DiabLLM: An LLM-Based Framework for Blood Glucose Prediction in Type 1 Diabetes
- 9 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-14
Abstract
Accurate Blood Glucose (BG) prediction is essential for enabling glycemic control in individuals with Type 1 Diabetes Mellitus (T1DM), particularly within Smart and Connected Health (SCH) systems that integrate Continuous Glucose Monitoring (CGM) and automated insulin delivery. The adaptability of Large Language Models (LLMs) provides a promising foundation for unified, fine-tunable forecasting models. We introduce DiabLLM, a framework based on two recent LLM-based architectures: Time-LLM, which incorporates a lightweight projection layer and alignment techniques to transform time-series data into embeddings interpretable by pre-trained LLMs, and Chronos, which employs time-series-aware tokenization and quantization to convert continuous inputs into discrete sequences for forecasting. Both models process 30-minute sequences of six historical BG values and predict 30- and 45-minute horizons. Experimental results on the OhioT1DM and D1NAMO datasets demonstrate that DiabLLM outper forms state-of-the-art baselines, including a Deep Reinforcement Learning model and an ensemble of LSTM, GRU, and WaveNet, achieving up to 27% improvement in RMSE and 37% in MAE. To enhance robustness to noisy and missing input data, a denoising autoencoder was employed for input reconstruction, yielding improved predictive performance. In addition, knowledge distillation was shown to significantly compress the model, making it a practical candidate for efficient deployment on resource-constrained edge devices without compromising accuracy.Keywords
This publication has 41 references indexed in Scilit:
- Personalized glucose forecasting for people with type 1 diabetes using large language modelsComputer Methods and Programs in Biomedicine, 2025
- Advancing blood glucose prediction with neural architecture search and deep reinforcement learning for type 1 diabeticsBiocybernetics and Biomedical Engineering, 2024
- IDF diabetes Atlas: Global estimates of undiagnosed diabetes in adults for 2021Diabetes Research and Clinical Practice, 2022
- Reinforcement Learning for Diabetes Blood Glucose Control with Meal Information2021
- A personalized blood glucose level prediction model with a fine-tuning strategy: A proof-of-concept studyComputer Methods and Programs in Biomedicine, 2021
- Blood glucose prediction with deep neural networks using weighted decision level fusionBiocybernetics and Biomedical Engineering, 2021
- Artificial Intelligence: The Future for Diabetes CareThe American Journal of Medicine, 2020
- Dilated Recurrent Neural Networks for Glucose Forecasting in Type 1 DiabetesJournal of Healthcare Informatics Research, 2020
- Toward Automated Insulin DeliveryNew England Journal of Medicine, 2019
- The open D1NAMO dataset: A multi-modal dataset for research on non-invasive type 1 diabetes managementInformatics in Medicine Unlocked, 2018