← Back to all news
arXiv Machine Learning

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

GlucoFM is a lightweight foundation model for continuous glucose monitoring that aligns irregular CGM data to a 24‑hour grid and splits glucose dynamics into slow‑varying trend and short‑term deviation streams. Pre‑trained on over 109,000 hours of unlabeled recordings, it outperforms existing CGM‑specific models on seven phenotype‑classification tasks, improving average PR‑AUC by 4.1 points and enabling strong cross‑dataset transfer and few‑shot adaptation. When combined with meal, nutrition, and subject context, its frozen encoder delivers the lowest two‑hour postprandial glycemic response errors for trajectory, incremental AUC, peak rise, and peak timing metrics.

Related stories

arXiv Machine Learning
Sep 11

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

The study evaluates time‑series foundation models for continuous glucose monitoring (CGM) forecasting across eight public datasets covering Type 1, Type 2, and non‑diabetes populations. Zero‑shot foundation models did not consistently beat strong task‑specific baselines, but lightweight fine‑tuning of models like Chronos‑Bolt improved root‑mean‑square error by up to 18% in both in‑distribution and out‑of‑distribution settings. Incorporating multimodal dietary context via CGMacros and a residual‑based fusion framework further reduced overall RMSE by ~3% and postprandial RMSE by ~15%, indicating that dietary signals add clinically meaningful value beyond CGM alone.

By Bowen Zhang, Hsiu-Wen Cheng, Hongyu Yang, Evie L. Shen, Joleen Vansomphone, Yuna Li, Kerry Zhou, Zitian Qu, Suning Zhao, Xiangning Deng, Hua Zhou, Jin J. Zhou
fine-tuningmultimodal
More like this →
arXiv Machine Learning
Oct 12

GlucoPRISM: Protocol-Supervised Pretraining for Cross-Cohort Glucose Transfer

GlucoPRISM introduces a protocol‑supervised pretraining approach that separates glucose monitoring data into distinct Trait, State, and Sensor representation bands. By removing the Sensor band from a frozen encoder, the method improves cross‑cohort transfer performance, raising mean AUROC from 68.75 to 73.57 across twelve directions and outperforming the baseline GlucoFM model. The retained bands maintain device decodability while enhancing predictive accuracy on multiple public tasks and clinical endpoints.

By Adinath Madhavrao Dukre, Abdullah Mohammad, Yifan Lu, Eran Segal, Ahmed Metwally, Imran Razzak
More like this →
arXiv Machine Learning
Jun 8

GlucoFM-Bench: Benchmarking Time-Series Foundation Models for Blood Glucose Forecasting

arXiv:2606. 06881v1 Announce Type: new Abstract: Blood glucose forecasting models are foundational for modern diabetes management systems, as reliable short-term predictions can enable proactive interventions, support automated insulin delivery, and reduce the risk of hypo- and hyperglycemic events.

By Baiying Lu, Zhaohui Liang, Ryan Pontius, Shengpu Tang, Temiloluwa Prioleau
llmsbenchmarks
More like this →
Hugging Face Trending Papers
Sep 8

It's All in the Way You Say It: The Role of Information Representation in LLM-Based Glycemic-Event Prediction

The paper examines how the representation of physiological data affects the performance of large language models (LLMs) in predicting post‑meal blood glucose events for people with type 1 diabetes. Using the OhioT1DM dataset, the authors compare zero‑shot and few‑shot prompt‑based LLMs across 30, 60, and 90‑minute horizons, varying the textual encoding of glucose readings, derived descriptors, and contextual variables such as insulin, meals, carbs, and activity. Results show that while conventional supervised models excel at hyperglycemia prediction, certain prompt‑based LLM configurations outperform them for hypoglycemia, and that the way data is presented to the model is a key determinant of success, with added context not consistently improving outcomes.

llms
More like this →
arXiv Machine Learning
Oct 16

PMB-NN: Physiological-Model-Based Neural Network for Glucose Forecasting in Type 1 Diabetes

The study introduces PMB‑NN, a physiological‑model‑based neural network that forecasts glucose levels in type 1 diabetes using a temporal convolutional network trained on 180 minutes of historical data and constrained by a personalized four‑parameter physiological model. Evaluated on 6–8 weeks of continuous glucose monitoring, pump, and meal data from 25 participants, PMB‑NN achieved median mean absolute errors of 16.24, 25.00, and 30.20 mg/dL for 30‑, 60‑, and 120‑minute horizons when basal insulin records were available, outperforming the physiological model alone across all settings. The model also demonstrated expected directional changes for most correction boluses and carbohydrate rescues, and its three‑term variant improved hyperglycaemia accuracy with basal records without significantly altering overall error.

By Yaowen Zhang, Shuhao Que, Ying Wang
More like this →