An End-to-End Neural Network Model
for Blood Pressure Estimation Using PPG
Signal
Cuicui Wang, Fan Yang, Xueguang Yuan
(&)
, Yangan Zhang,
Kunliang Chang, and Zhengyang Li
State Key Laboratory of Information Photonics and Optical Communications,
Beijing University of Posts and Telecommunications, Beijing 100876, China
yuanxg@bupt.edu.cn
Abstract. With the increasing number of hypertension patients, the monitoring
of blood pressure information becomes an important task. In this study, an endto-end approach is proposed to estimate blood pressure from the pulse wave
signal. In this approach, a normalized single pulse wave is the input of a neural
network, which consists of the convolutional layers and the recurrent layers,
then outputs the corresponding blood pressure. The convolutional layers consist
of one-dimensional convolutional layers and depth-separable convolutional
layers. The gated recurrent unit (GRU) is used in the recurrent layer. Finally, a
dense layer is used to output estimated values of blood pressure. In comparison
with previous approaches, the proposed method does not require complicated
feature extraction. It is only necessary to input a single pulse wave into the
neural network and blood pressure can be estimated. The proposed approach is
tested in the multi-parameter intelligent monitoring in intensive care (MIMIC)
dataset, and the average absolute error is 3.95 mmHg for systolic blood pressure
and 2.14 mmHg for diastolic blood pressure. This result fulfills the international
standard of blood pressure measurement, which shows the proposed approach is
simple and effective. In practice, the proposed method is designed to obtain
blood pressure information from pulse waves.
Keywords: Photoplethysmography Á Blood pressure measurement Á Neural
network Á Transfer learning
1 Introduction
Blood pressure (BP) is the pressure of circulating blood on the walls of blood vessels.
Monitoring of human blood pressure can reflect well the function of the cardiovascular
system of the human body, so it is a great way to judge the disease and observe the
therapeutic effect clinically. According to the association for the advancement of
medical instrumentation (AAMI), the mean and deviation absolute error between the
device and the mercury standard sphygmomanometer should be lower than
5 ± 8 mmHg [1].
With the development of deep learning, many scientists are committed to taking
advantages of the neural network to discover new blood pressure measurement
© Springer Nature Singapore Pte Ltd. 2020
Q. Liang et al. (Eds.): Artificial Intelligence in China, LNEE 572, pp. 262–272, 2020.
https://doi.org/10.1007/978-981-15-0187-6_30
for Blood Pressure Estimation Using PPG
Signal
Cuicui Wang, Fan Yang, Xueguang Yuan
(&)
, Yangan Zhang,
Kunliang Chang, and Zhengyang Li
State Key Laboratory of Information Photonics and Optical Communications,
Beijing University of Posts and Telecommunications, Beijing 100876, China
yuanxg@bupt.edu.cn
Abstract. With the increasing number of hypertension patients, the monitoring
of blood pressure information becomes an important task. In this study, an endto-end approach is proposed to estimate blood pressure from the pulse wave
signal. In this approach, a normalized single pulse wave is the input of a neural
network, which consists of the convolutional layers and the recurrent layers,
then outputs the corresponding blood pressure. The convolutional layers consist
of one-dimensional convolutional layers and depth-separable convolutional
layers. The gated recurrent unit (GRU) is used in the recurrent layer. Finally, a
dense layer is used to output estimated values of blood pressure. In comparison
with previous approaches, the proposed method does not require complicated
feature extraction. It is only necessary to input a single pulse wave into the
neural network and blood pressure can be estimated. The proposed approach is
tested in the multi-parameter intelligent monitoring in intensive care (MIMIC)
dataset, and the average absolute error is 3.95 mmHg for systolic blood pressure
and 2.14 mmHg for diastolic blood pressure. This result fulfills the international
standard of blood pressure measurement, which shows the proposed approach is
simple and effective. In practice, the proposed method is designed to obtain
blood pressure information from pulse waves.
Keywords: Photoplethysmography Á Blood pressure measurement Á Neural
network Á Transfer learning
1 Introduction
Blood pressure (BP) is the pressure of circulating blood on the walls of blood vessels.
Monitoring of human blood pressure can reflect well the function of the cardiovascular
system of the human body, so it is a great way to judge the disease and observe the
therapeutic effect clinically. According to the association for the advancement of
medical instrumentation (AAMI), the mean and deviation absolute error between the
device and the mercury standard sphygmomanometer should be lower than
5 ± 8 mmHg [1].
With the development of deep learning, many scientists are committed to taking
advantages of the neural network to discover new blood pressure measurement
© Springer Nature Singapore Pte Ltd. 2020
Q. Liang et al. (Eds.): Artificial Intelligence in China, LNEE 572, pp. 262–272, 2020.
https://doi.org/10.1007/978-981-15-0187-6_30