Search

Continuous blood pressure (BP) monitoring is crucial for individual health management, yet the significant inter-individual variations among patients pose challenges to achieving precision medicine. In response to this issue, we propose a parallel cross-hybrid architecture that integrates a convolutional neural network backbone and a Mix-Transformer backbone. This model, grounded in multi-view physiological signals and personalized fine-tuning strategies, aims to estimate BP, facilitating the capture of physiological information across diverse receptive fields and enhancing network expressive capabilities. Our proposed architecture exhibits superior performance in estimating systolic blood pressure and diastolic blood pressure, with average absolute errors of 3.94 mmHg and 2.24 mmHg, respectively. These results surpass existing baseline models and align with the standards set by the British Hypertension Society, the Association for the Advancement of Medical Instrumentation, and the Institute of Electrical and Electronics Engineers for BP measurement. Additionally, this study explores a personalized model fine-tuning strategy by adjusting specific layers and incorporating individual information, presenting an optimal solution. The model's generalization ability is validated through transfer learning across databases (public and self-made). To enhance the proposed architecture's usability in wearable devices, this study employs a knowledge distillation strategy for model lightweighting, with preliminary application in our designed real-time BP estimation system. This study provides an efficient and accurate solution for personalized BP estimation, exhibiting broad potential applications. ● Parallel cross-hybrid architecture captures local and global information. ● Proposing personalized fine-tuning strategy for optimized performance. ● Underscoring significance of individual information in fine-tuning. ● Cross-database validation conducted on three datasets totaling 1556 h. ● Utilizing knowledge distillation for lightweight model and reliability. [ABSTRACT FROM AUTHOR]

High Blood Pressure (BP) is one of the most dangerous and widespread diseases due to which uncontrolled BP increases the risk of health problems that affects many body organs. Unfortunately, accurate BP measurements require several medical devices and a specialist person who has experience in BP measurement and measured in separate times. Thus, this paper proposes a simple calibration-free method to estimate BP by training BP and Photoplethysmography (PPG) data signals on a machine learning (ML) regression model. The proposed method overcomes drawbacks of BP measurement accuracy and provides enough capability for reliable and calibration-free BP estimation. The obtained results clarify that the error standard deviation (STD) is about 5.3 and 6.4 mmHg of systolic pressure (SP) and diastolic pressure (DP), respectively. In addition, the mean absolute error (MAE) is about 4.2 and 4.5 mmHg of SP and DP, respectively. These results achieve grade "A" for both SP and DP based on the Britain Hypertension Society (BHS) standard. Finally, the results of BP estimation regression models meet the International Organization for Standardization (ISO) requirements for non-invasive BP devices and consequently they can be utilized later in life experiments. [ABSTRACT FROM AUTHOR]

Arterial blood pressure (ABP) waveforms indicate the efficiency with which a patient's blood responds to changes in the arterial flow. ABP waveforms can be used to analyze the cardiovascular health of patients, including heart rate analysis, stress analysis, and cardiovascular disease diagnosis. However, obtaining the ABP waveform is more difficult than recording the electrocardiography (ECG) and photoplethysmography (PPG) signals. Several studies have focused on the reconstruction of the ABP waveform by recombining bio-signals. Reconstructing ABP waveforms is considered a major challenge because of signals being distorted by waveform destruction, owing to the normalization and standardization of the input ABP waveform. This paper presents a model that can simultaneously output blood pressure estimation and ABP waveforms using the raw ABP signal as the input. Herein, the squeeze-and-excitation network (SE-Net) is coupled with the multi-task learning architecture. Three signals, namely, the ECG, PPG, and ECG–PPG, were trained as feature vectors using different variants of the U-Net model, and the results are compared. Additionally, we introduce a novel method for incorporating white Gaussian noise at different signal-to-noise ratios (SNRs) to augment the training data. The objective of the proposed approach is to evaluate the ABP signal reconstruction capability of the SE-Net at various SNR levels and analyze the overall performance and robustness of the model. In the case of systolic blood pressure, the root mean square error (RMSE) of the PPG-based values is 2.58 mmHg, and the Pearson correlation coefficient is r = 0.92 (p ≤ 0.001). In the case of diastolic blood pressure(DBP), the RMSE was 3.35 mmHg, and the Pearson correlation coefficient was r = 0.89 (p ≤ 0.001). The results indicate the potential for replacing ECG signals with PPG signals to overcome the constraints of optimizing the non-invasive reconstruction of ABP waveforms using SE-Net. Furthermore, we demonstrate that the SE-Net-combined multi-task learning architecture model can simultaneously perform blood pressure estimation and output ABP waveforms without damaging the raw signal. [ABSTRACT FROM AUTHOR]

• Measurement method exploiting compressed sensing. • Pulse wave estimation. • Non-invasive blood pressure measurement. • Radial artery pulse wave at wrist. In this paper, a Compressive Sampling (CS) based measurement method of the Bio-Impedance (Bio-Z) variation at the wrist, due to the blood flow inside of radial artery, is presented, allowing to estimate the pulse wave. The method uses as stimulus a known pulse-like waveform (e.g., a pseudo-random sequence) and it compressively samples the resulting signal with the goal of obtaining the impulse response variation of the wrist Bio-Z. The mathematical steps describing the method, the 3D electrical model of the wrist used for simulations as well as the experimental investigations are reported. The experimental results show that the proposed measurement method could be successful used to estimate the radial artery pulse wave, feature that could be further used in Blood Pressure computation. [ABSTRACT FROM AUTHOR]

[Display omitted] • The paper extracts features from PPG and its derivatives, while also incorporating statistical information from subjects. All 172 features from 10 dimensions are provided in Appendix A. • The SHAP algorithm is utilized to enhance the interpretability of the feature optimization process. • The optimized LightGBM model is combined with SHAP to calculate the SHAP values in each feature. • The paper proposes an interpretable method for feature importance ranking. The most appropriate number of features is obtained based on the performance of the model and feature importance. Appendix B provides the ranking of all features. • The results show that all evaluation metrics of the model improved after feature optimisation, achieving accurate SBP and DBP estimation. Blood pressure (BP) estimation based on photoplethysmography (PPG) signals enables continuous and comfortable BP measurement, which is important for the clinical management of hypertension. The purpose of this study is to propose a novel and interpretable feature optimization method to improve the performance of the PPG-based model for BP estimation. The PPG signals of 152 subjects were selected from a public database. Feature detection was performed on the signals after FIR band-pass filtering. A total of 172 features extracted from ten feature dimensions were used to construct a feature set, including features from the raw PPG signals, PPG derivative signals, and statistical information. Light Gradient Boosting Machine (LightGBM) was used as this work's prediction model. To further improve the performance of the LightGBM model, Shapley Additive Explanations (SHAP) were utilized for feature optimization to achieve the purpose. The number of features corresponding to the lowest model error was defined as the optimal feature set, and this was utilized for training the model to obtain BP estimation. Compared to the validated BP, the mean and standard deviation (SD) of the estimation errors for systolic blood pressure (SBP) and diastolic blood pressure (DBP) were −0.73 ± 6.50 mmHg and 0.37 ± 3.83 mmHg, respectively. According to the British Hypertension Society (BHS) criteria, SBP and DBP are within the range of B and A grades, respectively. We propose a novel feature optimization method to reduce the feature dimension for BP estimation. The algorithm can effectively prevent overfitting and improve the model's performance. [ABSTRACT FROM AUTHOR]

A variety of oscillometric algorithms have been recently proposed in the literature for estimation of blood pressure (BP). However, these algorithms possess specific strengths and weaknesses that should be taken into account before selecting the most appropriate one. In this paper, we propose a fusion method to exploit the advantages of the oscillometric algorithms and circumvent their limitations. The proposed fusion method is based on the computation of the weighted arithmetic mean of the oscillometric algorithms estimates, and the weights are obtained using a Bayesian approach by minimizing the mean square error. The proposed approach is used to fuse four different oscillometric blood pressure estimation algorithms. The performance of the proposed method is evaluated on a pilot dataset of 150 oscillometric recordings from 10 subjects. It is found that the mean error and standard deviation of error are reduced relative to the individual estimation algorithms by up to 7 mmHg and 3 mmHg in estimation of systolic pressure, respectively, and by up to 2 mmHg and 3 mmHg in estimation of diastolic pressure, respectively. [ABSTRACT FROM AUTHOR]

• In the proposed scalable MSF block, parallel convolution layers can help obtain features of different receptive fields and then they were integrated to form multi-scale representation by the attention mechanism. • Depthwise separable convolution borrowed from the MobileNet was introduced to keep the balance between parameter number and computation complexity. The above two advantages not only improved the richness of extracted features but also ensured the computation latency in real application. • Multi-task learning was introduced to help backbone network obtain more robust representation. Task-specific subnetworks can refine the feature from the shared backbone network into the features more suitable for SBP and DBP estimation task, respectively. Multi-scale fusion backbone network combined with the task-specific subnetworks can improve BP estimation accuracy. The continuous measurement of blood pressure (BP) plays an important role in preventing cardiovascular diseases. However, common cuff-based devices with cumbersome operations are difficult to realize continuous BP monitoring. We propose a continuous BP estimation method based on the end-to-end multi-scale fusion and multi-task learning neural network (MSF-MTLNet). It can use the 8-second PPG segment and its derivatives as input and automatically learn their multi-scale features to improve BP accuracy. The proposed method implements feature extraction by adaptively fusing multiple convolution kernels with different sizes through the attention mechanism. Simultaneously, multi-task learning was introduced to discover task-relevant features. A total of 277,600 segments from 1825 patients in the University of California, Irvine database are used for experiments. They are divided into the independent training set, validation set, and test set according to the ratio of 8:1:1 in an inter-subject manner. The mean and standard deviation of estimation error for systolic blood pressure and diastolic blood pressure are 0.97 ± 8.87 mmHg and 0.55 ± 4.23 mmHg, respectively, which outperforms the current cutting-edge method. Our approach almost meets the Association for the Advancement of Medical Instrumentation standard. Considering the British Hypertension Society standards, it achieves an 'A' grade for DBP estimation and a 'B' grade for SBP estimation. Experimental results show that MSF-MTLNet can obtain promising precision in cuffless and continuous BP estimation. [ABSTRACT FROM AUTHOR]

• The multi-filter to multi-channel approach is proposed for preprocessing PPG and ECG signal. • The proposed method (MLP-BP) is a novel framework based on MLP-Mixer for estimating BP task. • gMLP-BP and MLPlstm-BP are both end-to-end pipelines without any handcrafted feature extraction. • The performance of three distinct input signal (PPG, ECG, or PPG & ECG) are investigated. • Experiments demonstrate that MLP-BP attains excellent results compared with SOTA methods. High blood pressure (BP) is a major source of death worldwide as it slows down the flow of blood and oxygen, and leads to various chronic diseases such as chest pain (angina), heart disease and heart failure. Therefore, regular measurement and monitoring of BP is an essential element of the home healthy settings, especially for the elderly. In this study, a novel deep neural network (called MLP-BP, which including gMLP-BP and MLPlstm-BP) adapted from MLP-Mixer is proposed to estimate BP from plethysmography (PPG) and electrocardiograph (ECG) signal. More precisely, a novel multi-filter to multi-channel (MFMC) is presented for preprocessing ECG and PPG signals, namely using various filters and filtering parameters to handle with ECG and PPG, and integrating the filtered bio-signals into multi-channel data. Then, the multi-channel data is fed into the proposed methods to estimate blood pressure directly. The up-to-date concept MLP-Mixer is employed in the proposed frameworks, which are both end-to-end pipelines without any handcrafted feature extraction operation. MLPlstm-BP (gMLP-BP) achieves the predicted diastolic BP with a mean absolute error (MAE) of 2.13 (2.47) mmHg, and with a standard deviation (SD) of 3.07 (3.52) mmHg; those of systolic BP is an MAE of 3.52 (4.18) mmHg, and a SD of 5.10 (5.87) mmHg on the MIMIC II dataset. In addition, the testing results are all meet the highest level of the Association for the Advancement of Medical Instrumentation (AAMI) and British Hypertension Society (BHS). Extensive experiments demonstrate that the proposed methods attain competitive results over state-of-the-art (SOTA) learning-based pipelines. [ABSTRACT FROM AUTHOR]

Blood pressure measurement and continuous control are essential for heart and blood pressure patients. Therefore, continuous blood pressure measurement from these patients is required. In this paper, a novel hybrid prediction method combining Gaussian process regression (GPR) and feature extraction stage has been proposed and then applied to the estimation of blood pressure from cuff Oscillometric waveforms (or signals). First of all, 27 features including time, chaotic, and frequency domain have been extracted from these waveforms to detect the systolic blood pressure (SBP) and diastolic blood pressure (DBP) automatically. As the second stage in the proposed method, three different GPR methods comprising Exponential GPR, Matern 5/2 GPR, and Rational Quadratic GPR, have been used to estimate the SBP and DBP values based the extracted 27 features. As the performance measures, we have used seven different metrics including MAE (mean absolute error), MSE (mean square error), RMSE (root mean square error), R2, IA (index of agreement), and MAPE (mean absolute percentage error) for evaluation of the proposed methods concerning estimation performance of SBP and DBP values from cuff Oscillometric waveforms. The obtained MAPE values for Exponential GPR, Matern 5/2 GPR, and Rational Quadratic GPR in the estimation of SBP values from cuff Oscillometric signals are 0.1136, 0.2286, and 0.1745, respectively. The obtained MAPE values for Exponential GPR, Matern 5/2 GPR and Rational Quadratic GPR in the estimation of DBP values from cuff Oscillometric signals are 0.2878, 0.4220, and 0.4150, respectively. The experimental results have demonstrated that the best-proposed hybrid model is the combination of the Exponential GPR and the feature extraction stage for the estimation of both SBP and DBP values. The proposed method could be safely used in the medical blood pressure measurement systems in the hospital and clinics. [ABSTRACT FROM AUTHOR]

Blood pressure measurement and prediction is an important condition for heart patients and people with heart problems and should be kept under constant control. In this study, based on the oscillometric waveform obtained from individuals using a cuff, the oscillometric waveforms are divided into three periods. These periods are; the first period from the starting point to the systolic blood pressure (SBP), the second period is between systolic blood pressure (SBP) and diastolic blood pressure (DBP), and the third period is between diastolic blood pressure (DBP) and end of the waveform. In the dataset used, the attributes obtained from the oscillometric wave envelope were subtracted for each pulse. On the dataset, the attributes of the beat corresponding to the systolic pressure point are labeled 1, and the attributes of the beat corresponding to the diastolic pressure point are labeled with 2. Other beats are labeled with 0. In the study, the dataset was first re-labeled. Systolic beats were labeled with 1, beats before systolic point, 2 with systolic, diastolic point including diastolic point, and 3 with a diastolic point. After re-labeling, 350 measurements, 300 measurements were divided into training and 50 measurements were divided into test data subset. Classifiers were trained with 300 subsets and the classifier model was produced. With the generated model, the classification of the pulse sequences in the test data subsets was performed. In the found label series, the first 1 to 2 label was marked as the systolic pressure point and the last 2 to 3 labels as the diastolic pressure point and the corresponding cuff pressures were estimated as systolic and diastolic pressure values. By classifying these periods, the systolic blood pressure (SBP) and diastolic blood pressure (DBP) values have been estimated using three classifier algorithms including k-nearest neighbor (kNN), weighted k-nearest neighbor (WkNN), and Bagged Trees algorithms. To evaluate the performance of the prediction algorithms, four different performance metrics comprising MAE (mean absolute error), MSE (mean square error), RMSE (root mean square error), and R2 have been used. For the estimation of SBP values using the kNN algorithm, weighted kNN, and Bagged Trees, the obtained MAEs are 3.590, 3.520, and 4.499, respectively. As for the estimation of DBP values using kNN algorithm, weighted kNN and, Bagged Trees, the obtained MAEs are 11.077, 11.032, and 13.069, respectively. The obtained results demonstrated that the proposed method could be used in the blood pressure estimation as the new approach. [ABSTRACT FROM AUTHOR]

This work presents a system of continuously monitoring blood pulse waves that is integrated with a highly sensitive tactile sensing array and tension sensor. The sensing elements for the array and tension sensor consist of highly sensitive conductive polymer films based on multi-wall carbon nanotube (MWCNT) patterned with microdome structures. The tactile sensing array is designed in a 3 × 1 linear configuration, which greatly facilitates aligning the sensing array with the radial artery during measurement. The primary purpose of the tension sensor is to determine the optimal, most comfortable conditions for obtaining stable, clear pulse waves. The measured results show that the proposed sensing element is of high sensitivity (−0.438 kPa−1). In addition, the mechanical model for the arterial tonometry method was derived and the linear regression analysis technique was used to calculate the parameters of the model for estimating blood pressure. The results of blood pressure estimation showed that the R 2 values were 0.91 and 0.70 for systolic blood pressures and diastolic blood pressures, respectively. Unlabelled Image • This work presents a continuously blood pulse wave monitoring system that is integrated with a highly sensitive tactile sensing array and tension sensor. • The tactile sensing array is designed in a 3 × 1 linear configuration, which greatly facilitates aligning the sensing array with the radial artery during measurement. • The proposed tension sensor detects the optimal conditions for obtaining stable pulse waves. [ABSTRACT FROM AUTHOR]