GlyRAG: Context-Aware Retrieval-Augmented Framework for Blood Glucose Forecasting

Accurate blood glucose forecasting using continuous glucose monitoring (CGM) data can support early prediction of dysglycemic risk. However, current neural-network-based forecasting models treat CGM data as a purely numerical sequence without integrating con textual information that the CGM signal morphology contains. Recently, large language models (LLMs) have shown promise for time-series forecasting tasks, yet their role as agentic context extractors in diabetes care remains largely unexplored. In this study, we bridge glucose forecasting and LLM-based contextualization, and develop GlyRAG, a context-aware retrieval-augmented forecasting framework that uses an LLM as a contextualization agent to summarize glucose morphology directly from a timed CGM window. The generated CGM-only narrative is embedded and fused with patch-based glucose representations, and a retrieval module incorporates similar historical training episodes through cross-attention. We evaluate GlyRAG on OhioT1DM and AZT1D datasets for 5-, 30-, and 60-minute forecasting horizons. Against strong CGM-only baselines, GPT-4 GlyRAG significantly improves long-horizon RMSE (Root Mean Square Error) over PatchTST on both datasets. For example, RMSE decreases from 13.8 to 10.6 at 30 minutes and from 23.1 to 20.2 at 60 minutes on OhioT1DM. LLaMA 3.1 shows smaller but significant long-horizon gains, suggesting that the contextualization pipeline is not limited to GPT-4. Clinical error-grid analyses further show that approximately 85% of predictions fall in clinically acceptable Clarke Error Grid Zones A-B. These results suggest that CGM-derived linguistic context and case-based retrieval can improve long-horizon glucose forecasting without requiring additional sensing modalities.