Diabetes Science and Technology. https://doi.org/10.1089/DIA.2023.0532