A Novel Clustering-Based Algorithm for Continuous and Noninvasive Cuff-Less Blood Pressure Estimation

Extensive research has been performed on continuous and noninvasive cuff-less blood pressure (BP) measurement using artificial intelligence algorithms. This approach involves extracting certain features from physiological signals, such as ECG, PPG, ICG, and BCG, as independent variables and extracting features from arterial blood pressure (ABP) signals as dependent variables and then using machine-learning algorithms to develop a blood pressure estimation model based on these data. The greatest challenge of this field is the insufficient accuracy of estimation models. This paper proposes a novel blood pressure estimation method with a clustering step for accuracy improvement. The proposed method involves extracting pulse transit time (PTT), PPG intensity ratio (PIR), and heart rate (HR) features from electrocardiogram (ECG) and photoplethysmogram (PPG) signals as the inputs of clustering and regression, extracting systolic blood pressure (SBP) and diastolic blood pressure (DBP) features from ABP signals as dependent variables, and finally developing regression models by applying gradient boosting regression (GBR), random forest regression (RFR), and multilayer perceptron regression (MLP) on each cluster. The method was implemented using the MIMIC-II data set with the silhouette criterion used to determine the optimal number of clusters. The results showed that because of the inconsistency, high dispersion, and multitrend behavior of the extracted features vectors, the accuracy can be significantly improved by running a clustering algorithm and then developing a regression model on each cluster and finally weighted averaging of the results based on the error of each cluster. When implemented with 5 clusters and GBR, this approach yielded an MAE of 2.56 for SBP estimates and 2.23 for DBP estimates, which were significantly better than the best results without clustering (DBP: 6.27, SBP: 6.36).

Concatenated Convolutional Neural Network Model for Cuffless Blood Pressure Estimation Using Fuzzy Recurrence Properties of PPG Signals

Due to the importance of continuous monitoring of blood pressure (BP) in controlling hypertension, the topic of cuffless blood pressure (BP) estimation has been widely studied in recent years. A most important approach is to explore the nonlinear mapping between the recorded peripheral signals and the BP values which is usually conducted by deep neural networks. Because of the sequence-based pseudo periodic nature of peripheral signals such as photoplethysmogram (PPG), a proper estimation model needed to be equipped with the 1-dimensional (1-D) and recurrent layers. This, in turn, limits the usage of 2-dimensional (2-D) layers adopted in convolutional neural networks (CNN) for embedding spatial information in the model. In this study, considering the advantage of chaotic approaches, the recurrence characterization of peripheral signals was taken into account by a visual 2-D representation of PPG in phase space through fuzzy recurrence plot (FRP). FRP not only provides a beneficial framework for capturing the spatial properties of input signals but also creates a reliable approach for embedding the pseudo periodic properties to the neural models without using recurrent layers. Moreover, this study proposes a novel deep neural network architecture that combines the morphological features extracted simultaneously from two upgraded 1-D and 2-D CNNs capturing the temporal and spatial dependencies of PPGs in systolic and diastolic BP estimation. The model has been fed with the 1-D PPG sequences and the corresponding 2-D FRPs from two separate routes. The performance of the proposed framework was examined on the well-known public dataset, namely, Multi-Parameter Intelligent in Intensive Care II. Our scheme is analyzed and compared with the literature in terms of the requirements of the standards set by the British Hypertension Society (BHS) and the Association for the Advancement of Medical Instrumentation (AAMI). The proposed model met the AAMI requirements, and it achieved a grade of A as stated by the BHS standard. In addition, its mean absolute errors (MAE) and standard deviation for both systolic and diastolic blood pressure estimations were considerably low, 3.05±5.26 mmHg and 1.58±2.6 mmHg, in turn.

Blood Pressure Estimation from Photoplethysmography with Motion Artifacts Using Long Short Term Memory Network

Continuous measurement of the Blood Pressure (BP) is important in hypertensive patientsand elderly population. Traditional cuff based methods are difficult to use since it is uncomfortable towear a cuff throughout the day. A more suitable method is to estimate the BP using the Photoplethysmography(PPG) signal. However, it is difficult to estimate a BP when the PPG is corrupted withMotion Artifacts (MAs). In this paper, Long Short Term Memory (LSTM) an extension of RecurrentNeural Networks (RNN) is used used to improve the accuracy of the estimation of the BP from thecorrupted PPG. It shows that an accuracy of 97.86 is achieved.

Attention Mechanism-Based Convolutional Long Short-Term Memory Neural Networks to Electrocardiogram-Based Blood Pressure Estimation

Monitoring people’s blood pressure can effectively prevent blood pressure-related diseases. Therefore, providing a convenient and comfortable approach can effectively help patients in monitoring blood pressure. In this study, an attention mechanism-based convolutional long short-term memory (LSTM) neural network is proposed to easily estimate blood pressure. To easily and comfortably estimate blood pressure, electrocardiogram (ECG) and photoplethysmography (PPG) signals are acquired. To precisely represent the characteristics of ECG and PPG signals, the signals in the time and frequency domain are selected as the inputs of the proposed NN structure. To automatically extract the features, the convolutional neural networks (CNNs) are adopted as the first part of neural networks. To identify the meaningful features, the attention mechanism is used in the second part of neural networks. To model the characteristic of time series, the long short-term memory (LSTM) is adopted in the third part of neural networks. To integrate the information of previous neural networks, the fully connected networks are used to estimate blood pressure. The experimental results show that the proposed approach outperforms CNN and CNN-LSTM and complies with the Association for the Advancement of Medical Instrumentation standard.

New Method to Estimate Central Systolic Blood Pressure From Peripheral Pressure: A Proof of Concept and Validation Study

Objective: The non-invasive estimation of central systolic blood pressure (cSBP) is increasingly performed using new devices based on various pulse acquisition techniques and mathematical analyses. These devices are most often calibrated assuming that mean (MBP) and diastolic (DBP) BP are essentially unchanged when pressure wave travels from aorta to peripheral artery, an assumption which is evidence-based. We tested a new empirical formula for the direct central blood pressure estimation of cSBP using MBP and DBP only (DCBP = MBP2/DBP).Methods and Results: First, we performed a post-hoc analysis of our prospective invasive high-fidelity aortic pressure database (n = 139, age 49 ± 12 years, 78% men). The cSBP was 146.0 ± 31.1 mmHg. The error between aortic DCBP and cSBP was −0.9 ± 7.4 mmHg, and there was no bias across the cSBP range (82.5–204.0 mmHg). Second, we analyzed 64 patients from two studies of the literature in whom invasive high-fidelity pressures were simultaneously obtained in the aorta and brachial artery. The weighed mean error between brachial DCBP and cSBP was 1.1 mmHg. Finally, 30 intensive care unit patients equipped with fluid-filled catheter in the radial artery were prospectively studied. The cSBP (115.7 ± 18.2 mmHg) was estimated by carotid tonometry. The error between radial DCBP and cSBP was −0.4 ± 5.8 mmHg, and there was no bias across the range.Conclusion: Our study shows that cSBP could be reliably estimated from MBP and DBP only, provided BP measurement errors are minimized. DCBP may have implications for assessing cardiovascular risk associated with cSBP on large BP databases, a point that deserves further studies.

Featureless Blood Pressure Estimation Based on Photoplethysmography Signal Using CNN and BiLSTM for IoT Devices

Continuous blood pressure (BP) acquisition is critical to health monitoring of an individual. Photoplethysmography (PPG) is one of the most popular technologies in the last decade used for measuring blood pressure noninvasively. Several approaches have been carried out in various ways to utilize features extracted from PPG. In this study, we develop a continuous systolic and diastolic blood pressure (SBP and DBP) estimation mechanism without the need for any feature engineering. The raw PPG signal only got preprocessed before being fed to our model which mainly consists of one-dimensional convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) network. We evaluate the resulting SBP and DBP value by the root-mean-squared error (RMSE) and mean absolute error (MAE). This study addresses the effectiveness of the model by outperforming the previous feature engineering-based methods. We achieve RMSE of 11.503 and 6.525 for SBP and DBP, respectively, and MAE of 7.849 and 4.418 for SBP and DBP, respectively. The proposed method is expected to substantially enhance the current efficiency of healthcare IoT (Internet of Things) devices in BP monitoring using PPG signals only.

Cuff-Less Blood Pressure Estimation from Electrocardiogram and Photoplethysmography Based on VGG19-LSTM Network

In recent years, studies have found that the hierarchical neural network with LSTM network has higher accuracy than another feature engineering. Therefore, this paper first tries to build a multi-stage blood pressure estimation model through VGG19 and LSTM network. Based on the time node of the R wave peak in the QRS waveform in ECG, VGG19 is used to extract various higher-dimensional and rich life characteristics in the PPG signal segment by heartbeat as the unit and focus on processing the dynamics of SBP and DBP Correlation, finally use the LSTM model to extract the time dependence of the vital signs. Results: Experiments show that compared with similar multi-stage models, this model has higher accuracy. The performance of this method meets the Advancement of Medical Instrumentation (AAMI) standard and reaches the A level of the British Hypertension Society (BHS) standard. The average error and standard deviation of the estimated value of SBP were 1.7350 4.9606 mmHg, and the average error and standard deviation of the estimated value of DBP were 0.7839 2.7700 mmHg, respectively.