[论文解读] Wrist-worn blood pressure tracking in healthy free-living individuals using neural networks

Mustafa Radha, Koen de Groot+10 more|arXiv (Cornell University)|May 23, 2018

Non-Invasive Vital Sign Monitoring参考文献 45被引用 3

一句话总结

本研究提出一种结合腕部光电容积脉搏波（PPG）传感器与长短期记忆（LSTM）神经网络的方法，以无创方式估算自由生活状态下健康个体的夜间收缩压（SBP）下降值。基于226天内5,111组匹配的PPG与动态血压监测数据，LSTM模型在SBP下降值估算中的均方根误差（RMSE）达到3.12±2.20 mmHg，优于传统机器学习及非机器学习方法。

ABSTRACT

Objective: Evaluate a method for the estimation of the nocturnal systolic blood pressure (SBP) dip from 24-hour blood pressure trends using a wrist-worn photoplethysmography (PPG) sensor and a deep neural network in free-living individuals, comparing the deep neural network to traditional machine learning and non-machine learning baselines. Approach: A wrist-worn PPG sensor was worn by 106 healthy individuals for 226 days during which 5111 reference values for blood pressure (BP) were obtained with a 24-hour ambulatory BP monitor and matched with the PPG sensor data. Features based on heart rate variability and pulse morphology were extracted from the PPG waveforms. Long- and short term memory (LSTM) networks, dense networks, random forests and linear regression models were trained and evaluated in their capability of tracking trends in BP, as well as the estimation of the SBP dip. Main results: Best performance for estimating the SBP dip were obtained with a deep LSTM neural network with a root mean squared error (RMSE) of 3.12$\pm$2.20 $\Delta$mmHg and a correlation of 0.69 $(p=3*10^{-5})$. This dip was derived from trend estimates of BP which had an RMSE of 8.22$\pm$1.49 mmHg for systolic and 6.55$\pm$1.39 mmHg for diastolic BP (DBP). While other models had similar performance for the tracking of relative BP, they did not perform as well as the LSTM for the SBP dip. Significance: The work provides first evidence for the unobtrusive estimation of the nocturnal SBP dip, a highly prognostic clinical parameter. It is also the first to evaluate unobtrusive BP measurement in a large data set of unconstrained 24-hour measurements in free-living individuals and provides evidence for the utility of LSTM models in this domain.

研究动机与目标

• 评估在自由生活条件下，利用腕部PPG传感器估算夜间收缩压（SBP）下降值的可行性。
• 比较深度学习、传统机器学习与非机器学习模型在追踪24小时血压趋势方面的表现。
• 评估长短期记忆（LSTM）网络在捕捉长期血压变异性及估算临床相关参数（如SBP下降值）方面的性能。
• 为可穿戴PPG传感器在真实世界环境中实现连续无创血压监测的临床实用性提供证据。

提出的方法

• 腕部PPG传感器在226天内持续采集106名健康个体的光电容积脉搏波信号。
• 从PPG波形中提取的心率变异性与脉搏波形态特征作为特征。
• 使用长短期记忆（LSTM）网络对PPG衍生特征中的时间依赖性进行建模，以预测24小时血压趋势。
• 同时训练并比较了全连接神经网络、随机森林与线性回归模型在血压趋势估算与SBP下降值预测中的表现。
• 参考血压值通过24小时动态血压监测获得，并与PPG传感器读数进行匹配。
• 采用均方根误差（RMSE）与皮尔逊相关系数对模型性能进行评估，参照标准SBP下降值。

实验结果

研究问题

• RQ1 结合深度神经网络的腕部PPG传感器能否在自由生活个体中准确估算夜间收缩压（SBP）下降值？
• RQ2 基于LSTM的模型在PPG数据中估算SBP下降值方面，相较于传统机器学习与非机器学习模型表现如何？
• RQ3 PPG衍生特征在多大程度上能够捕捉长期血压趋势，从而支持SBP下降值估算？
• RQ4 在非受控的日常环境中，SBP下降值这一关键预后指标是否可通过无创、连续的PPG监测可靠估算？

主要发现

• LSTM神经网络在估算夜间SBP下降值方面取得了最低的均方根误差（RMSE）3.12±2.20 mmHg，显著优于其他模型。
• SBP下降值估算与参考值的相关系数为r=0.69（p=3×10⁻⁵），表明具有高度统计学意义。
• LSTM模型在血压趋势估算中的RMSE为：收缩压8.22±1.49 mmHg，舒张压6.55±1.39 mmHg。
• 其他模型在追踪相对血压趋势方面表现相近，但在SBP下降值估算方面准确度较低。
• 本研究首次提供了利用可穿戴PPG与深度学习实现无创、连续估算具有临床预后意义的夜间SBP下降值的证据。
• 结果表明，LSTM模型在捕捉PPG数据中复杂的时序模式方面具有显著优势，适用于心血管风险评估。