当前位置: X-MOL 学术IEEE J. Transl. Eng. Health Med. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Accurate Fiducial Point Detection using Haar Wavelet for Beat-by-Beat Blood Pressure Estimation
IEEE Journal of Translational Engineering in Health and Medicine ( IF 3.7 ) Pub Date : 2020-01-01 , DOI: 10.1109/jtehm.2020.3000327
Muskan Singla 1 , Syed Azeemuddin 1 , Prasad Sistla 2
Affiliation  

Pulse Arrival Time (PAT) derived from Electrocardiogram (ECG) and Photoplethysmogram (PPG) for cuff-less Blood Pressure (BP) measurement has been a contemporary and widely accepted technique. However, the features extracted for it are conventionally from an isolated pulse of ECG and PPG signals. As a result, the estimated BP is intermittent. Objective: This paper presents feature extraction from each beat of ECG and PPG signals to make BP measurements uninterrupted. These features are extracted by employing Haar transformation to adaptively attenuate measurement noise and improve the fiducial point detection precision. Method: the use of only PAT feature as an independent variable leads to an inaccurate estimation of either Systolic Blood Pressure (SBP) or Diastolic Blood Pressure (DBP) or both. We propose the extraction of supplementary features that are highly correlated to physiological parameters. Concurrent data was collected as per the Association for the Advancement of Medical Instrumentation (AAMI) guidelines from 171 human subjects belonging to diverse age groups. An Adaptive Window Wavelet Transformation (AWWT) technique based on Haar wavelet transformation has been introduced to segregate pulses. Further, an algorithm based on log-linear regression analysis is developed to process extracted features from each beat to calculate BP. Results: The mean error of 0.43 and 0.20 mmHg, mean absolute error of 4.6 and 2.3 mmHg, and Standard deviation of 6.13 and 3.06 mmHg is achieved for SBP and DBP respectively. Conclusions: The features extracted are highly precise and evaluated BP values are as per the AAMI standards. Clinical Impact: This continuous real-time BP monitoring technique can be useful in the treatment of hypertensive and potential-hypertensive subjects.

中文翻译:

使用 Haar 小波进行准确基准点检测以进行逐次血压估计

源自心电图 (ECG) 和光电容积描记图 (PPG) 的脉搏到达时间 (PAT) 用于无袖血压 (BP) 测量,已成为当代且被广泛接受的技术。然而,传统上从 ECG 和 PPG 信号的隔离脉冲中提取特征。因此,估计的血压是间歇性的。目的:本文提出了从 ECG 和 PPG 信号的每次心跳中提取特征,以使血压测量不间断。这些特征是通过哈尔变换来提取的,以自适应地衰减测量噪声并提高基准点检测精度。方法:仅使用 PAT 特征作为自变量会导致收缩压 (SBP) 或舒张压 (DBP) 或两者的估计不准确。我们建议提取与生理参数高度相关的补充特征。根据医疗器械促进协会 (AAMI) 指南,从属于不同年龄组的 171 名受试者中收集了同步数据。引入基于 Haar 小波变换的自适应窗口小波变换 (AWWT) 技术来分离脉冲。此外,还开发了一种基于对数线性回归分析的算法来处理从每个节拍中提取的特征以计算血压。结果:SBP 和 DBP 的平均误差分别为 0.43 和 0.20 mmHg,平均绝对误差为 4.6 和 2.3 mmHg,标准偏差分别为 6.13 和 3.06 mmHg。结论:提取的特征精度高,评估的BP值符合AAMI标准。临床影响:这种连续实时血压监测技术可用于治疗高血压和潜在高血压受试者。
更新日期:2020-01-01
down
wechat
bug