Zhu Taiyu, Afentakis Ioannis, Li Kezhi, Armiger Ryan, Hill Neil, Oliver Nick, Georgiou Pantelis
IEEE J Biomed Health Inform. 2024 Jul 16;PP. doi: 10.1109/JBHI.2024.3428921.
Real-time continuous glucose monitoring (CGM), augmented with accurate glucose prediction, offers an effective strategy for maintaining blood glucose levels within a therapeutically appropriate range. This is particularly crucial for individuals with type 1 diabetes (T1D) who require long-term self-management. However, with extensive glycemic variability, developing a prediction algorithm applicable across diverse populations remains a significant challenge. Leveraging meta-learning for domain generalization, we propose GPFormer, a Transformer-based zero-shot learning method designed for multi-horizon glucose prediction. We developed GPFormer on the REPLACE-BG dataset, comprising 226 participants with T1D, and proceeded to evaluate its performance using three external clinical datasets with CGM data. These included the OhioT1DM dataset, a publicly available dataset including 12 T1D participants, as well as two proprietary datasets. The first proprietary dataset included 22 participants, while the second contained 45 participants, encompassing a diverse group with T1D, type 2 diabetes, and those without diabetes, including patients admitted to hospitals. These four datasets include both outpatient and inpatient settings, various intervention strategies, and demographic variability, which effectively reflect real-world scenarios of CGM usage. When compared with a group of machine learning baseline methods, GPFormer consistently demonstrated superior performance and achieved the lowest root mean square error for all the evaluated datasets up to a prediction horizon of two hours. These experimental results highlight the effectiveness and generalizability of the proposed model across a variety of populations, demonstrating its substantial potential to enhance glucose management in a wide range of practical clinical settings.
实时连续血糖监测（CGM）结合精确的血糖预测，为将血糖水平维持在治疗适宜范围内提供了一种有效策略。这对于需要长期自我管理的1型糖尿病（T1D）患者尤为关键。然而，由于血糖变异性大，开发适用于不同人群的预测算法仍然是一项重大挑战。利用元学习进行领域泛化，我们提出了GPFormer，一种基于Transformer的用于多步血糖预测的零样本学习方法。我们在包含226名T1D患者的REPLACE - BG数据集上开发了GPFormer，并使用三个带有CGM数据的外部临床数据集来评估其性能。这些数据集包括OhioT1DM数据集（一个包含12名T1D参与者的公开可用数据集）以及两个专有数据集。第一个专有数据集包含22名参与者，第二个包含45名参与者，涵盖了T1D、2型糖尿病患者以及非糖尿病患者的多样化群体，包括住院患者。这四个数据集包括门诊和住院环境、各种干预策略以及人口统计学差异，有效反映了CGM使用的真实场景。与一组机器学习基线方法相比，GPFormer始终表现出卓越的性能，并且在长达两小时的预测范围内，对于所有评估数据集均实现了最低的均方根误差。这些实验结果突出了所提出模型在各种人群中的有效性和泛化能力，证明了其在广泛的实际临床环境中增强血糖管理的巨大潜力。
