A novel method for continuous blood pressure estimation based on a single-channel photoplethysmogram signal

被引：20
作者：
Hu, Qihan [1 ]
Deng, Xintao [2 ]
Wang, Aiguo [2 ]
Yang, Cuiwei [1 ,3 ]
机构：
[1] Fudan Univ, Dept Elect Engn, Shanghai 200433, Peoples R China
[2] Xinghua City Peoples Hosp, Taizhou 225700, Jiangsu, Peoples R China
[3] Shanghai Engn Res Ctr Cardiac Electrophysiol, Key Lab Med Imaging Comp & Comp Assisted Interven, Shanghai 201318, Peoples R China
来源：
PHYSIOLOGICAL MEASUREMENT | 2020年 / 41卷 / 12期
基金：
中国国家自然科学基金;
关键词：
blood pressure estimation; ensemble machine learning; multi-Gaussian fitting; photoplethysmogram (PPG); PULSE TRANSIT-TIME;
D O I：
10.1088/1361-6579/abc8dd
中图分类号：
Q6 [生物物理学];
学科分类号：
071011 ;
摘要：
Objective: Currently, continuous blood pressure (BP) measurements are mostly based on multi-sensor combinations and datasets with limited BP ranges. Besides, most BP-related features derive from the photoplethysmogram (PPG) signal. The mechanism of PPG signal formation is not considered. We aimed to design a noninvasive and continuous method for estimation of BP using a single PPG sensor, which takes the mechanism of PPG signal formation into account. Approach: We prepared a dataset containing PPG signals for 294 patients from three public databases for constructing the BP estimation model. The features used in the model consisted of two types: novel features based on a multi-Gaussian model and existing features. The multi-Gaussian model fitted the different components (i.e. the main wave, the dicrotic wave and the tidal wave) of the PPG signal. Ensemble machine learning algorithms were applied to estimate systolic blood pressure (SBP) and diastolic blood pressure (DBP). When partitioning the dataset, there was an overlap between the training set and the testing set. Main results: Datasets with a wide-range of SBP and DBP values (SBP ranging from 74 to 229 mmHg and DBP ranging from 26 to 141 mmHg) were used to evaluate our method. The mean and standard deviation of error for SBP and DBP estimations were -0.21 +/- 5.21 mmHg and -0.19 +/- 3.37 mmHg, respectively. The model performance fully met the Association for the Advancement of Medical Instrumentation standard and was grade 'A' on the British Hypertension Society standard. Significance: The multi-Gaussian model could be used to estimate BP, and our method was able to track a wide range of BP accurately. In addition our method is based on a single PPG sensor, making it very convenient.
引用
收藏
页数：12
相关论文
共 35 条
[1]   Electrocardiogram-Assisted Blood Pressure Estimation [J].
Ahmad, Saif ;
Chen, Silu ;
Soueidan, Karen ;
Batkin, Izmail ;
Bolic, Miodrag ;
Dajani, Hilmi ;
Groza, Voicu .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2012, 59 (03) :608-618
[2]  
American National Standard for Electronic or Automated Sphygmomanometers, 2002, ANSI AAMI SP
[3]  
[Anonymous], 2015, WORLD HLTH STAT
[4]  
Banerjee R, 2015, INT CONF ACOUST SPEE, P967, DOI 10.1109/ICASSP.2015.7178113
[5]  
Baruch Martin C, 2011, Nonlinear Biomed Phys, V5, P1, DOI 10.1186/1753-4631-5-1
[6]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[7]   XGBoost: A Scalable Tree Boosting System [J].
Chen, Tianqi ;
Guestrin, Carlos .
KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :785-794
[8]   Estimating Blood Pressure from the Photoplethysmogram Signal and Demographic Features Using Machine Learning Techniques [J].
Chowdhury, Moajjem Hossain ;
Shuzan, Md Nazmul Islam ;
Chowdhury, Muhammad E. H. ;
Mahbub, Zaid B. ;
Uddin, M. Monir ;
Khandakar, Amith ;
Reaz, Mamun Bin Ibne .
SENSORS, 2020, 20 (11)
[9]  
Dey J, 2018, IEEE ENG MED BIO, P5002, DOI 10.1109/EMBC.2018.8513189
[10]  
Dorogush A.V., 2018, ML Systems, NeurIPS, DOI DOI 10.48550/ARXIV.1810.11363
1234