Explore the vast range of titles available.

Conventional clinical markers guide cardiovascular risk stratification; however, continuous glucose monitoring (CGM) data remain absent from prediction models. A synthesis of the current literature is needed to clarify the prognostic relevance of CGM data for cardiovascular outcomes in people with diabetes. This scoping review aimed to identify published studies examining (1) the associations between glycemic control and cardiovascular outcomes and (2) the predictive value of CGM-derived metrics in cardiovascular risk assessment. MEDLINE and Embase were searched from inception to March 11, 2025, for peer-reviewed, original research that included CGM-derived metrics and cardiovascular disease (CVD) outcomes. Two reviewers screened the records independently. A total of 53 studies were identified. These studies focused on type 1 diabetes, type 2 diabetes, both diabetes types, or prediabetes. Clinical outcomes were examined in 16 studies, while subclinical outcomes were assessed in 40 studies. Of the 53 studies, 47 were cross-sectional studies and 6 were longitudinal studies. All studies were association studies, and 3 included secondary analyses of predictive performance. However, none applied machine learning-based methods. A wide range of CGM-derived metrics and CVD outcomes, both clinical and subclinical, were studied in the literature. Overall, the findings were inconsistent across studies, and this was likely due to methodological weaknesses such as underpowered analyses. Time-in-range was both the most studied metric and associated with cardiovascular risk in the largest single study. Only the mean amplitude of glycemic excursions was consistently associated with CVD in most studies investigating this metric, when using statistical significance as a pragmatic indicator of consistency across heterogeneous studies. The prognostic value of CGM-derived metrics for CVD outcomes is currently underexplored. Longitudinal prediction studies on clinical CVD outcomes, leveraging the potential of routinely collected CGM data, are needed.

Non-Hispanic white (White) populations are overrepresented in medical studies. Potential healthcare disparities can happen when machine learning models, used in diabetes technologies, are trained on data from primarily White patients. We aimed to evaluate algorithmic fairness in glucose predictions. This study utilized continuous glucose monitoring (CGM) data from 101 White and 104 Black participants with type 1 diabetes collected by the JAEB Center for Health Research, US. Long short-term memory (LSTM) deep learning models were trained on 11 datasets of different proportions of White and Black participants and tailored to each individual using transfer learning to predict glucose 60 minutes ahead based on 60-minute windows. Root mean squared errors (RMSE) were calculated for each participant. Linear mixed-effect models were used to investigate the association between racial composition and RMSE while accounting for age, sex, and training data size. A median of 9 weeks (IQR: 7, 10) of CGM data was available per participant. The divergence in performance (RMSE slope by proportion) was not statistically significant for either group. However, the slope difference (from 0% White and 100% Black to 100% White and 0% Black) between groups was statistically significant (p = 0.02), meaning the RMSE increased 0.04 [0.01, 0.08] mmol/L more for Black participants compared to White participants when the proportion of White participants increased from 0 to 100% in the training data. This difference was attenuated in the transfer learned models (RMSE: 0.02 [-0.01, 0.05] mmol/L, p = 0.20). The racial composition of training data created a small statistically significant difference in the performance of the models, which was not present after using transfer learning. This demonstrates the importance of diversity in datasets and the potential value of transfer learning for developing more fair prediction models.