Novel wavelet neural network algorithm for continuous and noninvasive dynamic estimation of blood pressure from photoplethysmography

Abstract

This paper proposes a novel wavelet neural network algorithm for the continuous and noninvasive dynamic estimation of blood pressure (BP). Unlike prior algorithms, the proposed algorithm capitalizes on the correlation between photoplethysmography (PPG) and BP. Complete BP waveforms are reconstructed based on PPG signals to extract systolic blood pressure (SBP) and diastolic blood pressure (DBP). To improve the robustness, Daubechies wavelet is implemented as the hidden layer node function for the neural network. An optimized neural network structure is proposed to reduce the computational complexity. Further, this paper investigates an inhomogeneous resilient backpropagation (IRBP) algorithm to calculate the weight of hidden layer nodes. The IRBP improves the convergence speed and reconstruction accuracy. Multiparameter intelligent monitoring in Intensive Care (MIMIC) databases, which contain a variety of physiological parameters captured from patient monitors, are used to validate this algorithm. The standard deviation σ between reconstructed and actual BP signals is 4.4797 mmHg, which satisfies the American National Standards of the Association for the Advancement of Medical Instrumentation. The reconstructed BP waveform can be used to extract the SBP and DBP, whose standard deviations σ are 2.91 mmHg and 2.41 mmHg respectively.Keywords photoplethysmogram (PPG), blood pressure (BP), Daubechies wavelet, neural network, inhomogeneous resilient backpropagation (IRBP) CitationLi P, Liu M, Zhang X, et al. Novel wavelet neural network algorithm for continuous and noninvasive dynamic estimation of blood pressure from photoplethysmography.

How Effective Is Pulse Arrival Time for Evaluating Blood Pressure? Challenges and Recommendations from a Study Using the MIMIC Database

“…Their study showed that PAT has a strong correlation with SBP and DBP and that PAT-middle is the best measure to use in terms of minimizing standard error deviations. Cattivelli and Garudadri [20] and Li et al [21] performed similar studies and found similar results. Generally, the PAT-middle makes more sense clinically, as does the R-peak in ECGs (representing the onset of ventricular mechanical contraction in the heart), while the middle of the PPG waveform (the peak of the first derivative of the PPG signal) is the moment when a pulse wave transmits to the artery.…”

A Non-Invasive Continuous Blood Pressure Estimation Approach Based on Machine Learning

“…Nowadays, researchers have attempted to build more complicated models for BP estimation based on big data to describe the correlation of PTT and characteristic parameters of pulse waveform with BP. Peng et al proposed a wavelet neural network model trying to understand the relationship between pulse wave and arterial blood pressure (ABP), and then extracted SBP and DBP from reconstructed arterial BP waveform [18]. The results were in line with the Association for the Advancement of Medical Instrumentation (AAMI) criteria, but the method had high computational complexity and significant data redundancy.…”

Mobile Personal Health Care System for Noninvasive, Pervasive, and Continuous Blood Pressure Monitoring: Development and Usability Study

“…Given that light emitted by LEDs can penetrate an area that involves skin, arteries, veins, blood, bone, and other tissues, optical absorption changes detected by a PPG sensor represent a complex mixture of pulsatile and nonpulsatile blood flow components [ 13 , 30 ]. Therefore, heuristic modeling based on advanced artificial neural networks (ANNs) using nonlinear regression could aid in dealing with confounding factors and improve the result of BP estimation from feature extraction or raw PPG signals [ 19 , 31 - 34 ].…”