Xiong Xin, Yang XinLiang, Cai Yunying, Xue Yuxin, He JianFeng, Su Heng
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China.
Department of Endocrinology, The First People's Hospital of Yunnan Province, The Affiliated Hospital of Kunming University of Science and Technology, Kunming, China.
Digit Health. 2025 Apr 3;11:20552076251328980. doi: 10.1177/20552076251328980. eCollection 2025 Jan-Dec.
Diabetes mellitus is a chronic condition that requires constant blood glucose monitoring to prevent serious health risks. Accurate blood glucose prediction is essential for managing glucose fluctuations and reducing the risk of hypo- and hyperglycemic events. However, existing models often face limitations in prediction horizon and accuracy. This study aims to develop a hybrid deep learning model combining Transformer and Long Short-Term Memory (LSTM) networks to improve prediction accuracy and extend the prediction horizon, using personalized patient information and continuous glucose monitoring data to support better real-time diabetes management.
In this study, we propose a hybrid deep learning model combining Transformer and LSTM networks to predict blood glucose levels for up to 120 min. The Transformer Encoder captures long-range dependencies, while the LSTM models short-term patterns. To improve feature extraction, we integrate Bidirectional LSTM and Transformer Encoder layers at multiple stages. We also use positional encoding, dropout layers, and a sliding window technique to reduce noise and manage temporal dependencies. Richer features, including meal composition and insulin dosage, are incorporated to enhance prediction accuracy. The model's performance is validated using real-world clinical data and error grid analysis.
On clinical data, the model achieved root mean square error/mean absolute error of 10.157/6.377 (30-min), 10.645/6.417 (60-min), 13.537/7.283 (90-min), and 13.986/6.986 (120-min). On simulated data, the results were 1.793/1.376 (15-min), 2.049/1.311 (30-min), and 3.477/1.668 (60-min). Clark Grid Analysis showed that over 96% of predictions fell within the clinical safety zone up to 120 min, confirming its clinical feasibility.
This study demonstrates that the combined Transformer and LSTM model can effectively predict blood glucose concentration in type 1 diabetes patients with high accuracy and clinical applicability. The model provides a promising solution for personalized blood glucose management, contributing to the advancement of artificial intelligence technology in diabetes care.
糖尿病是一种慢性病，需要持续监测血糖以预防严重的健康风险。准确的血糖预测对于控制血糖波动和降低低血糖及高血糖事件的风险至关重要。然而，现有模型在预测范围和准确性方面往往存在局限性。本研究旨在开发一种结合Transformer和长短期记忆（LSTM）网络的混合深度学习模型，以提高预测准确性并延长预测范围，利用个性化患者信息和连续血糖监测数据来支持更好的糖尿病实时管理。
在本研究中，我们提出一种结合Transformer和LSTM网络的混合深度学习模型，用于预测长达120分钟的血糖水平。Transformer编码器捕捉长程依赖关系，而LSTM对短期模式进行建模。为了改进特征提取，我们在多个阶段集成双向LSTM和Transformer编码器层。我们还使用位置编码、随机失活层和滑动窗口技术来减少噪声并管理时间依赖关系。纳入更丰富的特征，包括膳食成分和胰岛素剂量，以提高预测准确性。使用真实世界临床数据和误差网格分析验证模型的性能。
在临床数据上，该模型在30分钟时的均方根误差/平均绝对误差为10.157/6.377，60分钟时为10.645/6.417，90分钟时为13.537/7.283，120分钟时为13.986/6.986。在模拟数据上，15分钟时的结果为1.793/1.376，30分钟时为2.049/1.311，60分钟时为3.477/1.668。克拉克网格分析表明，在长达120分钟的时间内，超过96%的预测落在临床安全区内，证实了其临床可行性。
本研究表明，结合Transformer和LSTM的模型能够有效且高精度地预测1型糖尿病患者的血糖浓度，并具有临床适用性。该模型为个性化血糖管理提供了一个有前景的解决方案，有助于推动人工智能技术在糖尿病护理中的发展。
