Pulse transit time estimation of aortic pulse wave velocity and blood pressure using machine learning and simulated training data

Simultaneous Measurement of Local Pulse Wave Velocities in Radial Arteries Using a Soft Sensor Based on the Fiber Bragg Grating Technique

Arterial stiffness has been proved to be an important parameter in the evaluation of cardiovascular diseases, and Pulse Wave Velocity (PWV) is a strong indicator of arterial stiffness. Compared to regional PWV (PWV among different arteries), local PWV (PWV within a single artery) outstands in providing higher precision in indicating arterial properties, as regional PWVs are highly affected by multiple parameters, e.g., variations in blood vessel lengths due to individual differences, and multiple reflection effects on the pulse waveform. However, local PWV is less-developed due to its high dependency on the temporal resolution in synchronized signals with usually low signal-to-noise ratios. This paper presents a method for the noninvasive simultaneous measurement of two local PWVs in both left and right radial arteries based on the Fiber Bragg Grating (FBG) technique via correlation analysis of the pulse pairs at the fossa cubitalis and at the wrist. Based on the measurements of five male volunteers at the ages of 19 to 21 years old, the average left radial PWV ranged from 9.44 m/s to 12.35 m/s and the average right radial PWV ranged from 11.50 m/s to 14.83 m/s. What is worth mentioning is that a stable difference between the left and right radial PWVs was observed for each volunteer, ranging from 2.27 m/s to 3.04 m/s. This method enables the dynamic analysis of local PWVs and analysis of their features among different arteries, which will benefit the diagnosis of early-stage arterial stiffening and may bring more insights into the diagnosis of cardiovascular diseases.

Arterial Stiffness: From Basic Primers to Integrative Physiology

The elastic properties of conductance arteries are one of the most important hemodynamic functions in the body, and data continue to emerge regarding the importance of their dysfunction in vascular aging and a range of cardiovascular diseases. Here, we provide new insight into the integrative physiology of arterial stiffening and its clinical consequence. We also comprehensively review progress made on pathways/molecules that appear today as important basic determinants of arterial stiffness, particularly those mediating the vascular smooth muscle cell (VSMC) contractility, plasticity and stiffness. We focus on membrane and nuclear mechanotransduction, clearance function of the vascular wall, phenotypic switching of VSMCs, immunoinflammatory stimuli and epigenetic mechanisms. Finally, we discuss the most important advances of the latest clinical studies that revisit the classical therapeutic concepts of arterial stiffness and lead to a patient-by-patient strategy according to cardiovascular risk exposure and underlying disease.

Reconstruction of central arterial pressure waveform based on CBi-SAN network from radial pressure waveform

The central arterial pressure (CAP) is an important physiological indicator of the human cardiovascular system which represents one of the greatest threats to human health. Accurate non-invasive detection and reconstruction of CAP waveforms are crucial for the reliable treatment of cardiovascular system diseases. However, the traditional methods are reconstructed with relatively low accuracy, and some deep learning neural network models also have difficulty in extracting features, as a result, these methods have potential for further advancement. In this study, we proposed a novel model (CBi-SAN) to implement an end-to-end relationship from radial artery pressure (RAP) waveform to CAP waveform, which consisted of the convolutional neural network (CNN), the bidirectional long-short-time memory network (BiLSTM), and the self-attention mechanism to improve the performance of CAP reconstruction. The data on invasive measurements of CAP and RAP waveform were used in 62 patients before and after medication to develop and validate the performance of CBi-SAN model for reconstructing CAP waveform. We compared it with traditional methods and deep learning models in mean absolute error (MAE), root mean square error (RMSE), and Spearman correlation coefficient (SCC). Study results indicated the CBi-SAN model performed great performance on CAP waveform reconstruction (MAE: 2.23 ± 0.11 mmHg, RMSE: 2.21 ± 0.07 mmHg), concurrently, the best reconstruction effect was obtained in the central artery systolic pressure (CASP) and the central artery diastolic pressure(CADP) (RMSECASP: 2.94 ± 0.48 mmHg, RMSECADP: 1.96 ± 0.06 mmHg). These results implied the performance of the CAP reconstruction based on CBi-SAN model was superior to the existing methods, hopped to be effectively applied to clinical practice in the future.

Mechanistic insights on age-related changes in heart-aorta-brain hemodynamic coupling using a pulse wave model of the entire circulatory system

Age-related changes in aortic biomechanics can impact the brain by reducing blood flow and increasing pulsatile energy transmission. Clinical studies have shown that impaired cardiac function in patients with heart failure is associated with cognitive impairment. Although previous studies have attempted to elucidate the complex relationship between age-associated aortic stiffening and pulsatility transmission to the cerebral network, they have not adequately addressed the effect of interactions between aortic stiffness and left ventricle (LV) contractility (neither on energy transmission nor on brain perfusion). In this study, we use a well-established and validated one-dimensional blood flow and pulse wave computational model of the circulatory system to address how age-related changes in cardiac function and vasculature affect the underlying mechanisms involved in the LV-aorta-brain hemodynamic coupling. Our results reveal how LV contractility affects pulsatile energy transmission to the brain, even with preserved cardiac output. Our model demonstrates the existence of an optimal heart rate (near the normal human heart rate) that minimizes pulsatile energy transmission to the brain at different contractility levels. Our findings further suggest that the reduction in cerebral blood flow at low levels of LV contractility is more prominent in the setting of age-related aortic stiffening. Maintaining optimal blood flow to the brain requires either an increase in contractility or an increase in heart rate. The former consistently leads to higher pulsatile power transmission, and the latter can either increase or decrease subsequent pulsatile power transmission to the brain.NEW & NOTEWORTHY We investigated the impact of major aging mechanisms of the arterial system and cardiac function on brain hemodynamics. Our findings suggest that aging has a significant impact on heart-aorta-brain coupling through changes in both arterial stiffening and left ventricle (LV) contractility. Understanding the underlying physical mechanisms involved here can potentially be a key step for developing more effective therapeutic strategies that can mitigate the contributions of abnormal LV-arterial coupling toward neurodegenerative diseases and dementia.

Survey and Evaluation of Hypertension Machine Learning Research

Background Machine learning (ML) is pervasive in all fields of research, from automating tasks to complex decision-making. However, applications in different specialities are variable and generally limited. Like other conditions, the number of studies employing ML in hypertension research is growing rapidly. In this study, we aimed to survey hypertension research using ML, evaluate the reporting quality, and identify barriers to ML's potential to transform hypertension care. Methods and Results The Harmonious Understanding of Machine Learning Analytics Network survey questionnaire was applied to 63 hypertension-related ML research articles published between January 2019 and September 2021. The most common research topics were blood pressure prediction (38%), hypertension (22%), cardiovascular outcomes (6%), blood pressure variability (5%), treatment response (5%), and real-time blood pressure estimation (5%). The reporting quality of the articles was variable. Only 46% of articles described the study population or derivation cohort. Most articles (81%) reported at least 1 performance measure, but only 40% presented any measures of calibration. Compliance with ethics, patient privacy, and data security regulations were mentioned in 30 (48%) of the articles. Only 14% used geographically or temporally distinct validation data sets. Algorithmic bias was not addressed in any of the articles, with only 6 of them acknowledging risk of bias. Conclusions Recent ML research on hypertension is limited to exploratory research and has significant shortcomings in reporting quality, model validation, and algorithmic bias. Our analysis identifies areas for improvement that will help pave the way for the realization of the potential of ML in hypertension and facilitate its adoption.

Machine-Learning Classification of Pulse Waveform Quality

Pulse measurements made using wearable devices can aid the monitoring of human physiological condition. Accurate estimation of waveforms is often difficult for nonexperts; motion artifacts may occur during tonometry measurements when the skin-sensor contact pressure is insufficient. An alternative approach is to extract only high-quality pulses for use in index calculations. The present study aimed to determine the effectiveness of using machine-learning analysis in discriminating between high-quality and low-quality pulse waveforms induced by applying different contact pressures. Radial blood pressure waveform (BPW) signals were measured noninvasively in healthy young subjects using a strain-gauge transducer. One-minute-long trains of pulse data were measured when applying the appropriate contact pressure (67.80 ± 1.55 mmHg) and a higher contact pressure (151.80 ± 3.19 mmHg). Eight machine-learning algorithms were employed to evaluate the following 40 harmonic pulse indices: amplitude proportions and their coefficients of variation and phase angles and their standard deviations. Significant differences were noted in BPW indices between applying appropriate and higher skin-surface contact pressures. The present appropriate contact pressure could not only provide a suitable holding force for the wearable device but also helped to maintain the physiological stability of the underlying tissues. Machine-learning analysis provides an effective method for distinguishing between the high-quality and low-quality pulses with excellent discrimination performance (leave-one-subject-out test: random-forest AUC = 0.96). This approach will aid the development of an automatic screening method for waveform quality and thereby improve the noninvasive acquisition reliability. Other possible interfering factors in practical applications can also be systematically studied using a similar procedure.

Piezoelectric Dynamics of Arterial Pulse for Wearable Continuous Blood Pressure Monitoring

Piezoelectric arterial pulse wave dynamics are traditionally considered to be similar to those of typical blood pressure waves. However, achieving accurate continuous blood pressure wave monitoring based on arterial pulse waves remains challenging, because the correlation between piezoelectric pulse waves and their related blood pressure waves is unclear. To address this, the correlation between piezoelectric pulse waves and blood pressure waves is first elucidated via theoretical, simulation, and experimental analysis of these dynamics. Based on this correlation, the authors develop a wireless wearable continuous blood pressure monitoring system, with better portability than conventional systems that are based on the pulse wave velocity between multiple sensors. They explore the feasibility of achieving wearable continuous blood pressure monitoring without motion artifacts, using a single piezoelectric sensor. These findings eliminate the controversy over the arterial pulse wave piezoelectric response, and can potentially be used to develop a portable wearable continuous blood pressure monitoring device for the early prevention and daily control of hypertension.

Leveraging the potential of machine learning for assessing vascular ageing: state-of-the-art and future research

Vascular ageing biomarkers have been found to be predictive of cardiovascular risk independently of classical risk factors, yet are not widely used in clinical practice. In this review, we present two basic approaches for using machine learning (ML) to assess vascular age: parameter estimation and risk classification. We then summarize their role in developing new techniques to assess vascular ageing quickly and accurately. We discuss the methods used to validate ML-based markers, the evidence for their clinical utility, and key directions for future research. The review is complemented by case studies of the use of ML in vascular age assessment which can be replicated using freely available data and code.

Determination of Aortic Characteristic Impedance and Total Arterial Compliance From Regional Pulse Wave Velocities Using Machine Learning: An in-silico Study

In-vivo assessment of aortic characteristic impedance (Z ao ) and total arterial compliance (C T ) has been hampered by the need for either invasive or inconvenient and expensive methods to access simultaneous recordings of aortic pressure and flow, wall thickness, and cross-sectional area. In contrast, regional pulse wave velocity (PWV) measurements are non-invasive and clinically available. In this study, we present a non-invasive method for estimating Z ao and C T using cuff pressure, carotid-femoral PWV (cfPWV), and carotid-radial PWV (crPWV). Regression analysis is employed for both Z ao and C T . The regressors are trained and tested using a pool of virtual subjects (n = 3,818) generated from a previously validated in-silico model. Predictions achieved an accuracy of 7.40%, r = 0.90, and 6.26%, r = 0.95, for Z ao , and C T , respectively. The proposed approach constitutes a step forward to non-invasive screening of elastic vascular properties in humans by exploiting easily obtained measurements. This study could introduce a valuable tool for assessing arterial stiffness reducing the cost and the complexity of the required measuring techniques. Further clinical studies are required to validate the method in-vivo.

An integrated lumped-parameter model of the cardiovascular system for the simulation of acute ischemic stroke: description of instantaneous changes in hemodynamics

Acute Ischemic Stroke (AIS) is defined as the acute condition of occlusion of a cerebral artery and is often caused by a Hypertensive Condition (HC). Due to its sudden occurrence, AIS is not observable the right moment it occurs, thus information about instantaneous changes in hemodynamics is limited. This study aimed to propose an integrated Lumped Parameter (LP) model of the cardiovascular system to simulate an AIS and describe instantaneous changes in hemodynamics. In the integrated LP model of the cardiovascular system, heart chambers have been modelled with elastance systems with controlled pressure inputs; heart valves have been modelled with static open/closed pressure-controlled valves; eventually, the vasculature has been modelled with resistor-inductor-capacitor (RLC) direct circuits and have been linked to the rest of the system through a series connection. After simulating physiological conditions, HC has been simulated by changing pressure inputs and constant RLC parameters. Then, AIS occurring in arteries of different sizes have been simulated by considering time-dependent RLC parameters due to the elimination from the model of the occluding artery; instantaneous changes in hemodynamics have been evaluated by Systemic Arteriolar Flow (Qa) and Systemic Arteriolar Pressure (Pa) drop with respect to those measured in HC. Occlusion of arteries of different sizes leaded to an average Qa drop of 0.38 ml/s per cardiac cycle (with minimum and maximum values of 0.04 ml/s and 1.93 ml/s) and average Pa drop of 0.39 mmHg, (with minimum and maximum values of 0.04 mmHg and 1.98 mmHg). In conclusion, hemodynamic variations due to AIS are very small with respect to HC. A direct relation between the inverse of the length of the artery in which the occlusion occurs and the hemodynamic variations has been highlighted; this may allow to link the severity of AIS to the length of the interested artery.

Classification of patients with Alzheimer's disease using the arterial pulse spectrum and a multilayer-perceptron analysis

Cerebrovascular atherosclerosis has been identified as a prominent pathological feature of Alzheimer's disease (AD); the link between vessel pathology and AD risk may also extend to extracranial arteries. This study aimed to determine the effectiveness of using arterial pulse-wave measurements and multilayer perceptron (MLP) analysis in distinguishing between AD and control subjects. Radial blood pressure waveform (BPW) and finger photoplethysmography signals were measured noninvasively for 3 min in 87 AD patients and 74 control subjects. The 5-layer MLP algorithm employed evaluated the following 40 harmonic pulse indices: amplitude proportion and its coefficient of variation, and phase angle and its standard deviation. The BPW indices differed significantly between the AD patients (6247 pulses) and control subjects (6626 pulses). Significant intergroup differences were found between mild, moderate, and severe AD (defined by Mini-Mental-State-Examination scores). The hold-out test results indicated an accuracy of 82.86%, a specificity of 92.31%, and a 0.83 AUC of ROC curve when using the MLP-based classification between AD and Control. The identified differences can be partly attributed to AD-induced changes in vascular elastic properties. The present findings may be meaningful in facilitating the development of a noninvasive, rapid, inexpensive, and objective method for detecting and monitoring the AD status.

Vascular origins of low-frequency oscillations in the cerebrospinal fluid signal in resting-state fMRI: Interpretation using photoplethysmography

In vivo mapping of cerebrovascular oscillations in the 0.05–0.15 Hz remains difficult. Oscillations in the cerebrospinal fluid (CSF) represent a possible avenue for noninvasively tracking these oscillations using resting‐state functional MRI (rs‐fMRI), and have been used to correct for vascular oscillations in rs‐fMRI functional connectivity. However, the relationship between low‐frequency CSF and vascular oscillations remains unclear. In this study, we investigate this relationship using fast simultaneous rs‐fMRI and photoplethysmogram (PPG), examining the 0.1 Hz PPG signal, heart‐rate variability (HRV), pulse‐intensity ratio (PIR), and the second derivative of the PPG (SDPPG). The main findings of this study are: (a) signals in different CSF regions are not equivalent in their associations with vascular and tissue rs‐fMRI signals; (b) the PPG signal is maximally coherent with the arterial and CSF signals at the cardiac frequency, but coherent with brain tissue at ~0.2 Hz; (c) PIR is maximally coherent with the CSF signal near 0.03 Hz; and (d) PPG‐related vascular oscillations only contribute to ~15% of the CSF (and arterial) signal in rs‐fMRI. These findings caution against averaging all CSF regions when extracting physiological nuisance regressors in rs‐fMRI applications, and indicate the drivers of the CSF signal are more than simply cardiac. Our study is an initial attempt at the refinement and standardization of how the CSF signal in rs‐fMRI can be used and interpreted. It also paves the way for using rs‐fMRI in the CSF as a potential tool for tracking cerebrovascular health through, for instance, the potential relationship between PIR and the CSF signal.

Comparison of Machine Learning Algorithms for Structure State Prediction in Operational Load Monitoring

The aim of operational load monitoring is to make predictions about the remaining usability time of structures, which is extremely useful in aerospace industry where in-service life of aircraft structural components can be maximized, taking into account safety. In order to make such predictions, strain sensors are mounted to the structure, from which data are acquired during operational time. This allows to determine how many load cycles has the structure withstood so far. Continuous monitoring of the strain distribution of the whole structure can be complicated due to vicissitude nature of the loads. Sensors should be mounted in places where stress and strain accumulations occur, and due to experiencing variable loads, the number of required sensors may be high. In this work, different machine learning and artificial intelligence algorithms are implemented to predict the current safety factor of the structure in its most stressed point, based on relatively low number of strain measurements. Adaptive neuro-fuzzy inference systems (ANFIS), support-vector machines (SVM) and Gaussian processes for machine learning (GPML) are trained with simulation data, and their effectiveness is measured using data obtained from experiments. The proposed methods are compared to the earlier work where artificial neural networks (ANN) were proven to be efficiently used for reduction of the number of sensors in operational load monitoring processes. A numerical comparison of accuracy and computational time (taking into account possible real-time applications) between all considered methods is provided.

Noninvasive estimation of aortic hemodynamics and cardiac contractility using machine learning

Cardiac and aortic characteristics are crucial for cardiovascular disease detection. However, noninvasive estimation of aortic hemodynamics and cardiac contractility is still challenging. This paper investigated the potential of estimating aortic systolic pressure (aSBP), cardiac output (CO), and end-systolic elastance (E_es) from cuff-pressure and pulse wave velocity (PWV) using regression analysis. The importance of incorporating ejection fraction (EF) as additional input for estimating E_es was also assessed. The models, including Random Forest, Support Vector Regressor, Ridge, Gradient Boosting, were trained/validated using synthetic data (n = 4,018) from an in-silico model. When cuff-pressure and PWV were used as inputs, the normalized-RMSEs/correlations for aSBP, CO, and E_es (best-performing models) were 3.36 ± 0.74%/0.99, 7.60 ± 0.68%/0.96, and 16.96 ± 0.64%/0.37, respectively. Using EF as additional input for estimating E_es significantly improved the predictions (7.00 ± 0.78%/0.92). Results showed that the use of noninvasive pressure measurements allows estimating aSBP and CO with acceptable accuracy. In contrast, E_es cannot be predicted from pressure signals alone. Addition of the EF information greatly improves the estimated E_es. Accuracy of the model-derived aSBP compared to in-vivo aSBP (n = 783) was very satisfactory (5.26 ± 2.30%/0.97). Future in-vivo evaluation of CO and E_es estimations remains to be conducted. This novel methodology has potential to improve the noninvasive monitoring of aortic hemodynamics and cardiac contractility.

A Gaussian process regression model to predict energy contents of corn for poultry

The present study proposes a Gaussian process regression (GPR) approach to develop a model to predict true metabolizable energy corrected for nitrogen (TMEn) content of corn samples (as model output) for poultry given levels of feed chemical compositions of crude protein, ether extract, crude fiber, and ash (as model inputs). A 30 corn samples obtained from 5 origins [Brazil (n = 9), China (n = 5), Iran (n = 7), and Ukraine (n = 9)] were assayed to determine chemical composition and TMEn content using chemical analyses and bioassay technique. In addition to GPR model, data were also analyzed by multiple linear regression (MLR) model. Results revealed that corn samples of different origins differ in their gross energy and chemical composition of crude protein, crude fiber, and ash, but no differences were observed for their ether extract and TMEn contents. Based on model evaluation criteria of R² and root mean square error (RMSE), the GPR model showed satisfactory performance (R² = 0.92 and RMSE = 33.68 kcal/kg DM) in predicting TMEn and produced relatively better prediction values than those produce by MLR (R² = 0.23 and RMSE = 104.85 kcal/kg DM). The GPR model may be capable of improving our aptitude and capacity to precisely predict energy contents of feed ingredients to formulate optimal diets for poultry.

Cuffless Blood Pressure Monitoring: Promises and Challenges

Current BP measurements are on the basis of traditional BP cuff approaches. Ambulatory BP monitoring, at 15- to 30-minute intervals usually over 24 hours, provides sufficiently continuous readings that are superior to the office-based snapshot, but this system is not suitable for frequent repeated use. A true continuous BP measurement that could collect BP passively and frequently would require a cuffless method that could be worn by the patient, with the data stored electronically much the same way that heart rate and heart rhythm are already done routinely. Ideally, BP should be measured continuously and frequently during diverse activities during both daytime and nighttime in the same subject by means of novel devices. There is increasing excitement for newer methods to measure BP on the basis of sensors and algorithm development. As new devices are refined and their accuracy is improved, it will be possible to better assess masked hypertension, nocturnal hypertension, and the severity and variability of BP. In this review, we discuss the progression in the field, particularly in the last 5 years, ending with sensor-based approaches that incorporate machine learning algorithms to personalized medicine.

Deep learning for prediction of cardiac indices from photoplethysmographic waveform: A virtual database approach

Deep learning methods combined with large datasets have recently shown significant progress in solving several medical tasks. However, collecting and annotating large datasets can be a very cumbersome and expensive task. We tackle these problems with a virtual database approach where training data is generated using computer simulations of related phenomena. Specifically, we concentrate on the following problem: can cardiovascular indices such as aortic elasticity, diastolic and systolic blood pressures, and blood flow from heart be predicted continuously using wearable photoplethysmographic sensors? We simulate the blood flow using a haemodynamic model consisting of the entire human circulation. Repeated evaluation of the simulator allows us to create a database of "virtual subjects" with size that is only limited by available computational resources. Using this database, we train neural networks to predict the cardiac indices from photoplethysmographic signal waveform. We consider two approaches: neural networks based on predefined input features and deep convolutional neural networks taking waveform directly as the input. The performance of the methods is demonstrated using numerical examples, thus carrying out a preliminary assessment of the approaches. The results show improvements in accuracy compared with the previous methods. The improvements are especially significant with indices related to aortic elasticity and maximum blood flow. The proposed approach would provide new means to measure cardiovascular health continuously, for example, with a simple wrist device.