Search Results (28)

Traditional cuff-based blood pressure (BP) monitoring methods provide only intermittent readings, while invasive alternatives pose clinical risks. Recent studies have demonstrated feasibility of estimating continuous non-invasive cuff-less BP using photoplethysmogram (PPG) signals alone. However, existing approaches rely on complex manual feature engineering and/or multiple model architectures, resulting in inefficient epoch training numbers and limited performance. This research proposes cBP-Tnet, an efficient single-channel and model multi-task Transformer network designed for PPG signal automatic feature extraction. cBP-Tnet employed specialized hyperparameters—integrating adaptive Kalman filtering, outlier elimination, signal synchronization, and data augmentation—leveraging multi-head self-attention and multi-task learning strategies to identify subtle and shared waveform patterns associated with systolic blood pressure (SBP) and diastolic blood pressure (DBP). We used the MIMIC-II public dataset (500 patients with 202,956 samples) for experimentation. Results showed mean absolute errors of 4.32 mmHg for SBP and 2.18 mmHg for DBP. For the first time, both SBP and DBP meet the Association for the Advancement of Medical Instrumentation’s international standard (<5 mmHg, >85 subjects). Furthermore, the network efficiently reduces the epoch training number by 13.67% when compared to other deep learning methods. Thus, this establishes cBP-Tnet’s potential for integration into wearable and home-based healthcare devices with continuous non-invasive cuff-less blood pressure monitoring. Full article

Cuffless continuous blood pressure (BP) monitoring is essential for personal health management. However, its accuracy is challenged by the diversity and heterogeneity of physiological data sources. We propose a multi-source feature selection framework based on Markov blanket theory and the concept of causal invariance. We extracted 218 BP-related photoplethysmography (PPG) features from three heterogeneous datasets (differing in subject population, acquisition devices, and methods) and constructed a causal feature set using the Multi-Dataset Stable Feature Selection via Ensemble Markov Blanket (MDSFS-EMB) algorithm. BP estimation was then performed using four machine learning models. The MDSFS-EMB algorithm integrated PPFS and HITON-MB, enabling adaptability to different data scales and distribution scenarios. It employed Gaussian Copula Mutual Information, which was robust to outliers and capable of modeling nonlinear relationships. To validate the effectiveness of the selected feature set, we conducted experiments using an independent external validation dataset and explored the impact of data segmentation strategies on model prediction outcomes. The results demonstrated that the MDSFS-EMB algorithm has advantages in feature selection efficiency, prediction accuracy, and generalization capability. This study innovatively explores the causal relationships between PPG features and BP across multiple data sources, providing a clinically applicable approach for cuffless BP estimation. Full article

Nocturnal monitoring of continuous, cuffless blood pressure (BP) can unleash a whole new world for the prognostication of cardiovascular and other diseases due to its strong predictive capability. Nevertheless, the lack of an accurate and reliable method, primarily due to confounding variables, has prevented its widespread clinical adoption. Herein, we demonstrate how optimized machine learning using the Catch-22 features, when applied to the photoplethysmogram waveform and personalized with direct BP data through transfer learning, can accurately estimate systolic and diastolic BP. After training with a hemodynamically compromised VitalDB “calibration-free” dataset (n = 1293), the systolic and diastolic BP tested on a distinct VitalDB dataset that met AAMI criteria (n = 116) had acceptable error biases of −1.85 mm Hg and 0.11 mm Hg, respectively [within the 5 mm Hg IEC/ANSI/AAMI 80601-2-30, 2018 standard], but standard deviation (SD) errors of 19.55 mm Hg and 11.55 mm Hg, respectively [exceeding the stipulated 8 mm Hg limit]. However, personalization using an initial calibration data segment and subsequent use of transfer learning to fine-tune the pretrained model produced acceptable mean (−1.31 mm Hg and 0.10 mm Hg) and SD (7.91 mm Hg and 4.59 mm Hg) errors for systolic and diastolic BP, respectively. Levene’s test for variance found that the personalization method significantly outperformed (p < 0.05) the calibration-free method, but there was no difference between three machine learning methods. Optimized multimodal Catch-22 features, coupled with personalization, demonstrate great promise in the clinical adoption of continuous, cuffless blood pressure estimation in applications such as nocturnal BP monitoring. Full article

(1) Background: Blood pressure (BP) variability is an important risk factor for cardiovascular diseases. Still, existing BP monitoring methods often require periodic cuff-based measurements, raising concerns about their accuracy and convenience. This study aims to develop a subject-independent, cuff-less BP estimation method using finger and toe photoplethysmography (PPG) signals combined with an electrocardiogram (ECG) without the need for an initial cuff-based measurement. (2) Methods: A customized measurement system was used to record 80 readings from human subjects. Fifteen features with the highest dependency on the reference BP, including time and morphological characteristics of PPG and subject information, were analyzed. A multivariate regression model was employed to estimate BP. (3) Results: The results showed that incorporating toe PPG signals improved the accuracy of BP estimation, reducing the mean absolute error (MAE). Using both finger and toe PPG signals resulted in an MAE of 9.63 ± 12.54 mmHg for systolic BP and 6.76 ± 8.38 mmHg for diastolic BP, providing the lowest MAE compared to previous methods. (4) Conclusions: This study is the first to integrate toe PPG for more accurate BP estimation and proposes a method that does not require an initial cuff-based BP measurement, offering a promising approach for non-invasive, continuous BP monitoring. Full article

This paper presents a method to improve confidence-interval (CI) estimation using individual uncertainty measures and weighted feature decisions for cuff-less blood-pressure (BP) measurement. We obtained uncertainty using Gaussian process regression (GPR). The CI obtained from the GPR model is computed using the distribution of BP estimates, which provides relatively wide CIs. Thus, we proposed a method to obtain improved CIs for individual subjects by applying bootstrap and uncertainty methods using the cuff-less BP estimates of each subject obtained through GPR. This study also introduced a novel method to estimate cuff-less BP with high fidelity by determining highly weighted features using weighted feature decisions. The standard deviation of the proposed method’s mean error is 2.94 mmHg and 1.50 mmHg for systolic blood pressure (SBP) and (DBP), respectively. The mean absolute error results were obtained by weighted feature determination combining GPR and gradient boosting algorithms (GBA) for SBP (1.46 mmHg) and DBP (0.69 mmHg). The study confirmed that the BP estimates were within the CI based on the test samples of almost all subjects. The weighted feature decisions combining GPR and GBA were more accurate and reliable for cuff-less BP estimation. Full article

Blood pressure (BP) measurement is a major physiological information for people with cardiovascular diseases, such as hypertension, heart failure, and atherosclerosis. Moreover, elders and patients with kidney disease and diabetes mellitus also are suggested to measure their BP every day. The cuffless BP measurement has been developed in the past 10 years, which is comfortable to users. Now, ballistocardiogram (BCG) and impedance plethysmogram (IPG) could be used to perform the cuffless BP measurement. Thus, the aim of this study is to realize edge computing for the BP measurement in real time, which includes measurements of BCG and IPG signals, digital signal process, feature extraction, and BP estimation by machine learning algorithm. This system measured BCG and IPG signals from a bodily weight-fat scale with the self-made circuits. The signals were filtered to reduce the noise and segmented by 2 s. Then, we proposed a flowchart to extract the parameter, pulse transit time (PTT), within each segment. The feature included two calibration-based parameters and one calibration-free parameter was used to estimate BP with XGBoost. In order to realize the system in STM32F756ZG NUCLEO development board, we limited the hyperparameters of XGBoost model, including maximum depth (max_depth) and tree number (n_estimators). Results show that the error of systolic blood pressure (SBP) and diastolic blood pressure (DBP) in server-based computing are 2.64 ± 9.71 mmHg and 1.52 ± 6.32 mmHg, and in edge computing are 2.2 ± 10.9 mmHg and 1.87 ± 6.79 mmHg. This proposed method significantly enhances the feasibility of bodily weight-fat scale in the BP measurement for effective utilization in mobile health applications. Full article

It would be useful to develop a reliable method for the cuffless measurement of blood pressure (BP), as such a method could be made available anytime and anywhere for the effective screening and monitoring of arterial hypertension. The purpose of this study is to evaluate blood pressure measurements through a CardioQVARK device in clinical practice in different patient groups. Methods: This study involved 167 patients aged 31 to 88 years (mean 64.2 ± 7.8 years) with normal blood pressure, high blood pressure, and compensated high blood pressure. During each session, three routine blood pressure measurements with intervals of 30 s were taken using a sphygmomanometer with an appropriate cuff size, and the mean value was selected for comparison. The measurements were carried out by two observers trained at the same time with a reference sphygmomanometer using a Y-shaped connector. In the minute following the last cuff-based measurements, an electrocardiogram (ECG) with an I-lead and a photoplethysmocardiogram were recorded simultaneously for 3 min with the CardioQVARK device. We compared the systolic and diastolic BP obtained from a cuff-based mercury sphygmomanometer and smartphone-case-based BP device: the CardioQVARK monitor. A statistical analysis plan was developed using the IEEE Standard for Wearable Cuffless Blood Pressure Devices. Bland–Altman plots were used to estimate the precision of cuffless measurements. Results: The mean difference between the values defined by CardioQVARK and the cuff-based sphygmomanometer for systolic blood pressure (SBP) was 0.31 ± 3.61, while that for diastolic blood pressure (DBP) was 0.44 ± 3.76. The mean absolute difference (MAD) for SBP was 3.44 ± 2.5 mm Hg, and that for DBP was 3.21 ± 2.82 mm Hg. In the subgroups, the smallest error (less than 3 mm Hg) was observed in the prehypertension group, with a slightly larger error (up to 4 mm Hg) found among patients with a normal blood pressure and stage 1 hypertension. The largest error was found in the stage 2 hypertension group (4–5.5 mm Hg). The largest error was 4.2 mm Hg in the high blood pressure group. We, therefore, did not record an error in excess of 7 mmHg, the upper boundary considered acceptable in the IEEE recommendations. We also did not reach a mean error of 5 mmHg, the upper boundary considered acceptable according to the very recent ESH recommendations. At the same time, in all groups of patients, the systolic blood pressure was determined with an error of less than 5 mm Hg in more than 80% of patients. While this study shows that the CardioQVARK device meets the standards of IEEE, the Bland–Altman analysis indicates that the cuffless measurement of diastolic blood pressure has significant bias. The difference was very small and unlikely to be of clinical relevance for the individual patient, but it may well have epidemiological relevance on a population level. Therefore, the CardioQVARK device, while being worthwhile for monitoring patients over time, may not be suitable for screening purposes. Cuffless blood pressure measurement devices are emerging as a convenient and tolerable alternative to cuff-based devices. However, there are several limitations to cuffless blood pressure measurement devices that should be considered. For instance, this study showed a high proportion of measurements with a measurement error of <5 mmHg, while detecting a small, although statistically significant, bias in the measurement of diastolic blood pressure. This suggests that this device may not be suitable for screening purposes. However, its value for monitoring BP over time is confirmed. Furthermore, and most importantly, the easy measurement method and the device portability (integrated in a smartphone) may increase the self-awareness of hypertensive patients and, potentially, lead to an improved adherence to their treatment. Conclusion: The cuffless blood pressure technology developed in this study was tested in accordance with the IEEE protocol and showed great precision in patient groups with different blood pressure ranges. This approach, therefore, has the potential to be applied in clinical practice. Full article

Accurately measuring blood pressure (BP) is essential for maintaining physiological health, which is commonly achieved using cuff-based sphygmomanometers. Several attempts have been made to develop cuffless sphygmomanometers. To increase their accuracy and long-term variability, machine learning methods can be applied for analyzing photoplethysmogram (PPG) signals. Here, we propose a method to estimate the BP during exercise using a cuffless device. The BP estimation process involved preprocessing signals, feature extraction, and machine learning techniques. To ensure the reliability of the signals extracted from the PPG, we employed the skewness signal quality index and the RReliefF algorithm for signal selection. Thereafter, the BP was estimated using the long short-term memory (LSTM)-based neural network. Seventeen young adult males participated in the experiments, undergoing a structured protocol composed of rest, exercise, and recovery for 20 min. Compared to the BP measured using a non-invasive voltage clamp-type continuous sphygmomanometer, that estimated by the proposed method exhibited a mean error of 0.32 ± 7.76 mmHg, which is equivalent to the accuracy of a cuff-based sphygmomanometer per regulatory standards. By enhancing patient comfort and improving healthcare outcomes, the proposed approach can revolutionize BP monitoring in various settings, including clinical, home, and sports environments. Full article

Blood pressure (BP) is an essential physiological indicator to identify and determine health status. Compared with the isolated BP measurement conducted by traditional cuff approaches, cuffless BP monitoring can reflect the dynamic changes in BP values and is more helpful to evaluate the effectiveness of BP control. In this paper, we designed a wearable device for continuous physiological signal acquisition. Based on the collected electrocardiogram (ECG) and photoplethysmogram (PPG), we proposed a multi-parameter fusion method for noninvasive BP estimation. An amount of 25 features were extracted from processed waveforms and Gaussian copula mutual information (MI) was introduced to reduce feature redundancy. After feature selection, random forest (RF) was trained to realize systolic BP (SBP) and diastolic BP (DBP) estimation. Moreover, we used the records in public MIMIC-III as the training set and private data as the testing set to avoid data leakage. The mean absolute error (MAE) and standard deviation (STD) for SBP and DBP were reduced from 9.12 ± 9.83 mmHg and 8.31 ± 9.23 mmHg to 7.93 ± 9.12 mmHg and 7.63 ± 8.61 mmHg by feature selection. After calibration, the MAE was further reduced to 5.21 mmHg and 4.15 mmHg. The result showed that MI has great potential in feature selection during BP prediction and the proposed multi-parameter fusion method can be used for long-term BP monitoring. Full article

Wearable medical devices (WMDs) for healthcare applications have become ubiquitous, allowing remote, at-home, and real-time chronic monitoring that have significantly decongested clinics. These WMDs permitted the monitoring of several physiological parameters, such as heart and respiration rates, SPO₂, temperature, and energy expenditure during activities of daily living (ADLs) or fitness activities. While the measurement of these parameters has become common, full noninvasive, unobtrusive, and real-time blood pressure (BP) monitoring remains elusive owing to BP’s complex dynamics. To bring this into fruition, several works have been conducted combining different biosignals to indirectly extract BP by using PTT. Unlike previous works, we considered PTT variability by averaging it over discrete durations to account for BP variability for a more accurate estimation. PTTs were obtained using electrocardiograph (ECG) and reflective photoplethysmograph (rPPG) signals extracted by a wearable device attached to a single site on the upper arm. Our results show a significant correlation between average PTT and the BP measured using auscultation in a trial study. The developed system has potential for chronic, noninvasive, and cuff-less blood pressure monitors (BPMs) for localized and single-site implementations. Meanwhile, real-time data from the wearable device may be accessed via a remote desktop or a mobile phone application. Full article

Wearable cuffless photoplethysmographic blood pressure monitors have garnered widespread attention in recent years; however, the long-term performance values of these devices are questionable. Most cuffless blood pressure monitors require initial baseline calibration and regular recalibrations with a cuffed blood pressure monitor to ensure accurate blood pressure estimation, and their estimation accuracy may vary over time if left uncalibrated. Therefore, this study assessed the accuracy and long-term performance of an upper-arm, cuffless photoplethysmographic blood pressure monitor according to the ISO 81060-2 standard. This device was based on a nonlinear machine-learning model architecture with a fine-tuning optimized method. The blood pressure measurement protocol followed a validation procedure according to the standard, with an additional four weekly blood pressure measurements over a 1-month period, to assess the long-term performance values of the upper-arm, cuffless photoplethysmographic blood pressure monitor. The results showed that the photoplethysmographic signals obtained from the upper arm had better qualities when compared with those measured from the wrist. When compared with the cuffed blood pressure monitor, the means ± standard deviations of the difference in BP at week 1 (baseline) were −1.36 ± 7.24 and −2.11 ± 5.71 mmHg for systolic and diastolic blood pressure, respectively, which met the first criterion of ≤5 ± ≤8.0 mmHg and met the second criterion of a systolic blood pressure ≤ 6.89 mmHg and a diastolic blood pressure ≤ 6.84 mmHg. The differences in the uncalibrated blood pressure values between the test and reference blood pressure monitors measured from week 2 to week 5 remained stable and met both criteria 1 and 2 of the ISO 81060-2 standard. The upper-arm, cuffless photoplethysmographic blood pressure monitor in this study generated high-quality photoplethysmographic signals with satisfactory accuracy at both initial calibration and 1-month follow-ups. This device could be a convenient and practical tool to continuously measure blood pressure over long periods of time. Full article

Electronic health (eHealth) is a strategy to improve the physical and mental condition of a human, collecting daily physiological data and information from digital apparatuses. Body weight and blood pressure (BP) are the most popular and important physiological data. The goal of this study is to develop a minimal contact BP measurement method based on a commercial body weight-fat scale, capturing biometrics when users stand on it. The pulse transit time (PTT) is extracted from the ballistocardiogram (BCG) and impedance plethysmogram (IPG), measured by four strain gauges and four footpads of a commercial body weight-fat scale. Cuffless BP measurement using the electrocardiogram (ECG) and photoplethysmogram (PPG) serves as the reference method. The BP measured by a commercial BP monitor is considered the ground truth. Twenty subjects participated in this study. By the proposed model, the root-mean-square errors and correlation coefficients (r²s) of estimated systolic blood pressure and diastolic blood pressure are 7.3 ± 2.1 mmHg and 4.5 ± 1.8 mmHg, and 0.570 ± 0.205 and 0.284 ± 0.166, respectively. This accuracy level achieves the C grade of the corresponding IEEE standard. Thus, the proposed method has the potential benefit for eHealth monitoring in daily application. Full article

Cuffless blood pressure (BP) monitoring is crucial for patients with cardiovascular disease and hypertension. However, conventional BP monitors provide only single-point estimates without confidence intervals. Therefore, the statistical variability in the estimates is indistinguishable from the intrinsic variability caused by physiological processes. This study introduced a novel method for improving the reliability of BP and confidence intervals (CIs) estimations using a hybrid feature selection and decision method based on a Gaussian process. F-test and robust neighbor component analysis were applied as feature selection methods for obtaining a set of highly weighted features to estimate accurate BP and CIs. Akaike’s information criterion algorithm was used to select the best feature subset. The performance of the proposed algorithm was confirmed through experiments. Comparisons with conventional algorithms indicated that the proposed algorithm provided the most accurate BP and CIs estimates. To the best of the authors’ knowledge, the proposed method is currently the only one that provides highly reliable BP and CIs estimates. Therefore, the proposed algorithm may be robust for concurrently estimating BP and CIs. Full article

Remote health monitoring systems play an important role in the healthcare sector. Edge computing is a key enabler for realizing these systems, where it is required to collect big data while providing real-time guarantees. In this study, we focus on remote cuff-less blood pressure (BP) monitoring through electrocardiogram (ECG) as a case study to evaluate the benefits of edge computing and compression. First, we investigate the state-of-the-art algorithms for BP estimation and ECG compression. Second, we develop a system to measure the ECG, estimate the BP, and store the results in the cloud with three different configurations: (i) estimation in the edge, (ii) estimation in the cloud, and (iii) estimation in the cloud with compressed transmission. Third, we evaluate the three approaches in terms of application latency, transmitted data volume, and power usage. In experiments with batches of 64 ECG samples, the edge computing approach has reduced average application latency by 15%, average power usage by 19%, and total transmitted volume by 85%, confirming that edge computing improves system performance significantly. Compressed transmission proved to be an alternative when network bandwidth is limited and edge computing is impractical. Full article

Measuring continuous blood pressure (BP) in real time by using a mobile health (mHealth) application would open a new door in the advancement of the healthcare system. This study aimed to propose a real-time method and system for measuring BP without using a cuff from a digital artery. An energy-efficient real-time smartphone-application-friendly one-dimensional (1D) Squeeze U-net model is proposed to estimate systolic and diastolic BP values, using only raw photoplethysmogram (PPG) signal. The proposed real-time cuffless BP prediction method was assessed for accuracy, reliability, and potential usefulness in the hypertensive assessment of 100 individuals in two publicly available datasets: Multiparameter Intelligent Monitoring in Intensive Care (MIMIC-I) and Medical Information Mart for Intensive Care (MIMIC-III) waveform database. The proposed model was used to build an android application to measure BP at home. This proposed deep-learning model performs best in terms of systolic BP, diastolic BP, and mean arterial pressure, with a mean absolute error of 4.42, 2.25, and 2.56 mmHg and standard deviation of 4.78, 2.98, and 3.21 mmHg, respectively. The results meet the grade A performance requirements of the British Hypertension Society and satisfy the AAMI error range. The result suggests that only using a short-time PPG signal is sufficient to obtain accurate BP measurements in real time. It is a novel approach for real-time cuffless BP estimation by implementing an mHealth application and can measure BP at home and assess hypertension. Full article