A pretrained transformer model for decoding individual glucose dynamics from continuous glucose monitoring data

作者：Yurun Lu, Dan Liu, Zhongming Liang, Rui Liu, Pei Chen, Yitong Liu, Jiachen Li, Zhanying Feng, Lei M. Li, Bin Sheng, Weiping Jia, Luonan Chen, Huating Li, Yong Wang · 发表于：National Science Review · 年份：2025 · DOI：10.1093/nsr/nwaf039 · 被引用次数：19 · 研究领域：Diabetes Management and Research、Metabolomics and Mass Spectrometry Studies、Artificial Intelligence in Healthcare

Continuous glucose monitoring (CGM) technology has grown rapidly to track real-time blood glucose levels and trends with improved sensor accuracy. The ease of use and wide availability of CGM will facilitate safe and effective decision making for diabetes management. Here, we developed an attention-based deep learning model, CGMformer, pretrained on a well-controlled and diverse corpus of CGM data to represent individual's intrinsic metabolic state and enable clinical applications. During pretraining, CGMformer encodes glucose dynamics including glucose level, fluctuation, hyperglycemia, and hypoglycemia into latent space with self-supervised learning. It shows generalizability in imputing glucose value across five external datasets with different populations and metabolic states (MAE = 3.7 mg/dL). We then fine-tuned CGMformer towards a diverse panel of downstream tasks in the screening of diabetes and its complications using task-specific data, which demonstrated a consistently boosted predictive accuracy over direct fine-tuning on a single task (AUROC = 0.914 for type 2 diabetes (T2D) screening and 0.741 for complication screening). By learning an intrinsic representation of an individual's glucose dynamics, CGMformer classifies non-diabetic individuals into six clusters with elevated T2D risks, and identifies a specific cluster with lean body-shape but high risk of glucose metabolism disorders, which is overlooked by traditional glucose measurements. Furthermore, CGMformer...