对比多种Transformer模型,提升糖尿病患者血糖多时距预测精度。
A Comparative Study of Transformer-Based Models for Multi-Horizon Blood Glucose Prediction
- 用分块嵌入法处理血糖、胰岛素和饮食数据,捕捉时间序列特征。
- 1小时以上预测中,PatchTST模型表现最佳,4小时预测误差仅46.5 mg/dL。
- 输入一周历史数据可显著提升长期预测效果,适合临床闭环系统应用。
精准的血糖预测可推动1型糖尿病治疗的新干预手段,如个性化胰岛素与饮食调整。尽管基于Transformer的架构在复杂多变量时间序列预测中展现出注意力机制的优势,但其在血糖预测中的潜力仍待深入探索。本文对多种Transformer模型进行横向比较,针对最多4小时的多时距血糖预测,使用长达一周的历史数据。基于公开的DCLP3数据集(n=112)按80%-10%-10%划分训练、验证与测试集,并以OhioT1DM数据集(n=12)作为外部验证。采用点嵌入、块嵌入、序列嵌入及混合嵌入方式,融合连续血糖监测(CGM)、胰岛素与进食数据。短期预测中,块嵌入结构的Crossformer在30分钟预测上表现最优,RMSE达15.6 mg/dL(OhioT1DM)。对于1小时、2小时与4小时预测,另一块嵌入模型PatchTST表现最佳,对应RMSE为24.6、36.1、46.5 mg/dL。总体而言,采用块化分词的模型在更大输入规模下更准确,最佳结果出现在使用一周历史数据时。研究证明,Transformer架构能有效捕捉多变量时间序列中的周期性模式,显著提升血糖预测精度。
原文摘要 · Abstract (English)
Accurate blood glucose prediction can enable novel interventions for type 1 diabetes treatment, including personalized insulin and dietary adjustments. Although recent advances in transformer-based architectures have demonstrated the power of attention mechanisms in complex multivariate time series prediction, their potential for blood glucose (BG) prediction remains underexplored. We present a comparative analysis of transformer models for multi-horizon BG prediction, examining forecasts up to 4 hours and input history up to 1 week. The publicly available DCLP3 dataset (n=112) was split (80%-10%-10%) for training, validation, and testing, and the OhioT1DM dataset (n=12) served as an external test set. We trained networks with point-wise, patch-wise, series-wise, and hybrid embeddings, using CGM, insulin, and meal data. For short-term blood glucose prediction, Crossformer, a patch-wise transformer architecture, achieved a superior 30-minute prediction of RMSE (15.6 mg / dL on OhioT1DM). For longer-term predictions (1h, 2h, and 4h), PatchTST, another path-wise transformer, prevailed with the lowest RMSE (24.6 mg/dL, 36.1 mg/dL, and 46.5 mg/dL on OhioT1DM). In general, models that used tokenization through patches demonstrated improved accuracy with larger input sizes, with the best results obtained with a one-week history. These findings highlight the promise of transformer-based architectures for BG prediction by capturing and leveraging seasonal patterns in multivariate time-series data to improve accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。