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

Hada Melino Muhammad; Zechen Li; Flora Salim; Ahmed A. Metwally

title	CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining
authors	Hada Melino Muhammad, Zechen Li, Flora Salim, Ahmed A. Metwally
date	2026-05-01
venue	arXiv (preprint, not peer reviewed)
id	arXiv:2605.00933
affiliation	Google
upvotes	1 (Hugging Face Daily Papers, 2026-11-01)
links	abs pdf hf code
abstract	Continuous Glucose Monitoring (CGM) can detect early metabolic subphenotypes (insulin resistance, IR; β-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=27 and N=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 pp in cohort generalization and +3.6 pp in venous-to-CGM transfer (paired Wilcoxon, p<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%, NMI +40%). Code and weights: https://github.com/cruiseresearchgroup/CGM-JEPA

cite

@misc{muhammad2026cgm,
  title={CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining},
  author={Hada Melino Muhammad and Zechen Li and Flora Salim and Ahmed A. Metwally},
  year={2026},
  eprint={2605.00933},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2605.00933}
}