发表机构
University of California, Los Angeles; Union County Magnet High School; Huntington Beach High School; Crean Lutheran High School; Portola High School; Tsinghua University（加州大学洛杉矶分校; 联合县磁石高中; 亨廷顿海滩高中; 克林路德高中; 波托拉高中; 清华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究评估时间序列基础模型在CGM预测中的表现，发现零样本效果不佳，轻量微调显著提升性能，且多模态饮食上下文融合可进一步降低预测误差，尤其改善餐后预测。
AI 中文摘要
连续血糖监测（CGM）提供高频的血糖动态测量，并支持糖尿病管理中的短期血糖预测。尽管时间序列基础模型展现出强大的通用预测能力，但其在CGM预测中的有效性以及多模态饮食上下文的附加价值仍不明确。我们使用八个公共CGM数据集进行了全面的实证研究，涵盖1型糖尿病、2型糖尿病和非糖尿病人群。在统一协议下，跨多种上下文长度和预测视野，零样本基础模型并未持续优于如Elastic Net和PatchTST等强任务特定基线。相比之下，轻量级微调显著提升了预测性能。例如，微调后的Chronos-Bolt在T1D队列中将RMSE降低了6.5%-18.4%，在非糖尿病/T2D队列中降低了8.6%-18.2%，且在分布内和分布外测试设置中均有相当改进。我们进一步使用CGMacros评估多模态饮食上下文，该数据集提供时间对齐的CGM信号、食物图像和宏量营养素记录。基于残差的融合框架相对于仅CGM基线，将整体RMSE降低了约3%，餐后RMSE降低了约15%。此外，基于Chronos的CGM表示与观察到的餐后血糖增量相关性更强，优于LSTM和CatBoost的表示，即使这些模型融入了额外的饮食模态，这表明预训练的时间表示能更好地保留餐后诱导的波动模式。这些发现表明，基础模型需要针对CGM的特定适应以实现可靠预测，且饮食上下文提供了超越单独CGM的临床有意义信号，尤其是在餐后时期。
英文摘要
Continuous glucose monitoring (CGM) provides high-frequency measurements of glucose dynamics and enables short-term glucose forecasting for diabetes management. Although time-series foundation models have shown strong general forecasting ability, their effectiveness for CGM prediction and the added value of multimodal dietary context remain unclear. We conduct a comprehensive empirical study using eight public CGM datasets spanning Type 1 diabetes, Type 2 diabetes, and non-diabetes populations. Under a unified protocol across multiple context lengths and prediction horizons, zero-shot foundation models did not consistently outperform strong task-specific baselines such as Elastic Net and PatchTST. In contrast, lightweight fine-tuning substantially improved forecasting performance. For example, fine-tuned Chronos-Bolt reduced RMSE by 6.5%-18.4% in the T1D cohort and by 8.6%-18.2% in the non-diabetes/T2D cohort, with comparable improvements in both in-distribution and out-of-distribution test settings. We further evaluate multimodal dietary context using CGMacros, which provides temporally aligned CGM signals, food images, and macronutrient records. A residual-based fusion framework reduced overall RMSE by approximately 3% and postprandial RMSE by approximately 15% relative to the CGM-only baseline. Moreover, Chronos-based CGM representations were more strongly correlated with observed postprandial glucose increments than representations from LSTM and CatBoost, even after those models incorporated additional dietary modalities, suggesting that pretrained temporal representations better preserve meal-induced excursion patterns. These findings show that foundation models require CGM-specific adaptation for reliable forecasting and that dietary context provides clinically meaningful signals beyond CGM alone, especially during postprandial periods.
