cs.LGNov 13, 2026

Identification and external validation of the sets of 4-, 6-, 8-, 12-, and 24-hour CGM motifs

Authors: Benjamin Lobo

Organizations: School of Data Science, University of Virginia, Charlottesville, VA 22904 · Center for Diabetes Technology, School of Medicine, University of Virginia, Charlottesville, VA 22903

Abstract

There is growing interest in using CGM for purposes other than those initially intended. Recent work of Lobo et al. identified ΩΩ: a set of motifs such that almost any daily CGM profile (the 24-hour CGM time series starting at midnight) can be classified - matched to a motif in ΩΩ. This work generalizes the prior work by identifying sets of motifs for 4-, 6-, 8-, 12-, and 24-hr CGM profiles where an xx-hr CGM profile does not have to be 24 hours in length, and does not have to start at midnight. The prior work methods are modified to identify the five new sets of motifs using data from the same 6 studies in the original work. The newly identified sets were subjected to rigorous external validation using a data set comprised of data from 21 studies (3,455 subjects, 289,592 days of CGM data). The external validation data set has both temporal and geographic transportability and addresses limitations of the data set used to define the five new sets of motifs. The results of the external validation indicate that the prior work generalizes well: the performance of each xx-hr set of motifs on the external validation set is almost identical to that obtained for ΩΩ. The generalization of the original work broadens the potential use cases of the framework to include short term predictions (e.g., impending hypoglycemia) and diagnostics which rely on detecting changes in CGM time series which are less than 24 hours in length.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

May 29, 2026

GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring

Continuous glucose monitoring (CGM) provides a dense view of daily metabolic physiology, yet existing generic time-series and CGM-specific foundation models often encode glucose traces as entangled single-stream sequences, leaving the distinct temporal structure of glycemic dynamics only implicitly modeled. We present GlucoFM, a lightweight CGM foundation model that aligns irregular recordings to a 24-hour chronological grid, preserves observation masks, and decomposes glucose dynamics into slow physiological state and transient event streams, capturing low-frequency glycemic baselines and short-term deviations that may reflect acute physiological responses or sensor artifacts. GlucoFM is pretrained on 109,066 hours of unlabeled CGM recordings from 477 subjects with two complementary objectives: masked contextual latent prediction over fused daily representations and temporal dynamics prediction over state and event streams. Across four diverse cohorts and seven clinical prediction tasks, GlucoFM achieves the strongest subject-disjoint linear-probing performance among evaluated baselines, improving average PR-AUC by 4.1 points over the best CGM-specific foundation model. Its gains are most pronounced on core metabolic outcomes, leading PR-AUC on all diabetes-risk and ββ-cell dysfunction tasks and on 3 of 4 insulin-resistance tasks. GlucoFM also achieves the best overall cross-dataset transfer performance and strong few-shot adaptation among evaluated methods, and consistent gains when aggregating multiple days for subject-level prediction, highlighting physiology-aware decomposition as an effective inductive bias for transferable CGM representation learning.
Sep 10, 2026

Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting

Continuous glucose monitoring (CGM) provides high-frequency measurements of glucose dynamics and enables short-term glucose forecasting for diabetes management. Although time-series foundation models have shown strong general forecasting ability, their effectiveness for CGM prediction and the added value of multimodal dietary context remain unclear. We conduct a comprehensive empirical study using eight public CGM datasets spanning Type 1 diabetes, Type 2 diabetes, and non-diabetes populations. Under a unified protocol across multiple context lengths and prediction horizons, zero-shot foundation models did not consistently outperform strong task-specific baselines such as Elastic Net and PatchTST. In contrast, lightweight fine-tuning substantially improved forecasting performance. For example, fine-tuned Chronos-Bolt reduced RMSE by 6.5%-18.4% in the T1D cohort and by 8.6%-18.2% in the non-diabetes/T2D cohort, with comparable improvements in both in-distribution and out-of-distribution test settings. We further evaluate multimodal dietary context using CGMacros, which provides temporally aligned CGM signals, food images, and macronutrient records. A residual-based fusion framework reduced overall RMSE by approximately 3% and postprandial RMSE by approximately 15% relative to the CGM-only baseline. Moreover, Chronos-based CGM representations were more strongly correlated with observed postprandial glucose increments than representations from LSTM and CatBoost, even after those models incorporated additional dietary modalities, suggesting that pretrained temporal representations better preserve meal-induced excursion patterns. These findings show that foundation models require CGM-specific adaptation for reliable forecasting and that dietary context provides clinically meaningful signals beyond CGM alone, especially during postprandial periods.
May 1, 2026

CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining

Continuous Glucose Monitoring (CGM) can detect early metabolic subphenotypes (insulin resistance, IR; ββ-cell dysfunction), but population-scale deployment faces two coupled problems. First, the same physiological state appears through multiple views (CGM time series, venous OGTT, Glucodensity summaries), so single-view representations fail to transfer when deployment shifts the modality or setting. Second, baselines perform inconsistently across these shifts. Both problems point to one remedy: representations that abstract away from any single view to capture higher-level temporal and distributional structure. We propose CGM-JEPA, a self-supervised pretraining framework which predicts masked latent representations rather than raw values, yielding abstraction that transfers across modalities. X-CGM-JEPA adds a masked Glucodensity cross-view objective for complementary distributional information. We pretrain on ∼\sim389k unlabeled CGM readings from 228 subjects and evaluate on two clinical cohorts (N=27N=27 and N=17N=17 public-release subsets) across three regimes (cohort generalization, venous-to-CGM transfer, home CGM) under 20-iteration ×\times 2-fold cross-validation. X-CGM-JEPA ranks first or second on AUROC for both endpoints across all three regimes while no baseline does, exceeding the strongest baseline by up to +6.5+6.5 pp in cohort generalization and +3.6+3.6 pp in venous-to-CGM transfer (paired Wilcoxon, p<0.001p<0.001). Under modality shift, it matches mean AUROC while redistributing toward weaker subgroups (ethnicity AUROC gap shrinks 25-54%); on sparse in-domain venous data, the distributional view lifts label-aware clustering (ARI +39%+39\%, NMI +40%+40\%). Code and weights: https://github.com/cruiseresearchgroup/CGM-JEPA