A Large Sensor Foundation Model Pretrained on Continuous Glucose Monitor Data for Diabetes Management

• URL: http://arxiv.org/abs/2412.09727v3
• Date: Fri, 01 Aug 2025 14:45:11 GMT
• Title: A Large Sensor Foundation Model Pretrained on Continuous Glucose Monitor Data for Diabetes Management
• Authors: Junjie Luo, Abhimanyu Kumbara, Mansur Shomali, Rui Han, Anand Iyer, Ritu Agarwal, Gordon Gao,
• Abstract summary: 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.
• Score: 3.8195320624847833
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Continuous glucose monitoring (CGM) combined with AI offers new opportunities for proactive diabetes management through real-time glucose forecasting. However, most existing models are task-specific and lack generalization across patient populations. Inspired by the autoregressive paradigm of large language models, 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. 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. 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. We analyze model performance variations across patient subgroups and prediction scenarios and outline key opportunities and challenges for advancing CGM foundation models.

Related papers

• Type 1 Diabetes Management using GLIMMER: Glucose Level Indicator Model with Modified Error Rate [6.300322064585917]
  We develop GLIMMER, a machine learning approach for forecasting blood glucose levels. GLIMMER categorizes glucose values into normal and abnormal ranges and devises a novel custom loss function to prioritize accuracy in dysglycemic events.
  arXiv  Detail & Related papers  (2025-02-20T01:26:00Z)
• 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)
• Chronic Disease Diagnoses Using Behavioral Data [42.96592744768303]
  We aim to diagnose hyperglycemia (diabetes), hyperlipidemia, and hypertension (collectively known as 3H) using own collected behavioral data.
  arXiv  Detail & Related papers  (2024-10-04T12:52:49Z)
• FedGlu: A personalized federated learning-based glucose forecasting algorithm for improved performance in glycemic excursion regions [4.073768455373616]
  Continuous glucose monitoring (CGM) devices provide real-time glucose monitoring and timely alerts for glycemic excursions. Rare events like hypoglycemia and hyperglycemia remain challenging due to their infrequency. We propose a novel Hypo-Hyper (HH) loss function, which significantly improves performance in the glycemic excursion regions.
  arXiv  Detail & Related papers  (2024-08-25T19:51:27Z)
• From Glucose Patterns to Health Outcomes: A Generalizable Foundation Model for Continuous Glucose Monitor Data Analysis [50.80532910808962]
  We present GluFormer, a generative foundation model on biomedical temporal data based on a transformer architecture. GluFormer generalizes to 15 different external datasets, including 4936 individuals across 5 different geographical regions. It can also predict onset of future health outcomes even 4 years in advance.
  arXiv  Detail & Related papers  (2024-08-20T13:19:06Z)
• Automatic Prediction of Amyotrophic Lateral Sclerosis Progression using Longitudinal Speech Transformer [56.17737749551133]
  We propose ALS longitudinal speech transformer (ALST), a neural network-based automatic predictor of ALS disease progression. By taking advantage of high-quality pretrained speech features and longitudinal information in the recordings, our best model achieves 91.0% AUC. ALST is capable of fine-grained and interpretable predictions of ALS progression, especially for distinguishing between rarer and more severe cases.
  arXiv  Detail & Related papers  (2024-06-26T13:28:24Z)
• Using Pre-training and Interaction Modeling for ancestry-specific disease prediction in UK Biobank [69.90493129893112]
  Recent genome-wide association studies (GWAS) have uncovered the genetic basis of complex traits, but show an under-representation of non-European descent individuals. Here, we assess whether we can improve disease prediction across diverse ancestries using multiomic data.
  arXiv  Detail & Related papers  (2024-04-26T16:39:50Z)
• Toward Short-Term Glucose Prediction Solely Based on CGM Time Series [4.7066018521459725]
  TimeGlu is an end-to-end pipeline for short-term glucose prediction based on CGM time series data. It achieves state-of-the-art performance without the need for additional personal data from patients.
  arXiv  Detail & Related papers  (2024-04-18T06:02:12Z)
• Patterns Detection in Glucose Time Series by Domain Transformations and Deep Learning [0.0]
  We describe our research with the aim of predicting the future behavior of blood glucose levels, so that hypoglycemic events may be anticipated. We have tested our proposed method using real data from 4 different diabetes patients with promising results.
  arXiv  Detail & Related papers  (2023-03-30T09:08:31Z)
• 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)
• Clinical Deterioration Prediction in Brazilian Hospitals Based on Artificial Neural Networks and Tree Decision Models [56.93322937189087]
  An extremely boosted neural network (XBNet) is used to predict clinical deterioration (CD) The XGBoost model obtained the best results in predicting CD among Brazilian hospitals' data.
  arXiv  Detail & Related papers  (2022-12-17T23:29:14Z)
• SANSformers: Self-Supervised Forecasting in Electronic Health Records with Attention-Free Models [48.07469930813923]
  This work aims to forecast the demand for healthcare services, by predicting the number of patient visits to healthcare facilities. We introduce SANSformer, an attention-free sequential model designed with specific inductive biases to cater for the unique characteristics of EHR data. Our results illuminate the promising potential of tailored attention-free models and self-supervised pretraining in refining healthcare utilization predictions across various patient demographics.
  arXiv  Detail & Related papers  (2021-08-31T08:23:56Z)
• Task-wise Split Gradient Boosting Trees for Multi-center Diabetes Prediction [37.846368153741395]
  Task-wise Split Gradient Boosting Trees (TSGB) is proposed for the multi-center diabetes prediction task. TSGB achieves superior performance against several state-of-the-art methods. The proposed TSGB method has been deployed as an online diabetes risk assessment software for early diagnosis.
  arXiv  Detail & Related papers  (2021-08-16T14:22:44Z)
• Stacked LSTM Based Deep Recurrent Neural Network with Kalman Smoothing for Blood Glucose Prediction [4.040272012640556]
  We propose a novel approach to predicting blood glucose level with a stacked Long short-term memory (LSTM) based deep recurrent neural network (RNN) model. For the OhioT1DM dataset, containing eight weeks' data from six different patients, we achieve an average RMSE of 6.45 and 17.24 mg/dl for 30 minutes and 60 minutes of prediction horizon (PH) Our results indicate that the proposed approach is feasible for more reliable BG forecasting that might improve the performance of the artificial pancreas and insulin infusion system for T1D diabetes management.
  arXiv  Detail & Related papers  (2021-01-18T02:31:38Z)
• Adversarial Sample Enhanced Domain Adaptation: A Case Study on Predictive Modeling with Electronic Health Records [57.75125067744978]
  We propose a data augmentation method to facilitate domain adaptation. adversarially generated samples are used during domain adaptation. Results confirm the effectiveness of our method and the generality on different tasks.
  arXiv  Detail & Related papers  (2021-01-13T03:20:20Z)
• 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.