让血糖数据会说话：本地化智能问答系统保护隐私
If Only My CGM Could Speak: A Privacy-Preserving Agent for Question Answering over Continuous Glucose Data
- 用大模型做推理选分析函数，数据全程不离设备
- 合成问题准确率94%，真实问题准确率88%
- 适合关注健康隐私与低资源部署的开发者
连续血糖监测仪（CGM）在糖尿病管理中收集丰富个人健康数据，可提升日常自我管理。但现有患者平台仅提供静态摘要，无法支持自由提问。大语言模型（LLM）虽可实现对连续血糖数据的自由问答，但部署于敏感健康记录时存在隐私和准确性问题。本文提出CGM-Agent，一种面向个人血糖数据的隐私保护问答框架。设计中，LLM仅作为推理引擎选择分析函数，所有计算均在本地完成，用户健康数据永不离开设备。为评估，我们构建包含4,180个问题的基准测试集，结合参数化模板与真实用户查询，真值通过确定性程序执行生成。评估6个领先LLM发现，顶级模型在合成问题上达到94%值准确率，在模糊真实问题上达88%。错误主要源于意图与时间歧义，而非计算失误。此外，轻量级模型在该代理设计中表现良好，表明低成本部署可行。代码与基准已开源，以支持可信健康代理研究。
原文摘要 · Abstract (English)
Continuous glucose monitors (CGMs) used in diabetes care collect rich personal health data that could improve day-to-day self-management. However, current patient platforms only offer static summaries which do not support inquisitive user queries. Large language models (LLMs) could enable free-form inquiries about continuous glucose data, but deploying them over sensitive health records raises privacy and accuracy concerns. In this paper, we present CGM-Agent, a privacy-preserving framework for question answering over personal glucose data. In our design, the LLM serves purely as a reasoning engine that selects analytical functions. All computation occurs locally, and personal health data never leaves the user's device. For evaluation, we construct a benchmark of 4,180 questions combining parameterized question templates with real user queries and ground truth derived from deterministic program execution. Evaluating 6 leading LLMs, we find that top models achieve 94\% value accuracy on synthetic queries and 88\% on ambiguous real-world queries. Errors stem primarily from intent and temporal ambiguity rather than computational failures. Additionally, lightweight models achieve competitive performance in our agent design, suggesting opportunities for low-cost deployment. We release our code and benchmark to support future work on trustworthy health agents.
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。