The pre-ejection period is a highly stress dependent parameter of paramount importance for pulse-wave-velocity based applications

Comparing a cardiac sympathetic activity index with pre-ejection period in time series

Over the last decade, cardiology research has yielded a Sympathetic Activity Index (SAI) that captures the non-linear response patterns of the sympathetic nervous system. We investigated this chronotropic index alongside pre-ejection period (PEP), an inotropic index. While SAI has been validated in physiology, cardiology, and biomedical engineering research, this study introduces SAI to biopsychology. SAI is calculated exclusively from ECG, while PEP requires both ECG and impedance cardiography (ICG) as inputs. An average of 1468 time series observations were analysed per participant per sympathetic index (SAI, PEP) across 17 participants (13 female). The mean SAI-PEP correlation increased significantly from baseline to stimulus (rB->S(16) = .22, p = 0.042), and then dropped from stimulus to recovery, back to near baseline levels (rS->R(16) = -.21, p = 0.047). Ideographic patterns emerged, although overall average PEP-SAI correlations were lower than expected, as the procedure did not include a physical stressor. Participants with the strongest positive SAI-PEP correlations (mean r(1565) = .579, p < 0.001) had a matching pattern of psychological distress, as measured by Subjective Units of Distress Scale time series. When psychological distress patterns diverged from both SNS indices, SAI and PEP also diverged from each other. Results suggest that cardiac rate (SAI) and contractility (PEP) may reflect similar temporal dynamics when psychological and physiological stress patterns are aligned. PEP's lability in time series was over 10 times higher than that for SAI. While theoretical and methodological advantages are associated with SAI, further research is needed to comprehensively assess it as a cardiac sympathetic index.

Machine learning-based blood pressure estimation using impedance cardiography data

OBJECTIVE

Accurate blood pressure (BP) measurement is crucial for the diagnosis, risk assessment, treatment decision-making, and monitoring of cardiovascular diseases. Unfortunately, cuff-based BP measurements suffer from inaccuracies and discomfort. This study is the first to access the feasibility of machine learning-based BP estimation using impedance cardiography (ICG) data.

METHODS

We analyzed ICG data from 71 young and healthy adults. Nine different machine learning algorithms were evaluated for their BP estimation performance against quality controlled, oscillometric (cuff-based), arterial BP measurements during mental (Trier social stress test), and physical exercise (bike ergometer). Models were optimized to minimize the root mean squared error and their performance was evaluated against accuracy and regression metrics.

RESULTS

The multi-linear regression model demonstrated the highest measurement accuracy for systolic BP with a mean difference of -0.01 mmHg, a standard deviation (SD) of 10.79 mmHg, a mean absolute error (MAE) of 8.20 mmHg, and a correlation coefficient of r = 0.82. In contrast, the support vector regression model achieved the highest accuracy for diastolic BP with a mean difference of 0.15 mmHg, SD = 7.79 mmHg, MEA = 6.05 mmHg, and a correlation coefficient of r = 0.51.

CONCLUSION

The study demonstrates the feasibility of ICG-based machine learning algorithms for estimating cuff-based reference BP. However, further research into limiting biases, improving performance, and standardized validation is needed before clinical use.

Effect of respiration and exercise on seismocardiographic signals

BACKGROUND

Seismocardiographic signals (SCG) are chest wall vibrations induced by mechanical cardiac activities. This study investigated the morphological changes in the SCG signal due to respiration and exercise.

METHODS

Fifteen healthy subjects were recruited, and SCG was acquired before and after exercise. The changes in the SCG signal were quantified using time and amplitude features.

RESULTS

The amplitudes of the two main SCG events (SCG1 and SCG2) tended to increase after exercise. The absolute cardiac intervals (pre-ejection period (PEP), left ventricular ejection time (LVET), and diastolic time) decreased; the diastolic time relative to cardiac cycle duration (i.e., the R-R interval) also decreased, while the relative PEP and LVET increased for the majority of the subjects. Amplitude modulations were observed in both SCG1 and SCG2 and increased with exercise. Additionally, respiratory influences on the SCG features were observed in both the pre- and post-exercise states. SCG2 amplitude was higher during inspiration (p < 0.01), but SCG1 amplitude didn't exhibit consistent changes with respiration in the study subjects (p > 0.05). For cardiac intervals, PEP decreased during inspiration, while LVET and diastolic time increased (p < 0.01). All the cardiac intervals (both absolute and as a percentage of cardiac cycle duration) showed reduced respiratory variability post-exercise.

CONCLUSIONS

These results document SCG signal variabilities that were not reported before and provide a link between cardiac activity, respiration, and exercise, which may help increase the clinical utility of SCG in the diagnosis and management of cardiopulmonary conditions. More studies are required to validate the study findings in more normal subjects and in those with cardiopulmonary pathology.

Prediction of ECG signals from ballistocardiography using deep learning for the unconstrained measurement of heartbeat intervals

We developed a deep learning-based extraction of electrocardiographic (ECG) waves from ballistocardiographic (BCG) signals and explored their use in R-R interval (RRI) estimation. Preprocessed BCG and reference ECG signals were inputted into the bidirectional long short-term memory network to train the model to minimize the loss function of the mean squared error between the predicted ECG (pECG) and genuine ECG signals. Using a dataset acquired with polyvinylidene fluoride and ECG sensors in different recumbent positions from 18 participants, we generated pECG signals from preprocessed BCG signals using the learned model and evaluated the RRI estimation performance by comparing the predicted RRI with the reference RRI obtained from the ECG signal using a leave-one-subject-out cross-validation scheme. A mean absolute error (MAE) of 0.034 s was achieved for the beat-to-beat interval accuracy. To further test the generalization ability of the learned model trained with a short-term-recorded dataset, we collected long-term overnight recordings of BCG signals from 12 different participants and performed validation. The beat-to-beat interval correlation between BCG and ECG signals was 0.82 ± 0.06 with an average MAE of 0.046 s, showing practical performance for long-term measurement of RRIs. These results suggest that the proposed approach can be used for continuous heart rate monitoring in a home environment.

Cuffless Blood Pressure in clinical practice: challenges, opportunities and current limits

Background: Cuffless blood pressure measurement technologies have attracted significant attention for their potential to transform cardiovascular monitoring.Methods: This updated narrative review thoroughly examines the challenges, opportunities, and limitations associated with the implementation of cuffless blood pressure monitoring systems.Results: Diverse technologies, including photoplethysmography, tonometry, and ECG analysis, enable cuffless blood pressure measurement and are integrated into devices like smartphones and smartwatches. Signal processing emerges as a critical aspect, dictating the accuracy and reliability of readings. Despite its potential, the integration of cuffless technologies into clinical practice faces obstacles, including the need to address concerns related to accuracy, calibration, and standardization across diverse devices and patient populations. The development of robust algorithms to mitigate artifacts and environmental disturbances is essential for extracting clear physiological signals. Based on extensive research, this review emphasizes the necessity for standardized protocols, validation studies, and regulatory frameworks to ensure the reliability and safety of cuffless blood pressure monitoring devices and their implementation in mainstream medical practice. Interdisciplinary collaborations between engineers, clinicians, and regulatory bodies are crucial to address technical, clinical, and regulatory complexities during implementation. In conclusion, while cuffless blood pressure monitoring holds immense potential to transform cardiovascular care. The resolution of existing challenges and the establishment of rigorous standards are imperative for its seamless incorporation into routine clinical practice.Conclusion: The emergence of these new technologies shifts the paradigm of cardiovascular health management, presenting a new possibility for non-invasive continuous and dynamic monitoring. The concept of cuffless blood pressure measurement is viable and more finely tuned devices are expected to enter the market, which could redefine our understanding of blood pressure and hypertension.

Are Wearable Photoplethysmogram-Based Heart Rate Variability Measures Equivalent to Electrocardiogram? A Simulation Study

BACKGROUND

Traditional electrocardiography (ECG)-derived heart rate variability (HRV) and photoplethysmography (PPG)-derived "HRV" (termed PRV) have been reported interchangeably. Any potential dissociation between HRV and PRV could be due to the variability in pulse arrival time (PAT; time between heartbeat and peripheral pulse).

OBJECTIVE

This study examined if PRV is equivalent to ECG-derived HRV and if PRV's innate error makes it a high-quality measurement separate from HRV.

METHODS

ECG data from 1084 subjects were obtained from the PhysioNet Autonomic Aging dataset, and individual PAT dispersions for both the wrist (n = 42) and finger (n = 49) were derived from Mol et al. (Exp Gerontol. 2020; 135: 110938). A Bayesian simulation was constructed whereby the individual arrival times of the PPG wave were calculated by placing a Gaussian prior on the individual QRS-wave timings of each ECG series. The standard deviation (σ) of the prior corresponds to the PAT dispersion from Mol et al. This was simulated 10,000 times for each PAT σ. The root mean square of successive differences (RMSSD) and standard deviation of N-N intervals (SDNN) were calculated for both HRV and PRV. The Region of Practical Equivalence bounds (ROPE) were set a priori at ± 0.2% of true HRV. The highest density interval (HDI) width, encompassing 95% of the posterior distribution, was calculated for each PAT σ.

RESULTS

The lowest PAT σ (2.0 SD) corresponded to 88.4% within ROPE for SDNN and 21.4% for RMSSD. As the σ of PAT increases, the equivalence of PRV and HRV decreases for both SDNN and RMSSD. The HDI interval width increases with increasing PAT σ, with the HDI width increasing at a higher rate for RMSSD than SDNN.

CONCLUSIONS

For individuals with greater PAT variability, PRV is not a surrogate for HRV. When considering PRV as a unique biometric measure, SDNN may have more favorable measurement properties than RMSSD, though both exhibit a non-uniform measurement error.

Pulse Wave Velocity: Methodology, Clinical Applications, and Interplay with Heart Rate Variability

Pulse wave velocity (PWV) has been established as a promising biomarker in cardiovascular diagnostics, providing deep insights into vascular health and cardiovascular risk. Defined as the velocity at which the mechanical wave propagates along the arterial wall, PWV represents a useful surrogate marker for arterial vessel stiffness. PWV has garnered clinical attention, particularly in monitoring patients suffering from vascular diseases such as hypertension and diabetes mellitus. Its utility extends to preventive cardiology, aiding in identifying and stratifying cardiovascular risk. Despite the development of various measurement techniques, direct or indirect tonometry, Doppler ultrasound, oscillometric analysis, and magnetic resonance imaging (MRI), methodological variability and lack of standardization lead to inconsistencies in PWV assessment. In addition, PWV can be estimated through surrogate parameters, such as pulse arrival or pulse transit times, although this heterogeneity limits standardization and, therefore, its clinical use. Furthermore, confounding factors, such as variations in sympathetic tone, strongly influence PWV readings, thereby necessitating careful control during assessments. The bidirectional relationship between heart rate variability (HRV) and PWV underscores the interplay between cardiac autonomic function and vascular health, suggesting that alterations in one could directly influence the other. Future research should prioritize the standardization and increase comparability of PWV measurement techniques and explore the complex physiological variables influencing PWV. Integrating multiple physiological parameters such as PWV and HRV into algorithms based on artificial intelligence holds immense promise for advancing personalized vascular health assessments and cardiovascular care.

Estimating Blood Pressure during Exercise with a Cuffless Sphygmomanometer

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.

Towards continuous non-invasive blood pressure measurements-interpretation of the vasculature response to cuff inflation

Blood pressure (BP) surrogates, such as pulse transit time (PTT) or pulse arrival time (PAT), have been intensively explored with the goal of achieving cuffless, continuous, and accurate BP inference. In order to estimate BP, a one-point calibration strategy between PAT and BP is typically used. Recent research focuses on advanced calibration procedures exploiting the cuff inflation process to improve calibration robustness by active and controlled modulation of peripheral PAT, as measured via plethysmograph (PPG) and electrocardiogram (ECG) combination. Such methods require a detailed understanding of the mechanisms behind the vasculature's response to cuff inflation; for this, a model has recently been developed to infer the PAT-BP calibration from measured cuff-induced vasculature changes. The model, while promising, is still preliminary and only partially validated; in-depth analysis and further developments are still needed. Therefore, this work aims to improve our understanding of the cuff-vasculature interaction in this model; we seek to define potential opportunities and to highlight which aspects may require further study. We compare model behaviors with clinical data samples based on a set of observable characteristics relevant for BP inference and calibration. It is found that the observed behaviors are qualitatively well represented with the current simulation model and complexity, with limitations regarding the prediction of the onset of the distal arm dynamics and behavior changes at high cuff pressures. Additionally, a sensitivity analysis of the model's parameter space is conducted to show the factors that influence the characteristics of its observable outputs. It was revealed that easily controllable experimental variables, such as lateral cuff length and inflation rate, have a significant impact on cuff-induced vasculature changes. An interesting dependency between systemic BP and cuff-induced distal PTT change is also found, revealing opportunities for improved methods for BP surrogate calibration. However, validation via patient data shows that this relation does not hold for all patients, indicating required model improvements to be validated in follow up studies. These results provide promising directions to improve the calibration process featuring cuff inflation towards accurate and robust non-invasive blood pressure estimation.

Intraoperative Beat-to-Beat Pulse Transit Time (PTT) Monitoring via Non-Invasive Piezoelectric/Piezocapacitive Peripheral Sensors Can Predict Changes in Invasively Acquired Blood Pressure in High-Risk Surgical Patients

BACKGROUND

Non-invasive tracking of beat-to-beat pulse transit time (PTT) via piezoelectric/piezocapacitive sensors (PES/PCS) may expand perioperative hemodynamic monitoring. This study evaluated the ability for PTT via PES/PCS to correlate with systolic, diastolic, and mean invasive blood pressure (SBP_IBP, DBP_IBP, and MAP_IBP, respectively) and to detect SBP_IBP fluctuations.

METHODS

PES/PCS and IBP measurements were performed in 20 patients undergoing abdominal, urological, and cardiac surgery. A Pearson's correlation analysis (r) between 1/PTT and IBP was performed. The predictive ability of 1/PTT with changes in SBP_IBP was determined by area under the curve (reported as AUC, sensitivity, specificity).

RESULTS

Significant correlations between 1/PTT and SBP_IBP were found for PES (r = 0.64) and PCS (r = 0.55) (p < 0.01), as well as MAP_IBP/DBP_IBP for PES (r = 0.6/0.55) and PCS (r = 0.5/0.45) (p < 0.05). A 7% decrease in 1/PTT_PES predicted a 30% SBP_IBP decrease (0.82, 0.76, 0.76), while a 5.6% increase predicted a 30% SBP_IBP increase (0.75, 0.7, 0.68). A 6.6% decrease in 1/PTT_PCS detected a 30% SBP_IBP decrease (0.81, 0.72, 0.8), while a 4.8% 1/PTT_PCS increase detected a 30% SBP_IBP increase (0.73, 0.64, 0.68).

CONCLUSIONS

Non-invasive beat-to-beat PTT via PES/PCS demonstrated significant correlations with IBP and detected significant changes in SBP_IBP. Thus, PES/PCS as a novel sensor technology may augment intraoperative hemodynamic monitoring during major surgery.