用160万条血糖数据训练通用模型，实现跨人群精准血糖预测。
A Large Sensor Foundation Model Pretrained on Continuous Glucose Monitor Data for Diabetes Management
- 基于Transformer架构，将患者血糖数据建模为时间序列学习通用特征。
- 一小时预测误差降低48.51%，跨人群零样本预测性能稳定。
- 适合糖尿病管理研究者与医疗AI开发者参考。
连续血糖监测（CGM）结合人工智能为实时血糖预测提供了新机遇。然而，现有模型多为特定任务设计，缺乏跨人群泛化能力。受大语言模型自回归范式的启发，我们提出基于Transformer解码器的大型传感器模型（CGM-LSM），在来自不同糖尿病类型、年龄和性别的患者中预训练了160万条CGM记录。通过将患者建模为血糖时间步序列，学习嵌入在数据中的潜在知识，并用于2小时内的血糖读数预测。相较于先前方法，CGM-LSM显著提升了预测准确性和鲁棒性：在一小时预测中均方根误差降低48.51%，并在保留患者群体上保持一致的零样本预测表现。我们分析了模型在不同患者子群和预测场景下的性能差异，指出了推动CGM基础模型发展的关键机遇与挑战。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。