Cuffless Blood Pressure Estimation Based on Data-Oriented Continuous Health Monitoring System

Cuffless Blood Pressure Estimation Based on Monte Carlo Simulation Using Photoplethysmography Signals

Blood pressure measurements are one of the most routinely performed medical tests globally. Blood pressure is an important metric since it provides information that can be used to diagnose several vascular diseases. Conventional blood pressure measurement systems use cuff-based devices to measure the blood pressure, which may be uncomfortable and sometimes burdensome to the subjects. Therefore, in this study, we propose a cuffless blood pressure estimation model based on Monte Carlo simulation (MCS). We propose a heterogeneous finger model for the MCS at wavelengths of 905 nm and 940 nm. After recording the photon intensities from the MCS over a certain range of blood pressure values, the actual photoplethysmography (PPG) signals were used to estimate blood pressure. We used both publicly available and self-made datasets to evaluate the performance of the proposed model. In case of the publicly available dataset for transmission-type MCS, the mean absolute errors are 3.32 ± 6.03 mmHg for systolic blood pressure (SBP), 2.02 ± 2.64 mmHg for diastolic blood pressure (DBP), and 1.76 ± 2.8 mmHg for mean arterial pressure (MAP). The self-made dataset is used for both transmission- and reflection-type MCSs; its mean absolute errors are 2.54 ± 4.24 mmHg for SBP, 1.49 ± 2.82 mmHg for DBP, and 1.51 ± 2.41 mmHg for MAP in the transmission-type case as well as 3.35 ± 5.06 mmHg for SBP, 2.07 ± 2.83 mmHg for DBP, and 2.12 ± 2.83 mmHg for MAP in the reflection-type case. The estimated results of the SBP and DBP satisfy the requirements of the Association for the Advancement of Medical Instrumentation (AAMI) standards and are within Grade A according to the British Hypertension Society (BHS) standards. These results show that the proposed model is efficient for estimating blood pressures using fingertip PPG signals.

Cuff-less Blood Pressure Estimation from Photoplethysmography via Visibility Graph and Transfer Learning

This paper presents a new solution that enables the use of transfer learning for cuff-less blood pressure (BP) monitoring via short duration of photoplethysmogram (PPG). The proposed method estimates BP with low computational budget by 1) creating images from segments of PPG via visibility graph (VG) that preserves the temporal information of the PPG waveform, 2) using pre-trained deep convolutional neural network (CNN) to extract feature vectors from VG images, and 3) solving for the weights and bias between the feature vectors and the reference BPs with ridge regression. Using the University of California Irvine (UCI) database consisting of 348 records, the proposed method achieves a best error performance of 0.008.46 mmHg for systolic blood pressure (SBP), and -0.045.36 mmHg for diastolic blood pressure (DBP), respectively, in terms of the mean error (ME) and the standard deviation (SD) of error, ranking grade B for SBP and grade A for DBP under the British Hypertension Society (BHS) protocol. Our novel data-driven method offers a computationally-efficient end-to-end solution for rapid and user-friendly cuff-less PPG-based BP estimation.

Continuous PPG-Based Blood Pressure Monitoring Using Multi-Linear Regression

In this work, we present a photoplethysmography-based blood pressure monitoring algorithm (PPG-BPM) that solely requires a photoplethysmography (PPG) signal. The technology is based on pulse wave analysis (PWA) of PPG signals retrieved from different body locations to continuously estimate the systolic blood pressure (SBP) and the diastolic blood pressure (DBP). The proposed algorithm extracts morphological features from the PPG signal and maps them to SBP and DBP values using a multiple linear regression (MLR) model. The performance of the algorithm is evaluated on the publicly available Multiparameter Intelligent Monitoring in Intensive Care (MIMIC I) database. We utilize 28 data-sets (records) from the MIMIC I database that contain both PPG and brachial arterial blood pressure (ABP) signals. The collected PPG and ABP signals are synchronized and divided into intervals of 30 seconds, called epochs. In total, we utilize 47153 \textit{clean} 30-second epochs for the performance analysis. Out of the 28 data-sets, we use only 2 data-sets (records 041 and 427 in the MIMIC I) with a total of 2677 \textit{clean} 30-second epochs to build the MLR model of the algorithm. For the SBP, a standard deviation of error (SDE) of 8.01 mmHg and a mean absolute error (MAE) of 6.10 mmHg between the arterial line and the PPG-based values are achieved, with a Pearson correlation coefficient r = 0.90, . For the DBP, an SDE of 6.22 mmHg and an MAE of 4.65 mmHg between the arterial line and the PPG-based values are achieved, with a Pearson correlation coefficient r = 0.85, . We also use a binary classifier for the BP values with the positives indicating SBP ≥ 130 mmHg and/or DBP ≥ 80 mmHg and the negatives indicating otherwise. The classifier results generated by the PPG-based SBP and DBP estimates achieve a sensitivity and a specificity of 79.11% and 92.37%, respectively.

Photoplethysmography Based Blood Pressure Monitoring Using the Senbiosys Ring

In this work, we evaluate the accuracy of our cuffless photoplethysmography based blood pressure monitoring (PPG-BPM) algorithm. The algorithm is evaluated on an ultra low power photoplethysmography (PPG) signal acquired from the Senbiosys Ring. The study involves six male subjects wearing the ring for continuous finger PPG recordings and non-invasive brachial cuff inflated every two to ten minutes for intermittent blood pressure (BP) measurements. Each subject performs the required recordings two to three times with at least two weeks difference between any two recordings. In total, the study includes 17 recordings 2.21 ± 0.89 hours each. The PPG recordings are processed by the PPG-BPM algorithm to generate systolic BP (SBP) and diastolic BP (DBP) estimates. For the SBP, the mean difference between the cuff-based and the PPG-BPM values is -0.28 ± 7.54 mmHg. For the DBP, the mean difference between the cuff-based and the PPG-BPM values is -1.30 ± 7.18 mmHg. The results show that the accuracy of our algorithm is within the 5 ± 8 mmHg ISO/ANSI/AAMI protocol requirement.

Cuff-less blood pressure estimation using wrist photoplethysmography

One of the most promising and at the same time rapidly growing sectors in healthcare is that of wearable medical devices. Population ageing constantly shifts towards a higher number of senior and elderly people with increased prevalence of chronic diseases often requiring long-term care and a need to decrease hospitalization time and cost. However, today most of the devices entering the market are not standardized nor medically approved, and they are highly inaccurate. In this work we present a system and a method to provide accurate measurement of systolic and diastolic blood pressure (BP) based solely on wrist photoplethysmography. We map morphological features to BP values using machine learning and propose ways to select high quality signals leading to an accuracy improvement of up to 33.5%, if compared against no signal selection, a mean absolute error of 1.1mmHg in a personalized scenario and 8.7mmHg in an uncalibrated leave-one-out scenario.

Learning and non-learning algorithms for cuffless blood pressure measurement: a review

The machine learning approach has gained a significant attention in the healthcare sector because of the prospect of developing new techniques for medical devices and handling the critical database of chronic diseases. The learning approach has potential to analyze complex medical data, disease diagnosis, and patient monitoring system, and to monitor e-health record. Non-invasive cuffless blood pressure (CLBP) measurement secured a significant position in the patient monitoring system. From a few recent decades, the importance of cuffless technology has been perceived towards continuous monitoring of blood pressure (BP) and supplementary efforts have been made towards its continuous monitoring. However, the optimal method that measures BP unambiguously and continuously has not yet emerged along with issues like calibration time, accuracy and long-term estimation of BP with miniaturizing hardware. The present study provides an insight into several learning algorithms along with their feature selection models. Various challenges and future improvements towards the current state of machine learning in healthcare industries are discussed in the present review. The bottom line of this study is to provide a comprehensive perspective of the machine learning approach of CLBP for the generation of highly precise predictive models for continuous BP measurement.

Cuffless Blood Pressure Estimation from only the Waveform of Photoplethysmography using CNN

Although the pulse transit time is generally used for blood pressure estimation without a cuff, a method of estimating blood pressure only from photoplethysmography (PPG) based on the relationship between pulse waveform and blood pressure has been studied. This can eliminate the need for an electrocardiogram and allow more continuous and simpler blood pressure measurement. Previous studies have proposed methods of machine learning by extracting features such as wave height and time difference, or generating features with an auto-encoder. In this paper, we propose a method to estimate blood pressure and to automatically generate features from pulse wave using the convolutional neural networks (CNN). By comparing the accuracy of the proposed method with that of the conventional method, the effectiveness of cuffless blood pressure estimation from only PPG by using CNN is examined.

Cuffless Single-Site Photoplethysmography for Blood Pressure Monitoring

One in three adults worldwide has hypertension, which is associated with significant morbidity and mortality. Consequently, there is a global demand for continuous and non-invasive blood pressure (BP) measurements that are convenient, easy to use, and more accurate than the currently available methods for detecting hypertension. This could easily be achieved through the integration of single-site photoplethysmography (PPG) readings into wearable devices, although improved reliability and an understanding of BP estimation accuracy are essential. This review paper focuses on understanding the features of PPG associated with BP and examines the development of this technology over the 2010-2019 period in terms of validation, sample size, diversity of subjects, and datasets used. Challenges and opportunities to move single-site PPG forward are also discussed.

Non-invasive continuous blood pressure monitoring systems: current and proposed technology issues and challenges

High blood pressure (BP) or hypertension is the single most crucial adjustable risk factor for cardiovascular diseases (CVDs) and monitoring the arterial blood pressure (ABP) is an efficient way to detect and control the prevalence of the cardiovascular health of patients. Therefore, monitoring the regulation of BP during patients' daily life plays a critical role in the ambulatory setting and the latest mobile health technology. In recent years, many studies have been conducted to explore the feasibility and performance of such techniques in the health care system. The ultimate aim of these studies is to find and develop an alternative to conventional BP monitoring by using cuff-less, easy-to-use, fast, and cost-effective devices for controlling and lowering the physical harm of CVDs to the human body. However, most of the current studies are at the prototype phase and face a range of issues and challenges to meet clinical standards. This review focuses on the description and analysis of the latest continuous and cuff-less methods along with their key challenges and barriers. Particularly, most advanced and standard technologies including pulse transit time (PTT), ultrasound, pulse arrival time (PAT), and machine learning are investigated. The accuracy, portability, and comfort of use of these technologies, and the ability to integrate to the wearable healthcare system are discussed. Finally, the future directions for further study are suggested.

Features Extraction for Cuffless Blood Pressure Estimation by Autoencoder from Photoplethysmography

Several studies have been proposed to estimate blood pressure (BP) with cuffless devices using only a Photoplethysmograph (PPG) sensor on the basis of the physiological knowledge that the PPG changes depend on the state of the cardiovascular system. In these studies, machine learning algorithms were used to extract various features from the wave height and the elapsed time from the rising point of the pulse wave to feature points have been used to estimate the BP. However, the accuracy is still not adequate to be used as medical equipment because their features cannot express fully information of the pulse waveform which changes according to the BP. And, no other effective knowledge about the pulse waveform for estimating BP has been found yet. Therefore, in this study, we focus on the autoencoder which can extract complex features and can add new features of the pulse waveform for estimating the BP. By using autoencoder, we extracted 100 features from the coupling signal of the pulse wave and from its first-order differentiation and second-order differentiation. The result of examination with 1363 test subjects show that the correlation coefficients and the standard deviation of the difference between the measured BP and the estimated BP got improved from R = 0.67, SD = 13.97 without autoencoder to R = 0.78, SD = 11.86 with autoencoder.

Hypertension Assessment Using Photoplethysmography: A Risk Stratification Approach

Hypertension is a common chronic cardiovascular disease (CVD). Early screening and diagnosis of hypertension plays a major role in its prevention and in the control of CVDs. Our study discusses the early screening of hypertension while using the morphological features of photoplethysmography (PPG). Numerous morphological features of PPG and its derivative waves were defined and extracted. Six types of feature selection methods were chosen to screen and evaluate these PPG morphological features. The optimal features were comprehensively analyzed in relation to the physiological processes of the cardiovascular circulatory system. Particularly, the intrinsic relation and physiological significance between the formation process of systolic blood pressure (SBP) and PPG morphology features were analyzed in depth. A variety of linear and nonlinear classification models were established for the comparison trials. The F1 scores for the normotension versus prehypertension, normotension and prehypertension versus hypertension, and normotension versus hypertension trials were 72.97%, 81.82%, and 92.31%, respectively. In summary, this study established a PPG characteristic analysis model and established the intrinsic relationship between SBP and PPG characteristics. Finally, the risk stratification of hypertension at different stages was examined and compared based on the optimal feature subset.

Blood Pressure Estimation Using Photoplethysmography Only: Comparison between Different Machine Learning Approaches

Introduction

Blood pressure (BP) has been a potential risk factor for cardiovascular diseases. BP measurement is one of the most useful parameters for early diagnosis, prevention, and treatment of cardiovascular diseases. At present, BP measurement mainly relies on cuff-based techniques that cause inconvenience and discomfort to users. Although some of the present prototype cuffless BP measurement techniques are able to reach overall acceptable accuracies, they require an electrocardiogram (ECG) and a photoplethysmograph (PPG) that make them unsuitable for true wearable applications. Therefore, developing a single PPG-based cuffless BP estimation algorithm with enough accuracy would be clinically and practically useful.

Methods

The University of Queensland vital sign dataset (online database) was accessed to extract raw PPG signals and its corresponding reference BPs (systolic BP and diastolic BP). The online database consisted of PPG waveforms of 32 cases from whom 8133 (good quality) signal segments (5 s for each) were extracted, preprocessed, and normalised in both width and amplitude. Three most significant pulse features (pulse area, pulse rising time, and width 25%) with their corresponding reference BPs were used to train and test three machine learning algorithms (regression tree, multiple linear regression (MLR), and support vector machine (SVM)). A 10-fold cross-validation was applied to obtain overall BP estimation accuracy, separately for the three machine learning algorithms. Their estimation accuracies were further analysed separately for three clinical BP categories (normotensive, hypertensive, and hypotensive). Finally, they were compared with the ISO standard for noninvasive BP device validation (average difference no greater than 5 mmHg and SD no greater than 8 mmHg).

Results

In terms of overall estimation accuracy, the regression tree achieved the best overall accuracy for SBP (mean and SD of difference: −0.1 ± 6.5 mmHg) and DBP (mean and SD of difference: −0.6 ± 5.2 mmHg). MLR and SVM achieved the overall mean difference less than 5 mmHg for both SBP and DBP, but their SD of difference was >8 mmHg. Regarding the estimation accuracy in each BP categories, only the regression tree achieved acceptable ISO standard for SBP (−1.1 ± 5.7 mmHg) and DBP (−0.03 ± 5.6 mmHg) in the normotensive category. MLR and SVM did not achieve acceptable accuracies in any BP categories.

Conclusion

This study developed and compared three machine learning algorithms to estimate BPs using PPG only and revealed that the regression tree algorithm was the best approach with overall acceptable accuracy to ISO standard for BP device validation. Furthermore, this study demonstrated that the regression tree algorithm achieved acceptable measurement accuracy only in the normotensive category, suggesting that future algorithm development for BP estimation should be more specific for different BP categories.

Data mining investigation of the association between a limb ballistocardiogram and blood pressure

OBJECTIVE

To investigate the association between a limb ballistocardiogram (BCG) and blood pressure (BP) based on data mining.

APPROACH

During four BP-perturbing interventions, the BCG and reference BP were measured from 23 young, healthy volunteers using a custom-manufactured wristband equipped with a MEMS accelerometer and a commercial continuous BP measurement device. Both timing and amplitude features in the wrist BCG waveform were extracted, and significant features predictive of diastolic (DP) and systolic (SP) BP were selected using stepwise linear regression analysis. The selected features were further compressed using principal component analysis to yield a small set of DP and SP predictors. The association between the predictors thus obtained and BP was investigated by multivariate linear regression analysis.

MAIN RESULTS

The predictors exhibited a meaningful association with BP. When three most significant predictors were used for DP and SP, a correlation coefficient of r  =  0.75  ±  0.03 (DP) and r  =  0.75  ±  0.03 (SP), a root-mean-squared error (RMSE) of 7.4  ±  0.6 mmHg (DP) and 10.3  ±  0.8 mmHg (SP), and a mean absolute error (MAE) of 6.0  ±  0.5 mmHg (DP) and 8.3  ±  0.7 mmHg (SP) were obtained across all interventions (mean  ±  SE). The association was consistent in all the individual interventions (r  ⩾  0.68, RMSE  ⩽  5.7 mmHg, and MAE  ⩽  4.5 mmHg for DP as well as r  ⩾  0.61, RMSE  ⩽  7.9 mmHg, and MAE  ⩽  6.4 mmHg for SP on the average). The minimum number of requisite predictors for robust yet practically realistic BP monitoring appeared to be three. The association between predictors and BP was maintained even under regularized calibration (r  =  0.63  ±  0.05, RMSE  =  9.3  ±  0.8 mmHg, and MAE  =  7.6  ±  0.7 mmHg for DP as well as r  =  0.60  ±  0.05, RMSE  =  14.7  ±  1.4 mmHg, and MAE  =  11.9  ±  1.1 mmHg for SP (mean  ±  SE)). The requisite predictors for DP and SP were distinct from each other.

SIGNIFICANCE

The results of this study may provide a viable basis for ultra-convenient BP monitoring based on a limb BCG alone.