PACD-Net: 假设增强对比学习用于从SMBG估计血糖控制
PACD-Net: Pseudo-Augmented Contrastive Distillation for Glycemic Control Estimation from SMBG
AI总结：
本研究提出PACD-Net，一种自监督对比学习框架，用于从稀疏不规则采样的SMBG数据中估计血糖控制指标，通过伪SMBG样本指导学习并提高模型的准确性和稳定性。
摘要：
有效的糖尿病管理需要持续监测血糖水平。临床中，通过连续葡萄糖监测（CGM）获取的指标如时间范围（TIR）、低于范围时间（TBR）和高于范围时间（TAR）用于评估血糖控制。然而，由于CGM成本高且可及性有限，许多患者依赖自测血糖（SMBG）。与CGM不同，SMBG提供稀疏且不规则的测量，使得准确估计这些指标具有挑战性。传统监督学习方法在稀疏数据下表现不佳，导致泛化能力差和性能不稳定。为此，我们提出PACD-Net，一种自监督对比学习框架，用于从SMBG估计血糖控制。使用具有更丰富时间覆盖的伪SMBG样本作为教师信号，指导从稀疏观测中学习。此外，多视图对比学习强制不同采样模式下的表征一致性。模型采用混合Swin Transformer-CNN主干网络以捕捉稀疏SMBG序列中的时间依赖性。实验结果表明，PACD-Net在真实世界SMBG数据中对TAR、TIR和TBR的估计优于现有方法，实现了在极稀疏观测设置下的改进准确性和增强的稳定性与泛化能力。所提出的框架为临床SMBG解释提供了实用工具，并为从稀疏且不规则采样的传感器数据中学习提供了通用方法。
英文摘要：
Effective diabetes management requires continuous monitoring of glycemic levels. Clinically, glycemic control is assessed using metrics such as Time in Range (TIR), Time Below Range (TBR), and Time Above Range (TAR), typically derived from continuous glucose monitoring (CGM). However, many patients rely on self-monitoring of blood glucose (SMBG) due to the high cost and limited accessibility of CGM. Unlike CGM, SMBG provides sparse and irregular measurements, making accurate estimation of these metrics challenging. Conventional supervised learning approaches struggle under such sparsity, leading to poor generalization and unstable performance. To address this, we propose PACD-Net, a self-supervised contrastive knowledge distillation framework for estimating glycemic control from SMBG. Pseudo-SMBG samples with richer temporal coverage are used as teacher signals to guide learning from sparse observations. In addition, multi-view contrastive learning enforces representation consistency across diverse sampling patterns. The model adopts a hybrid Swin Transformer-CNN backbone to capture temporal dependencies in sparse SMBG sequences. Experimental results demonstrate that PACD-Net consistently outperforms existing methods in estimating TAR, TIR, and TBR from real-world SMBG data, achieving improved accuracy as well as enhanced stability and generalization under extremely sparse observation settings. The proposed framework provides a practical tool for clinical SMBG interpretation and offers a generalizable approach for learning from sparse and irregularly sampled sensor data in broader applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
