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

• URL: http://arxiv.org/abs/2605.30865v1
• Date: Fri, 29 May 2026 05:46:35 GMT
• Title: GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring
• Abstract summary: GlucoFM is a lightweight foundation model for continuous glucose monitoring (CGM)<n>It aligns irregular recordings to a 24-hour chronological grid, preserves observation masks, and decomposes glucose dynamics into slow physiological state and transient event streams.<n>It achieves the strongest subject-disjoint linear-probing performance among evaluated baselines.
• Score: 12.757891952959987
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 $β$-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.

Related papers

• Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting [14.534275200164712]
  We conduct a study using eight public CGM datasets spanning Type 1 diabetes, Type 2 diabetes, and non-diabetes populations.<n>Foundation models did not consistently outperform strong task-specific baselines such as Elastic Net and PatchTST.<n>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.<n>A residual-based fusion framework reduced overall RMSE by approximately 3% and postprandial RMSE by approximately 15% relative to the CGM-only baseline.
  arXiv  Detail & Related papers  (2026-09-10T17:43:29Z)
• Large-Small Model Collaboration for Zero-Shot Surgical Phase Recognition [45.191945465591374]
  Task-specific lightweight models for surgical phase recognition excel at capturing temporal dynamics but generalize poorly under domain shift.<n>We propose textbfLarge-textbfSmall textbfTemporal adaptation (textbfLaST), a novel large-small collaborative framework that enables zero-shot adaptation to unseen clinical domains.
  arXiv  Detail & Related papers  (2026-08-24T07:06:52Z)
• GlucoFM-Bench: Benchmarking Time-Series Foundation Models for Blood Glucose Forecasting [6.427581905332425]
  We present GlucoFM-Bench, a benchmark evaluating state-of-the-art foundation models for blood glucose forecasting.<n>We assess eight representative architectures, including pre-trained TSFMs, time-series large language models, and task-specific deep learning models.<n>Across datasets, pre-trained TSFMs show strong zero-shot and few-shot transfer, with the best zero-shot model performing within 5% of the best full-shot supervised model.
  arXiv  Detail & Related papers  (2026-06-05T03:49:26Z)
• SSM-CGM: Interpretable State-Space Forecasting Model of Continuous Glucose Monitoring for Personalized Diabetes Management [0.6481500397175589]
  Continuous glucose monitoring (CGM) generates dense data streams critical for diabetes management.<n>We present SSM-CGM, a Mamba-based neural state-space forecasting model that integrates CGM and wearable activity signals.
  arXiv  Detail & Related papers  (2025-10-05T22:37:28Z)
• Composable Score-based Graph Diffusion Model for Multi-Conditional Molecular Generation [85.58520120011269]
  We propose Composable Score-based Graph Diffusion model (CSGD), which extends score matching to discrete graphs via concrete scores.<n>We show that CSGD achieves state-of-the-art performance with a 15.3% average improvement in controllability over prior methods.<n>Our findings highlight the practical advantages of score-based modeling for discrete graph generation and its capacity for flexible, multi-property molecular design.
  arXiv  Detail & Related papers  (2025-09-11T13:37:56Z)
• AttenGluco: Multimodal Transformer-Based Blood Glucose Forecasting on AI-READI Dataset [8.063401183752347]
  Diabetes is a chronic metabolic disorder characterized by persistently high blood glucose levels (BGLs)<n>Recent deep learning models show promise in improving BGL prediction.<n>We propose AttenGluco, a multimodal Transformer-based framework for long-term blood glucose prediction.
  arXiv  Detail & Related papers  (2025-02-14T05:07:38Z)
• Finetuning and Quantization of EEG-Based Foundational BioSignal Models on ECG and PPG Data for Blood Pressure Estimation [46.36100528165335]
  Photoplethysmography and electrocardiography can potentially enable continuous blood pressure (BP) monitoring.<n>Yet accurate and robust machine learning (ML) models remains challenging due to variability in data quality and patient-specific factors.<n>In this work, we investigate whether a model pre-trained on one modality can effectively be exploited to improve the accuracy of a different signal type.<n>Our approach achieves near state-of-the-art accuracy for diastolic BP and surpasses by 1.5x the accuracy of prior works for systolic BP.
  arXiv  Detail & Related papers  (2025-02-10T13:33:12Z)
• A Large Sensor Foundation Model Pretrained on Continuous Glucose Monitor Data for Diabetes Management [3.8195320624847833]
  We introduce CGM-LSM, a Transformer decoder-based Large Sensor Model (LSM) pretrained on 1.6 million CGM records from patients with different diabetes types, ages, and genders.<n>We model patients as sequences of glucose time steps to learn latent knowledge embedded in CGM data and apply it to the prediction of glucose readings for a 2-hour horizon.<n>Compared with prior methods, CGM-LSM significantly improves prediction accuracy and robustness: a 48.51% reduction in root mean square error in one-hour horizon forecasting and consistent zero-shot prediction performance across held-out patient groups.
  arXiv  Detail & Related papers  (2024-12-12T21:35:13Z)
• From Glucose Patterns to Health Outcomes: A Generalizable Foundation Model for Continuous Glucose Monitor Data Analysis [47.23780364438969]
  We present GluFormer, a generative foundation model for CGM data that learns nuanced glycemic patterns and translates them into predictive representations of metabolic health.<n>GluFormer generalizes to 19 external cohorts spanning different ethnicities and ages, 5 countries, 8 CGM devices, and diverse pathophysiological states.<n>In a longitudinal study of 580 adults with CGM data and 12-year follow-up, GluFormer identifies individuals at elevated risk of developing diabetes more effectively than blood HbA1C%.
  arXiv  Detail & Related papers  (2024-08-20T13:19:06Z)
• A Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics [51.147876395589925]
  A non-stationary PGDS is proposed to allow the underlying transition matrices to evolve over time. A fully-conjugate and efficient Gibbs sampler is developed to perform posterior simulation. Experiments show that, in comparison with related models, the proposed non-stationary PGDS achieves improved predictive performance.
  arXiv  Detail & Related papers  (2024-02-26T04:39:01Z)
• Improving Diffusion Models for ECG Imputation with an Augmented Template Prior [43.6099225257178]
  noisy and poor-quality recordings are a major issue for signals collected using mobile health systems. Recent studies have explored the imputation of missing values in ECG with probabilistic time-series models. We present a template-guided denoising diffusion probabilistic model (DDPM), PulseDiff, which is conditioned on an informative prior for a range of health conditions.
  arXiv  Detail & Related papers  (2023-10-24T11:34:15Z)
• Machine Learning based prediction of Glucose Levels in Type 1 Diabetes Patients with the use of Continuous Glucose Monitoring Data [0.0]
  Continuous Glucose Monitoring (CGM) devices offer detailed, non-intrusive and real time insights into a patient's blood glucose concentrations. Leveraging advanced Machine Learning (ML) Models as methods of prediction of future glucose levels, gives rise to substantial quality of life improvements.
  arXiv  Detail & Related papers  (2023-02-24T19:10:40Z)
• Short Term Blood Glucose Prediction based on Continuous Glucose Monitoring Data [53.01543207478818]
  This study explores the use of Continuous Glucose Monitoring (CGM) data as input for digital decision support tools. We investigate how Recurrent Neural Networks (RNNs) can be used for Short Term Blood Glucose (STBG) prediction.
  arXiv  Detail & Related papers  (2020-02-06T16:39:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.