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

arXiv: https://arxiv.org/abs/2412.09727 · HTML: https://mlsanity.com/paper/2412.09727/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 42 references that are in the map.
- First posted on arXiv 12 Dec 2024.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [On Decoding Strategies for Neural Text Generators](https://mlsanity.com/paper/2203.15721/) (2022)
- [Convolutional Recurrent Neural Networks for Glucose Prediction](https://mlsanity.com/paper/1807.03043/) (2018)

## Built on by (most cited first, 6 of 6)

- [GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring](https://mlsanity.com/paper/2605.30865/) (2026)
- [CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining](https://mlsanity.com/paper/2605.00933/) (2026)
- [GlucoFM-Bench: Benchmarking Time-Series Foundation Models for Blood Glucose Forecasting](https://mlsanity.com/paper/2606.06881/) (2026)
- [MetaboNet-Bench: A Multi-modal Benchmark for Glucose Forecasting in Type 1 Diabetes](https://mlsanity.com/paper/2606.18640/) (2026)
- [FairGlucose: A CGM Fairness Benchmark Reveals Subgroup Disparities Hidden in Population-Level Validation](https://mlsanity.com/paper/2608.18296/) (2026)
- [Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting](https://mlsanity.com/paper/2609.11872/) (2026)

## Abstract (arXiv)

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.