发表机构
Vanderbilt University; Vanderbilt Institute for Surgery and Engineering; Department of Electrical and Computer Engineering（范德堡大学; 范德堡外科工程研究所; 电气与计算机工程系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出轻量混合学习框架，结合ECG、耳式PPG与6轴IMU，实现单搏无袖带血压估计，在多阶段压力方案与PulseDB数据集上，较基线模型降低28.2%组合MAE，适配可穿戴部署。
AI 中文摘要
连续无袖带血压（BP）监测仍面临挑战，原因包括运动伪影、生理变异性，以及传统脉搏传播时间（PTT）模型在动态条件下鲁棒性有限。许多现有方法依赖多秒窗口稳定估计，而这一假设在实际监测中常因间歇性信号损坏被打破。本研究表明，与血压相关的判别信息在单搏层面仍有保留，因此提出一种用于连续血压估计的轻量多模态可穿戴框架。该系统整合同步胸部心电图（ECG）与耳夹式反射光电容积描记法（PPG），两者均搭配6轴惯性测量单元以提供运动上下文。研究引入混合学习架构：一维卷积神经网络从单个PPG搏波中提取64维嵌入，将其与30个基于生理的特征（包括PTT统计量与心率变异性）融合，随后输入LightGBM回归器。该方法通过多阶段压力方案（n=10）与PulseDB公开数据集，采用受试者不重叠验证进行评估。在30次独立运行中，模型对收缩压的平均绝对误差为4.02±0.21 mmHg，对舒张压的平均绝对误差为1.79±0.05 mmHg，相较于基线模型，组合平均绝对误差降低了28.2%。该框架无需长时序上下文即可实现逐搏估计，支持计算高效的无袖带血压监测，适用于实际资源约束下的可穿戴设备部署。本研究的源代码可在指定URL获取。
英文摘要
Continuous cuffless blood pressure (BP) monitoring remains challenging due to motion artifacts, physiological variability, and the limited robustness of conventional pulse transit time (PTT) models under dynamic conditions. Many prior approaches rely on multi-second windows to stabilize estimation, an assumption that is frequently violated during real-world monitoring with intermittent signal corruption. Here, we show that discriminative BP-related information is preserved at the single-beat level and present a lightweight multi-modal wearable framework for continuous BP estimation. The system integrates synchronized chest electrocardiography (ECG) and ear-clip reflectance photoplethysmography, each co-located with a 6-axis inertial measurement unit to provide motion context. We introduce a hybrid learning architecture in which a one-dimensional convolutional neural network extracts a 64-dimensional embedding from individual PPG beats and fuses it with 30 physiology-grounded features, including PTT statistics and heart rate variability, followed by LightGBM regression. The method was evaluated using a multi-phase stress protocol ($n=10$) and the PulseDB public dataset with subject-disjoint validation. Across 30 independent runs, the model achieved mean absolute errors of $4.02 \pm 0.21$~mmHg for systolic BP and $1.79 \pm 0.05$~mmHg for diastolic BP, corresponding to a 28.2\% reduction in combined MAE relative to baseline models. By enabling beat-wise estimation without long temporal context, this framework supports computationally efficient cuffless BP monitoring suitable for wearable deployment under practical resource constraints. The source code for this work is available at https://github.com/SYMBIOX-Lab/BP-wireless.
Comments7 pages, 5 figures
