This is the authors' abstract. We don't add key points for this paper.
OBJECTIVE: Data from continuous glucose monitors (CGM) enable the extraction of features descriptive of glycemic dynamics that may provide insight into underlying health status. In this work, we analyse CGM data from a large population of individuals with type 2 diabetes (T2D) and study the association of features with clinical covariates. METHODS: We retrospectively analysed CGM and electronic health record data from a large population of individuals with T2D. We extracted 25 daily CGM features for each individual over a 30-day period and performed statistical association tests on the features and clinical findings from medical claims data and laboratory records. RESULTS: Our final analysis was performed on 6533 individuals. When clustering the CGM features across the population of individuals with T2D, four distinct clusters of features emerged. Further, the CGM features had heterogeneous discriminatory power with clinical covariates, including laboratory values and the presence of claims for diabetic complications. Features related to glycemic variability, such as coefficient of variation, showed markedly lower p-values in many association tests for the presence of diabetic complications than mean glucose. CONCLUSIONS: In examining the characteristics of different features extracted from CGM data in a large population of individuals with T2D, we found that the features were heterogeneously associated with different clinical comorbidities related to diabetes. This work motivates further research to investigate the relationship between CGM features and health outcomes in T2D to enable precision medicine.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Healey et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: