Corrigendum: Determination of aortic characteristic impedance and total arterial compliance from regional pulse wave velocities using machine learning: an in silico study.

[This corrects the article DOI: 10.3389/fbioe.2021.649866.].

Novel theory and potential applications of central diastolic pressure decay time constant.

Central aortic diastolic pressure decay time constant ( τ ) is according to the two-element Windkessel model equal to the product of total peripheral resistance ( R ) times total arterial compliance ( C ). As such, it is related to arterial stiffness, which has considerable pathophysiological relevance in the assessment of vascular health. This study aimed to investigate the relationship of the constant τ with the product T MBP cPP , given by heart period ( T ) times the ratio of mean blood pressure (MBP) to central pulse pressure ( cPP ). The relationship was derived by performing linear fitting on an in silico population of n1 = 3818 virtual subjects, and was subsequently evaluated on in vivo data (n2 = 2263) from the large Asklepios study. The resulted expression was found to be τ = k ' T MBP cPP , with k ' = 0.7 (R2 = 0.9). The evaluation of the equation on the in vivo human data reported high agreement between the estimated and reference τ values, with a correlation coefficient equal to 0.94 and a normalized RMSE equal to 5.5%. Moreover, the analysis provided evidence that the coefficient k ' is age- and gender-independent. The proposed formula provides novel theoretical insights in the relationship between τ and central blood pressure features. In addition, it may allow for the evaluation of τ without the need for acquiring the entire central blood pressure wave, especially when an approximation of the cPP is feasible. This study adds to the current literature by contributing to the accessibility of an additional biomarker, such as the central diastolic pressure decay time constant, for the improved assessment of vascular ageing.

Utility of smart watches for identifying arrhythmias in children.

BACKGROUND: Arrhythmia symptoms are frequent complaints in children and often require a pediatric cardiology evaluation. Data regarding the clinical utility of wearable technologies are limited in children. We hypothesize that an Apple Watch can capture arrhythmias in children. METHODS: We present an analysis of patients ≤18 years-of-age who had signs of an arrhythmia documented by an Apple Watch. We include patients evaluated at our center over a 4-year-period and highlight those receiving a formal arrhythmia diagnosis. We evaluate the role of the Apple Watch in arrhythmia diagnosis, the results of other ambulatory cardiac monitoring studies, and findings of any EP studies. RESULTS: We identify 145 electronic-medical-record identifications of Apple Watch, and find arrhythmias confirmed in 41 patients (28%) [mean age 13.8 ± 3.2 years]. The arrythmias include: 36 SVT (88%), 3 VT (7%), 1 heart block (2.5%) and wide 1 complex tachycardia (2.5%). We show that invasive EP study confirmed diagnosis in 34 of the 36 patients (94%) with SVT (2 non-inducible). We find that the Apple Watch helped prompt a workup resulting in a new arrhythmia diagnosis for 29 patients (71%). We note traditional ambulatory cardiac monitors were worn by 35 patients (85%), which did not detect arrhythmias in 10 patients (29%). In 73 patients who used an Apple Watch for recreational or self-directed heart rate monitoring, 18 (25%) sought care due to device findings without any arrhythmias identified. CONCLUSION: We demonstrate that the Apple Watch can record arrhythmia events in children, including events not identified on traditionally used ambulatory monitors.

Wearable devices, such as smart watches, have become popular for the monitoring of health, particularly for people with heart conditions. Wearable devices have been well-studied in adults, however there is less information available on their effectiveness in monitoring children's health. We reviewed the heart electrical recordings of a group of children who submitted recordings obtained from their Apple Watches during moments when they felt as though their heart's rhythm was abnormal. The Apple Watches captured rhythm abnormalities that matched the diagnoses obtained using heart monitors used clinically. This study shows that use of Apple Watches can enable clinicians to identify abnormalities that many traditional at-home monitoring devices do not detect. Thus, wearable devices, such as the Apple Watch, could be used to help identify heart rhythm disorders in children.

Corrigendum: Estimation of left ventricular end-systolic elastance from brachial pressure waveform via deep learning.

[This corrects the article DOI: 10.3389/fbioe.2021.754003.].

Design and computational optimization of compliance-matching aortic grafts.

Introduction: Synthetic vascular grafts have been widely used in clinical practice for aortic replacement surgery. Despite their high rates of surgical success, they remain significantly less compliant than the native aorta, resulting in a phenomenon called compliance mismatch. This incompatibility of elastic properties may cause serious post-operative complications, including hypertension and myocardial hypertrophy. Methods: To mitigate the risk for these complications, we designed a multi-layer compliance-matching stent-graft, that we optimized computationally using finite element analysis, and subsequently evaluated in vitro. Results: We found that our compliance-matching grafts attained the distensibility of healthy human aortas, including those of young adults, thereby significantly exceeding the distensibility of gold-standard grafts. The compliant grafts maintained their properties in a wide range of conditions that are expected after the implantation. Furthermore, the computational model predicted the graft radius with enough accuracy to allow computational optimization to be performed effectively. Conclusion: Compliance-matching grafts may offer a valuable improvement over existing prostheses and they could potentially mitigate the risk for post-operative complications attributed to excessive graft stiffness.

On the similarity between aortic and carotid pressure diastolic decay: a mathematical modelling study.

Aortic diastolic pressure decay (DPD) has been shown to have considerable pathophysiological relevance in the assessment of vascular health, as it is significantly affected by arterial stiffening. Nonetheless, the aortic pressure waveform is rarely available and hence the utility of the aortic DPD is limited. On the other hand, carotid blood pressure is often used as a surrogate of central (aortic) blood pressure in cardiovascular monitoring. Although the two waveforms are inherently different, it is unknown whether the aortic DPD shares a common pattern with the carotid DPD. In this study, we compared the DPD time constant of the aorta (aortic RC) and the DPD time constant of the carotid artery (carotid RC) using an in-silico-generated healthy population from a previously validated one-dimensional numerical model of the arterial tree. Our results demonstrated that there is near-absolute agreement between the aortic RC and the carotid RC. In particular, a correlation of ~ 1 was reported for a distribution of aortic/carotid RC values equal to 1.76 ± 0.94 s/1.74 ± 0.87 s. To the best of our knowledge, this is the first study to compare the DPD of the aortic and the carotid pressure waveform. The findings indicate a strong correlation between carotid DPD and aortic DPD, supported by the examination of curve shape and the diastolic decay time constant across a wide range of simulated cardiovascular conditions. Additional investigation is required to validate these results in human subjects and assess their applicability in vivo.

Cardiac output estimated from an uncalibrated radial blood pressure waveform: validation in an in-silico-generated population.

Background: Cardiac output is essential for patient management in critically ill patients. The state-of-the-art for cardiac output monitoring bears limitations that pertain to the invasive nature of the method, high costs, and associated complications. Hence, the determination of cardiac output in a non-invasive, accurate, and reliable way remains an unmet need. The advent of wearable technologies has directed research towards the exploitation of wearable-sensed data to improve hemodynamical monitoring. Methods: We developed an artificial neural networks (ANN)-enabled modelling approach to estimate cardiac output from radial blood pressure waveform. In silico data including a variety of arterial pulse waves and cardiovascular parameters from 3,818 virtual subjects were used for the analysis. Of particular interest was to investigate whether the uncalibrated, namely, normalized between 0 and 1, radial blood pressure waveform contains sufficient information to derive cardiac output accurately in an in silico population. Specifically, a training/testing pipeline was adopted for the development of two artificial neural networks models using as input: the calibrated radial blood pressure waveform (ANNcalradBP), or the uncalibrated radial blood pressure waveform (ANNuncalradBP). Results: Artificial neural networks models provided precise cardiac output estimations across the extensive range of cardiovascular profiles, with accuracy being higher for the ANNcalradBP. Pearson's correlation coefficient and limits of agreement were found to be equal to [0.98 and (-0.44, 0.53) L/min] and [0.95 and (-0.84, 0.73) L/min] for ANNcalradBP and ANNuncalradBP, respectively. The method's sensitivity to major cardiovascular parameters, such as heart rate, aortic blood pressure, and total arterial compliance was evaluated. Discussion: The study findings indicate that the uncalibrated radial blood pressure waveform provides sample information for accurately deriving cardiac output in an in silico population of virtual subjects. Validation of our results using in vivo human data will verify the clinical utility of the proposed model, while it will enable research applications for the integration of the model in wearable sensing systems, such as smartwatches or other consumer devices.

Quantification of the Phenomena Affecting Reflective Arterial Photoplethysmography.

Photoplethysmography (PPG) is a widely emerging method to assess vascular health in humans. The origins of the signal of reflective PPG on peripheral arteries have not been thoroughly investigated. We aimed to identify and quantify the optical and biomechanical processes that influence the reflective PPG signal. We developed a theoretical model to describe the dependence of reflected light on the pressure, flow rate, and the hemorheological properties of erythrocytes. To verify the theory, we designed a silicone model of a human radial artery, inserted it in a mock circulatory circuit filled with porcine blood, and imposed static and pulsatile flow conditions. We found a positive, linear relationship between the pressure and the PPG and a negative, non-linear relationship, of comparable magnitude, between the flow and the PPG. Additionally, we quantified the effects of the erythrocyte disorientation and aggregation. The theoretical model based on pressure and flow rate yielded more accurate predictions, compared to the model using pressure alone. Our results indicate that the PPG waveform is not a suitable surrogate for intraluminal pressure and that flow rate significantly affects PPG. Further validation of the proposed methodology in vivo could enable the non-invasive estimation of arterial pressure from PPG and increase the accuracy of health-monitoring devices.

Arterial pulse wave modeling and analysis for vascular-age studies: a review from VascAgeNet.

Arterial pulse waves (PWs) such as blood pressure and photoplethysmogram (PPG) signals contain a wealth of information on the cardiovascular (CV) system that can be exploited to assess vascular age and identify individuals at elevated CV risk. We review the possibilities, limitations, complementarity, and differences of reduced-order, biophysical models of arterial PW propagation, as well as theoretical and empirical methods for analyzing PW signals and extracting clinically relevant information for vascular age assessment. We provide detailed mathematical derivations of these models and theoretical methods, showing how they are related to each other. Finally, we outline directions for future research to realize the potential of modeling and analysis of PW signals for accurate assessment of vascular age in both the clinic and in daily life.

Arterial Wave Reflection and Aortic Valve Stenosis: Diagnostic Challenges and Prognostic Significance.

Introduction: Arterial wave reflection is an important component of the left ventricular afterload, affecting both pressure and flow to the aorta. The aim of the present study was to evaluate the impact of wave reflection on transvalvular pressure gradients (TPG), a key parameter for the evaluation of aortic valve stenosis (AS), as well as its prognostic significance in patients with AS undergoing a transcatheter aortic valve replacement (TAVR). Materials and Methods: The study population consisted of 351 patients with AS (mean age 84 ± 6 years, 43% males) who underwent a complete hemodynamic evaluation before the TAVR. The baseline assessment included right and left heart catheterization, transthoracic echocardiography, and a thorough evaluation of the left ventricular afterload by means of wave separation analysis. The cohort was divided into quartiles according to the transit time of the backward pressure wave (BWTT). Primary endpoint was all-cause mortality at 1 year. Results: Early arrival of the backward pressure wave was related to lower cardiac output (Q1: 3.7 ± 0.9 lt/min vs Q4: 4.4 ± 1.0 lt/min, p < 0.001) and higher aortic systolic blood pressure (Q1: 132 ± 26 mmHg vs Q4: 117 ± 26 mmHg, p < 0.001). TPG was significantly related to the BWTT, patients in the arrival group exhibiting the lowest TPG (mean TPG, Q1: 37.6 ± 12.7 mmHg vs Q4: 44.8 ± 14.7 mmHg, p = 0.005) for the same aortic valve area (AVA) (Q1: 0.58 ± 0.35 cm2 vs 0.61 ± 0.22 cm2, p = 0.303). In multivariate analysis, BWTT remained an independent determinant of mean TPG (beta 0.3, p = 0.002). Moreover, the prevalence of low-flow, low-gradient AS with preserved ejection fraction was higher in patients with early arterial reflection arrival (Q1: 33.3% vs Q4: 14.9%, p = 0.033). Finally, patients with early arrival of the reflected wave (Q1) exhibited higher all-cause mortality at 1 year after the TAVR (unadjusted HR: 2.33, 95% CI: 1.17-4.65, p = 0.016). Conclusion: Early reflected wave arrival to the aortic root is associated with poor prognosis and significant aortic hemodynamic alterations in patients undergoing a TAVR for AS. This is related to a significant decrease in TPG for a given AVA, leading to a possible underestimation of the AS severity.

Prognostic Implications of the Novel Pulmonary Hypertension Definition in Patients with Aortic Stenosis after Transcatheter Valve Replacement.

Introduction: Pulmonary hypertension (PH), traditionally defined as a mean pulmonary artery pressure (PAP) ≥ 25 mmHg, is associated with poor outcomes in patients undergoing a transcatheter aortic valve replacement (TAVR) for severe aortic stenosis (AS). Recently, a novel definition for PH has been proposed, placing the cut-off value of mean PAP at 20 mmHg, and introducing pulmonary vascular resistance as an exclusive indicator for the pre-capillary involvement. In light of the novel criteria, whether PH still preserves its prognostic significance remains unknown. Methods: The study population consisted of 380 patients with AS, who underwent a right heart catheterization before TAVR. The cohort was divided according to the presence of PH (n = 174, 45.7%) or not. Patients with PH were further divided into the following groups: (1) Pre-capillary PH ((Pre-capPH), n = 46, 12.1%); (2) Isolated post-capillary PH ((IpcPH), n = 78, 20.5%); (3) Combined pre and post-capillary PH ((CpcPH), n = 82, 21.6%). The primary endpoint was all-cause mortality at 1 year. Results: A total of 246 patients (64.7%) exhibited mean PAP > 20 mmHg. Overall, the presence of PH was associated with higher 1-year mortality rates (hazard ratio (HR) 2.8, 95% CI: 1.4−5.8, p = 0.004). Compared to patients with no PH, Pre-capPH and CpcPH (but not IpcPH) were related to higher 1-year mortality (HR 2.7, 95% CI: 1.0−7.2, p = 0.041 and HR 3.9, 95% CI: 1.8−8.5, p = 0.001, respectively). This remained significant even after the adjustment for baseline comorbidities. Conclusions: Pre-interventional PH according to the novel hemodynamic criteria, is linked with poor outcomes in patients undergoing TAVR for severe AS. However, this is mainly driven by patients with mean PAP ≥ 25 mmHg. Patients with a pre-capillary PH component as defined by increased PVR present an even worse prognosis as compared to patients with isolated post-capillary or no PH who present comparable 1-year mortality rates.

Assessment of Stiffness of Large to Small Arteries in Multistage Renal Disease Model: A Numerical Study.

Arterial stiffness (AS), as assessed via pulse wave velocity (PWV), is a major biomarker for cardiovascular risk assessment in patients with chronic kidney disease (CKD). However, the mechanisms responsible for the changes in PWV in the presence of kidney disease are not yet fully elucidated. In the present study, we aimed to investigate the direct effects attributable to biomechanical changes in the arterial tree caused by staged renal removal, independent of any biochemical or compensatory effects. Particularly, we simulated arterial pressure and flow using a previously validated one-dimensional (1-D) model of the cardiovascular system with different kidney configurations: two kidneys (2KDN), one single kidney (1KDN), no kidneys (0KDN), and a transplanted kidney (TX) attached to the external iliac artery. We evaluated the respective variations in blood pressure (BP), as well as AS of large-, medium-, and small-sized arteries via carotid-femoral PWV (cfPWV), carotid-radial PWV (crPWV), and radial-digital PWV (rdPWV), respectively. Our results showed that BP was increased in 1KDN and 0KDN, and that systolic BP values were restored in the TX configuration. Furthermore, a rise was reported in all PWVs for all tested configurations. The relative difference in stiffness from 2KDN to 0KDN was higher in the case of crPWV (15%) in comparison with the increase observed for cfPWV (11%). In TX, we observed a restoration of the PWVs to values close to 1KDN. Globally, it was demonstrated that alterations of the outflow boundaries to the renal arteries with staged kidney removal led to changes in BP and central and peripheral PWV in line with previously reported clinical data. Our findings suggest that the PWV variations observed in clinical practice with different stages of kidney disease may be partially attributed to biomechanical alterations of the arterial tree and their effect on BP.

Estimation of Left Ventricular End-Systolic Elastance From Brachial Pressure Waveform via Deep Learning.

Determination of left ventricular (LV) end-systolic elastance (E es ) is of utmost importance for assessing the cardiac systolic function and hemodynamical state in humans. Yet, the clinical use of E es is not established due to the invasive nature and high costs of the existing measuring techniques. The objective of this study is to introduce a method to assess cardiac contractility, using as a sole measurement an arterial blood pressure (BP) waveform. Particularly, we aim to provide evidence on the potential in using the morphology of the brachial BP waveform and its time derivative for predicting LV E es via convolution neural networks (CNNs). The requirement of a broad training dataset is addressed by the use of an in silico dataset (n = 3,748) which is generated by a validated one-dimensional mathematical model of the cardiovasculature. We evaluated two CNN configurations: 1) a one-channel CNN (CNN1) with only the raw brachial BP signal as an input, and 2) a two-channel CNN (CNN2) using as inputs both the brachial BP wave and its time derivative. Accurate predictions were yielded using both CNN configurations. For CNN1, Pearson's correlation coefficient (r) and RMSE were equal to 0.86 and 0.27 mmHg/ml, respectively. The performance was found to be greatly improved for CNN2 (r = 0.97 and RMSE = 0.13 mmHg/ml). Moreover, all absolute errors from CNN2 were found to be less than 0.5 mmHg/ml. Importantly, the brachial BP wave appeared to be a promising source of information for estimating E es . Predictions were found to be in good agreement with the reference E es values over an extensive range of LV contractility values and loading conditions. Therefore, the proposed methodology could be easily transferred to the bedside and potentially facilitate the clinical use of E es for monitoring the contractile state of the heart in the real-life setting.

The effect of left ventricular contractility on arterial hemodynamics: A model-based investigation.

Ventricular-arterial coupling is a major determinant of cardiovascular performance, however, there are still inherent difficulties in distinguishing ventricular from vascular effects on arterial pulse phenotypes. In the present study, we employed an extensive mathematical model of the cardiovascular system to investigate how sole changes in cardiac contractility might affect hemodynamics. We simulated two physiologically relevant cases of high and low contractility by altering the end-systolic elastance, Ees, (3 versus 1 mmHg/mL) under constant cardiac output and afterload, and subsequently performed pulse wave analysis and wave separation. The aortic forward pressure wave component was steeper for high Ees, which led to the change of the total pressure waveform from the characteristic Type A phenotype to Type C, and the decrease in augmentation index, AIx (-2.4% versus +18.1%). Additionally, the increase in Ees caused the pulse pressure amplification from the aorta to the radial artery to rise drastically (1.86 versus 1.39). Our results show that an increase in cardiac contractility alone, with no concomitant change in arterial properties, alters the shape of the forward pressure wave, which, consequently, changes central and peripheral pulse phenotypes. Indices based on the pressure waveform, like AIx, cannot be assumed to reflect only arterial properties.

Acute and Long-Term Effects of Aortic Compliance Decrease on Central Hemodynamics: A Modeling Analysis.

Aortic compliance is an important determinant of cardiac afterload and a contributor to cardiovascular morbidity. In the present study, we sought to provide in silico insights into the acute as well as long-term effects of aortic compliance decrease on central hemodynamics. To that aim, we used a mathematical model of the cardiovascular system to simulate the hemodynamics (a) of a healthy young adult (baseline), (b) acutely after banding of the proximal aorta, (c) after the heart remodeled itself to match the increased afterload. The simulated pressure and flow waves were used for subsequent wave separation analysis. Aortic banding induced hypertension (SBP 106 mmHg at baseline versus 152 mmHg after banding), which was sustained after left ventricular (LV) remodeling. The main mechanism that drove hypertension was the enhancement of the forward wave, which became even more significant after LV remodeling (forward amplitude 30 mmHg at baseline versus 60 mmHg acutely after banding versus 64 mmHg after remodeling). Accordingly, the forward wave's contribution to the total pulse pressure increased throughout this process, while the reflection coefficient acutely decreased and then remained roughly constant. Finally, LV remodeling was accompanied by a decrease in augmentation index (AIx 13% acutely after banding versus -3% after remodeling) and a change of the central pressure wave phenotype from the characteristic Type A ("old") to Type C ("young") phenotype. These findings provide valuable insights into the mechanisms of hypertension and provoke us to reconsider our understanding of AIx as a solely arterial parameter.

On the assessment of arterial compliance from carotid pressure waveform.

In a progressively aging population, it is of utmost importance to develop reliable, noninvasive, and cost-effective tools to estimate biomarkers that can be indicative of cardiovascular risk. Various pathophysiological conditions are associated to changes in the total arterial compliance (CT), and thus, its estimation via an accurate and simple method is valuable. Direct noninvasive measurement of CT is not feasible in the clinical practice. Previous methods exist for indirect estimation of CT, which, however, require noninvasive, yet complex and expensive, recordings of the central pressure and flow. Here, we introduce a novel, noninvasive method for estimating CT from a single carotid waveform measurement using regression analysis. Features were extracted from the carotid wave and were combined with demographic data. A prediction pipeline was adopted for estimating CT using, first, a feature-based regression analysis and, second, the raw carotid pulse wave. The proposed methodology was appraised using the large human cohort (N = 2,256) of the Asklepios study. Accurate estimates of CT were yielded for both prediction schemes, namely, r = 0.83 and normalized root mean square error (nRMSE) = 9.58% for the feature-based model, and r = 0.83 and nRSME = 9.67% for the model that used the raw signal. The major advantage of this method pertains to the simplification of the technique offering easily applicable and convenient CT monitoring. Such an approach could offer promising applications, ranging from fast and cost-efficient hemodynamical monitoring by the physician to integration in wearable technologies.NEW & NOTEWORTHY This article introduces a novel artificial intelligence method to estimate total arterial compliance (CT) via exploiting the information provided by an uncalibrated carotid blood pressure waveform as well as typical clinical variables. The major finding of this study is that CT, which is usually acquired using both pressure and flow waveforms, can be accurately derived by the use of the pressure wave alone. This method could potentially facilitate easily applicable and convenient monitoring of CT.

AI-Based Estimation of End-Systolic Elastance From Arm-Pressure and Systolic Time Intervals.

Left ventricular end-systolic elastance (Ees) is a major determinant of cardiac systolic function and ventricular-arterial interaction. Previous methods for the Ees estimation require the use of the echocardiographic ejection fraction (EF). However, given that EF expresses the stroke volume as a fraction of end-diastolic volume (EDV), accurate interpretation of EF is attainable only with the additional measurement of EDV. Hence, there is still need for a simple, reliable, noninvasive method to estimate Ees. This study proposes a novel artificial intelligence-based approach to estimate Ees using the information embedded in clinically relevant systolic time intervals, namely the pre-ejection period (PEP) and ejection time (ET). We developed a training/testing scheme using virtual subjects (n = 4,645) from a previously validated in-silico model. Extreme Gradient Boosting regressor was employed to model Ees using as inputs arm cuff pressure, PEP, and ET. Results showed that Ees can be predicted with high accuracy achieving a normalized RMSE equal to 9.15% (r = 0.92) for a wide range of Ees values from 1.2 to 4.5 mmHg/ml. The proposed model was found to be less sensitive to measurement errors (±10-30% of the actual value) in blood pressure, presenting low test errors for the different levels of noise (RMSE did not exceed 0.32 mmHg/ml). In contrast, a high sensitivity was reported for measurements errors in the systolic timing features. It was demonstrated that Ees can be reliably estimated from the traditional arm-pressure and echocardiographic PEP and ET. This approach constitutes a step towards the development of an easy and clinically applicable method for assessing left ventricular systolic function.

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.

In vivo application and validation of a novel noninvasive method to estimate the end-systolic elastance.

Accurate assessment of the left ventricular (LV) systolic function is indispensable in the clinic. However, estimation of a precise index of cardiac contractility, i.e., the end-systolic elastance (Ees), is invasive and cannot be established as clinical routine. The aim of this work was to present and validate a methodology that allows for the estimation of Ees from simple and readily available noninvasive measurements. The method is based on a validated model of the cardiovascular system and noninvasive data from arm-cuff pressure and routine echocardiography to render the model patient-specific. Briefly, the algorithm first uses the measured aortic flow as model input and optimizes the properties of the arterial system model to achieve correct prediction of the patient's peripheral pressure. In a second step, the personalized arterial system is coupled with the cardiac model (time-varying elastance model) and the LV systolic properties, including Ees, are tuned to predict accurately the aortic flow waveform. The algorithm was validated against invasive measurements of Ees (multiple pressure-volume loop analysis) taken from n = 10 patients with heart failure with preserved ejection fraction and n = 9 patients without heart failure. Invasive measurements of Ees (median = 2.4 mmHg/mL, range = [1.0, 5.0] mmHg/mL) agreed well with method predictions (normalized root mean square error = 9%, ρ = 0.89, bias = -0.1 mmHg/mL, and limits of agreement = [-0.9, 0.6] mmHg/mL). This is a promising first step toward the development of a valuable tool that can be used by clinicians to assess systolic performance of the LV in the critically ill.NEW & NOTEWORTHY In this study, we present a novel model-based method to estimate the left ventricular (LV) end-systolic elastance (Ees) according to measurement of the patient's arm-cuff pressure and a routine echocardiography examination. The proposed method was validated in vivo against invasive multiple-loop measurements of Ees, achieving high correlation and low bias. This tool could be most valuable for clinicians to assess the cardiovascular health of critically ill patients.

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.