Signal, Image and Video Processing
https://doi.org/10.1007/s11760-021-01952-z
ORIGINAL PAPER
Wavelet scattering transform and long short-term memory
network-based noninvasive blood pressure estimation from
photoplethysmograph signals
N. Jean Effil
1,2
· R. Rajeswari
1,2
Received: 22 June 2020 / Revised: 5 October 2020 / Accepted: 29 May 2021
© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2021
Abstract
Measuring blood pressure from photoplethysmograph (PPG) signals is gaining popularity as the PPG devices are inexpensive,
convenient to use and much portable. The advent of wearable PPG devices, machine learning and signal processing has
motivated in the development of cuffless blood pressure calculation from PPG signals captured from fingertip. The conventional
pulse transit time-based method of measuring blood pressure from PPG is inconvenient as it requires electrocardiogram signals
and PPG signals or PPG signals captured simultaneously from two different sites of the body. The proposed system uses the
PPG signals alone to estimate blood pressure (BP). A signal analysis method called wavelet scattering transform is applied
on the preprocessed PPG signals to extract features. Predictor model that estimates BP are derived by training the support
vector regression model and long short term memory prediction model. The derived models are evaluated with testing dataset
and the results are compared with ground truth values. The results show that the accuracy of the proposed method achieves
grade B for the estimation of the diastolic blood pressure and grade C for the mean arterial pressure under the standard British
Hypertension Society protocol. On comparing the results of the proposed system with the benchmark machine learning
algorithms, it is observed that the proposed model outperforms others by a considerable margin. A comparative analysis with
prior studies shows that the results obtained from proposed work are comparable with existing works in the literature.
Keywords Photoplethysmography · Wavelet scattering · Support vector machine · Blood pressure · LSTM · Regression
1 Introduction
According to World Health Organization, presently, 1.13 bil-
lion people in the world have high BP and among them less
than 1 in 5 people have taken remedial measures to keep
BP under control. Hypertension is one of the biggest causes
of life threatening cardiovascular diseases such as stroke
and heart attack. Cardiovascular disease caused 17.9 mil-
lion (31%) deaths worldwide in the year 2016. Hence blood
pressure needs to be checked regularly, and if found high,
remedial measures such as medications, healthy diet and
physical activity need to be taken to keep the blood pres-
sure under control [1].
B R. Rajeswari
rajeswari@buc.edu.in
1
Government Arts and Science College, Kadayanallur,
Tamilnadu, India
2
Bharathiar University, Coimbatore, Tamilnadu, India
Hypertension, also known as high blood pressure is a con-
dition in which the blood vessels have constricted due to
deposit of fats and free radicals and the individual has per-
sistently ‘raised’ blood pressure. Blood is carried from the
heart to all parts of the body through the blood vessels. Each
time the heart beats, it pumps blood into the vessels. Blood
pressure is created due to the force exerted by blood, which
pushes against the blood vessel walls and the arteries, when
it is pumped by the heart. The unit for measuring blood pres-
sure is millimetres of mercury (“mmHg”). Blood pressure is
recorded with the systolic reading followed by the diastolic
reading. Systolic blood pressure (SBP) is the pressure created
when the heart pumps out blood. Diastolic blood pressure
(DBP) is created while the heart muscle is resting between
beats and is being refilled with blood. Mean arterial pressure
(MAP) refers to the average of SBP and DBP values for one
cardiac cycle.
The sphygmomanometer is the gold standard for measur-
ing blood pressure. This is not convenient for the continuous
monitoring of blood pressure and also it requires trained
123