Development of a Personalized Multiclass Classification Model to Detect Blood Pressure Variations Associated with Physical or Cognitive Workload.

Comprehending the regulatory mechanisms influencing blood pressure control is pivotal for continuous monitoring of this parameter. Implementing a personalized machine learning model, utilizing data-driven features, presents an opportunity to facilitate tracking blood pressure fluctuations in various conditions. In this work, data-driven photoplethysmograph features extracted from the brachial and digital arteries of 28 healthy subjects were used to feed a random forest classifier in an attempt to develop a system capable of tracking blood pressure. We evaluated the behavior of this latter classifier according to the different sizes of the training set and degrees of personalization used. Aggregated accuracy, precision, recall, and F1-score were equal to 95.1%, 95.2%, 95%, and 95.4% when 30% of a target subject's pulse waveforms were combined with five randomly selected source subjects available in the dataset. Experimental findings illustrated that incorporating a pre-training stage with data from different subjects made it viable to discern morphological distinctions in beat-to-beat pulse waveforms under conditions of cognitive or physical workload.

Assessing pressure wave components for aortic stiffness monitoring through spectral regression learning.

Aims: The ageing process notably induces structural changes in the arterial system, primarily manifesting as increased aortic stiffness, a precursor to cardiovascular events. While wave separation analysis is a robust tool for decomposing the components of blood pressure waveform, its relationship with cardiovascular events, such as aortic stiffening, is incompletely understood. Furthermore, its applicability has been limited due to the need for concurrent measurements of pressure and flow. Our aim in this study addresses this gap by introducing a spectral regression learning method for pressure-only wave separation analysis. Methods and results: Leveraging data from the Framingham Heart Study (2640 individuals, 55% women), we evaluate the accuracy of pressure-only estimates, their interchangeability with a reference method based on ultrasound-derived flow waves, and their association with carotid-femoral pulse wave velocity (PWV). Method-derived estimates are strongly correlated with the reference ones for forward wave amplitude ( R 2 = 0.91 ), backward wave amplitude ( R 2 = 0.88 ), and reflection index ( R 2 = 0.87 ) and moderately correlated with a time delay between forward and backward waves ( R 2 = 0.38 ). The proposed pressure-only method shows interchangeability with the reference method through covariate analysis. Adjusting for age, sex, body size, mean blood pressure, and heart rate, the results suggest that both pressure-only and pressure-flow evaluations of wave separation parameters yield similar model performances for predicting carotid-femoral PWV, with forward wave amplitude being the only significant factor (P < 0.001; 95% confidence interval, 0.056-0.097). Conclusion: We propose an interchangeable pressure-only wave separation analysis method and demonstrate its clinical applicability in capturing aortic stiffening. The proposed method provides a valuable non-invasive tool for assessing cardiovascular health.

Arterial Stiffness and Heart Failure With Preserved Ejection Fraction.

Heart failure with preserved ejection fraction (HFpEF) is prevalent and associated with a poor prognosis, imposing a significant burden on society. Arterial stiffness is increasingly recognized as a crucial factor in the pathophysiology of HFpEF, affecting diagnosis, management, and prognosis. As a hallmark of vascular aging, arterial stiffness contributes to increased afterload on the left ventricle (LV), leading to diastolic dysfunction, a key feature of HFpEF. Elevated arterial stiffness is linked with common cardiovascular risk factors in HFpEF, such as hypertension, diabetes and obesity, exacerbating the progression of disease. Studies have demonstrated that patients with HFpEF exhibit significantly higher levels of arterial stiffness compared to those without HFpEF, highlighting the value of arterial stiffness measurements as both diagnostic and prognostic tools. Moreover, interventions aimed at reducing arterial stiffness, whether through pharmacological therapies or lifestyle modifications, have shown potential in improving LV diastolic function and patient outcomes. Despite these advancements, the precise mechanisms by which arterial stiffness contributes to HFpEF are still not fully understood, necessitating the need for further research.

Estimated pulse wave velocity as a forefront indicator of developing metabolic syndrome in Korean adults.

BACKGROUND/AIMS: The predictive value of the estimated pulse wave velocity (ePWV) for the development of metabolic syndrome has not yet been extensively explored. This study aimed to fill this gap by evaluating ePWV as a potential predictor of metabolic syndrome development in middle-aged Korean adults. METHODS: Using prospective data obtained from the Ansan-Ansung cohort database, participants without metabolic syndrome at baseline were studied. ePWV was calculated using specific equations based on age and blood pressure. The primary outcome was the incidence of metabolic syndrome during a median follow-up period of 187 months. RESULTS: Among the 6,186 participants, 2,726 (44.1%) developed metabolic syndrome during the follow-up period. ePWV methvalues were categorized into tertiles to assess their predictive value for the development of metabolic syndrome. An ePWV cut-off of 7.407 m/s was identified as a predictor of metabolic syndrome development, with a sensitivity of 0.743 and a specificity of 0.464. Participants exceeding this cut-off, especially those in the third tertile (8.77-14.63 m/s), had a notably higher risk of developing metabolic syndrome. Specifically, the third tertile exhibited a 52.8% cumulative incidence compared with 30.8% in the first tertile. After adjustments, those in the third tertile faced a 1.530-fold increased risk of metabolic syndrome (95% confidence interval, 1.330-1.761). CONCLUSION: ePWV is a significant predictor of the development of metabolic syndrome. This finding underscores the potential of ePWV as a cardiometabolic risk assessment tool and can thus provide useful information for primary prevention strategies.

Aortic pulse wave analysis and functional capacity of heart transplantation candidates: a pilot study.

We compared cardiovascular parameters obtained with the Mobil-O-Graph and functional capacity assessed by the Duke Activity Status Index (DASI) before and after Heart Transplantation (HT) and also compared the cardiovascular parameters and the functional capacity of candidates for HT with a control group. Peripheral and central vascular pressures increased after surgery. Similar results were observed in cardiac output and pulse wave velocity. The significant increase in left ventricular ejection fraction (LVEF) postoperatively was not followed by an increase in the functional capacity. 24 candidates for HT and 24 controls were also compared. Functional capacity was significantly lower in the HT candidates compared to controls. Stroke volume, systolic, diastolic, and pulse pressure measured peripherally and centrally were lower in the HT candidates when compared to controls. Despite the significant increase in peripheral and central blood pressures after surgery, the patients were normotensive. The 143.85% increase in LVEF in the postoperative period was not able to positively affect functional capacity. Furthermore, the lower values of LVEF, systolic volume, central and peripheral arterial pressures in the candidates for HT are consistent with the characteristics signs of advanced heart failure, negatively impacting functional capacity, as observed by the lower DASI score.

Implications of pulse wave velocity and central pulse pressure in heart failure with reduced ejection fraction.

BACKGROUND: Carotid-femoral pulse wave velocity (cfPWV) and central pulse pressure (PP) are recognised as significant indicators of vascular health and predictors of cardiovascular outcomes. In this study, associations between central hemodynamics and left ventricular (LV) echocardiographic parameters were investigated in subjects with heart failure with reduced ejection fraction (HFrEF), comparing the results to healthy individuals. METHODS AND RESULTS: This cross-sectional prospective controlled study included 50 subjects with HFrEF [mean LV ejection fraction (EF) 26 ± 6.5%] and 30 healthy controls (mean LVEF 65.9 ± 5.3%). Pulse wave analysis (PWA) and carotid-femoral pulse wave velocity (cfPWV) were used to measure central hemodynamics and arterial stiffness. The HFrEF group displayed higher cfPWV (8.2 vs. 7.2 m/s, p = 0.007) and lower central (111.3 vs. 121.7 mmHg, p = 0.001) and peripheral (120.1 vs. 131.5 mmHg, p = 0.002) systolic blood pressure. Central pulse pressure (PP) was comparable between the two groups (37.6 vs. 40.4 mmHg, p = 0.169). In the HFrEF group, cfPWV significantly correlated with left ventricular end-diastolic volume (LVEDV) index (mL/m2) and LVEF, with LVEDV index being a significant independent predictor of cfPWV (R2 = 0.42, p = 0.003). Central PP was significantly associated with heart rate, LVEF and LVEDV index, with the latter being a significant independent predictor of central PP (R2 = 0.41, p < 0.001). These correlations were not observed in healthy controls. CONCLUSIONS: Significant associations between central hemodynamic measures and LV echocardiographic parameters were identified, suggesting the potential to use PWA and cfPWV as possible tools for managing HFrEF.

What is the context?Heart failure with reduced ejection fraction (HFrEF) affects millions of people worldwide.Vascular health plays a significant role in the development and progression of HFrEF.This study investigates two indicators of arterial stiffness­pulse wave velocity (PWV) and central pulse pressure (PP)­and their impact on the functioning of the heart in HFrEF patients compared to healthy individuals.What is new?The study found that higher carotid-femoral PWV and central PP, which typically indicate worse vascular health, were associated with better heart function in HFrEF patients. This paradoxical finding suggests that in the context of HFrEF, traditional markers of vascular health may have different implications.The study included non-invasive methods to evaluate these indicators, offering a potential new additional approach for monitoring and managing HFrEF.What is the impact?We could possibly use non-invasively evaluated PWV and central PP (measures of vascular function) as markers of left ventricular function assessment in HFrEF.

Influence of Blood Pressure Reduction on Pulse Wave Velocity in Primary Hypertension: A Meta-Analysis and Comparison With an Acute Modulation of Transmural Pressure.

BACKGROUND: Increased arterial stiffness and pulse wave velocity (PWV) of the aorta and large arteries impose adverse hemodynamic effects on the heart and other organs. Antihypertensive treatment reduces PWV, but it is unknown whether this results from an unloading of stiffer elements in the arterial wall or is due to an alternate functional or structural change that might differ according to class of antihypertensive drug. METHODS: We performed a systematic review and meta-analysis of the effects of different antihypertensive drug classes and duration of treatment on PWV with and without adjustment for change in mean arterial blood pressure (BP; study 1) and compared this to the change in PWV after an acute change in transmural pressure, simulating an acute change in BP (study 2). RESULTS: A total of 83 studies involving 6200 subjects were identified. For all drug classes combined, the reduction of PWV was 0.65 (95% CI, 0.46-0.83) m/s per 10 mm Hg reduction in mean arterial BP, a change similar to that induced by an acute change in transmural pressure in a group of hypertensive subjects. When adjusted for change in mean arterial BP, the reduction in PWV after treatment with beta-blockers or diuretics was less than that after treatment with angiotensin-converting enzyme inhibitors/angiotensin receptor antagonists or calcium channel antagonists. CONCLUSIONS: Reduction in PWV after antihypertensive treatment is largely explained by the reduction in BP, but there are some BP-independent effects. These might increase over time and contribute to better outcomes over the long term, but this remains to be demonstrated in long-term clinical trials.

Make my haemodynamic monitor GREEN: sustainable monitoring solutions.

Anaesthesiologists overwhelmingly favour pulse wave analysis techniques as their primary method to monitor cardiac output during high-risk noncardiac surgery. In patients with a radial arterial catheter in place, pulse wave analysis techniques have the advantage of instantly providing non-operator-dependent and continuous haemodynamic monitoring information. Green pulse wave analysis techniques working with any standard pressure transducer are as reliable as techniques requiring dedicated pressure transducers. They have the advantage of minimising plastic waste and related carbon dioxide emissions, and also significantly reducing hospital costs. The future integration of pulse wave analysis algorithms into multivariable bedside monitors, obviating the need for standalone haemodynamic monitors, could lead to wider use of haemodynamic monitoring solutions by further reducing their cost and carbon footprint.

Impact of respiratory cycle during mechanical ventilation on beat-to-beat right ventricle stroke volume estimation by pulmonary artery pulse wave analysis.

BACKGROUND: The same principle behind pulse wave analysis can be applied on the pulmonary artery (PA) pressure waveform to estimate right ventricle stroke volume (RVSV). However, the PA pressure waveform might be influenced by the direct transmission of the intrathoracic pressure changes throughout the respiratory cycle caused by mechanical ventilation (MV), potentially impacting the reliability of PA pulse wave analysis (PAPWA). We assessed a new method that minimizes the direct effect of the MV on continuous PA pressure measurements and enhances the reliability of PAPWA in tracking beat-to-beat RVSV. METHODS: Continuous PA pressure and flow were simultaneously measured for 2-3 min in 5 pigs using a high-fidelity micro-tip catheter and a transonic flow sensor around the PA trunk, both pre and post an experimental ARDS model. RVSV was estimated by PAPWA indexes such as pulse pressure (SVPP), systolic area (SVSystAUC) and standard deviation (SVSD) beat-to-beat from both corrected and non-corrected PA signals. The reference RVSV was derived from the PA flow signal (SVref). RESULTS: The reliability of PAPWA in tracking RVSV on a beat-to-beat basis was enhanced after accounting for the direct impact of intrathoracic pressure changes induced by MV throughout the respiratory cycle. This was evidenced by an increase in the correlation between SVref and RVSV estimated by PAPWA under healthy conditions: rho between SVref and non-corrected SVSD - 0.111 (0.342), corrected SVSD 0.876 (0.130), non-corrected SVSystAUC 0.543 (0.141) and corrected SVSystAUC 0.923 (0.050). Following ARDS, correlations were SVref and non-corrected SVSD - 0.033 (0.262), corrected SVSD 0.839 (0.077), non-corrected SVSystAUC 0.483 (0.114) and corrected SVSystAUC 0.928 (0.026). Correction also led to reduced limits of agreement between SVref and SVSD and SVSystAUC in the two evaluated conditions. CONCLUSIONS: In our experimental model, we confirmed that correcting for mechanical ventilation induced changes during the respiratory cycle improves the performance of PAPWA for beat-to-beat estimation of RVSV compared to uncorrected measurements. This was demonstrated by a better correlation and agreement between the actual SV and the obtained from PAPWA.

A reliable evaluation approach for multichannel signal denoising algorithms based on a novel arterial pulse acquisition system.

Background: Tactile sensors are utilized to measure multichannel pulse signals in pulse wave analysis (PWA). Owing to noise interferences, researchers have applied various denoising algorithms on multichannel pulse signals. To comprehensively assess these algorithms, numerous evaluation metrics have been proposed. However, these studies did not investigate the noise mechanisms in depth and lacked reference pulse signals, thus making the evaluations insufficiently objective. Materials and methods: An applicable denoising evaluation approach for multichannel pulse signal algorithms based on an arterial pulse acquisition system is established by superimposing real-world multichannel noise to the reference signals. The system, comprising a SphygmoCor and a uniaxial noise acquisition device, allows us to acquire single-reference pulse signals as well as real-world multichannel noise. Results: We assess eight popular denoising algorithms with three evaluation metrics, including amplitude relative error (ARE), mean square error (MSE) and increased percentage signal-noise ratio (SNR%). Our proposed approach provides accurate and objective evaluations of multichannel pulse signal denoising. Notably, classic algorithms for single-channel denoising are not recommended for multichannel denoising. Comparatively, RPCA-based algorithms can denoise pulse signals independently for each channel. Conclusion: This study sets the stage for the establishment of accurate and objective pulse signal denoising evaluations and provides insights for data-driven clinical diagnoses in cardiovascular medicine.

Exploring the Influence of Insulin Resistance on Arterial Stiffness in Healthy Adults: From the Metabolic and Cardiovascular Health Insights of the EVasCu Study.

Previous evidence associates insulin resistance with arterial stiffness in various pathologies, yet limited reports exist in healthy adults. Therefore, this study aims to estimate the association between insulin resistance and arterial stiffness in healthy adults. The cross-sectional EVasCu study enrolled 390 participants (42.05 ± 13.15 years). ANCOVAs, unadjusted (model 1) and adjusted (model 2), explored the association between arterial stiffness markers (aortic Pulse Wave Velocity [aPWV], Augmentation Index [AIx@75] and Cardio-Ankle Vascular Index [CAVI]), and insulin resistance markers (Homeostasis Model Assessment of Insulin Resistance [HOMA-IR], Quantitative Insulin Sensitivity Check Index [QUICKI] and Triglycerides-Glucose [TyG]). In model 1, all insulin resistance markers were associated with aPWV, HOMA-IR and QUICKI were associated with AIx@75, and the TyG index was associated with CAVI. In model 2, HOMA-IR and QUICKI increased aPWV by 0.179 and 0.156 m/s (p = 0.001 and p = 0.011), and AIx@75 by 4.17 and 5.39% (p = 0.009 and p = 0.003). The EVasCu study offers valuable insights into the relationship between insulin resistance and arterial stiffness in healthy adults, providing a deeper understanding of metabolic and cardiovascular health. By examining this influence, we embark on an intriguing exploration of how these factors interplay in the human body.

Assessment of Arterial Stiffness and Biochemical Markers in Systemic Lupus Erythematosus in the Diagnosis of Subclinical Atherosclerosis.

Patients with systemic lupus erythematosus (SLE) are 2-10 times more likely to develop cardiovascular disease (CVD) than the general population. The assessment of the risk of developing CVD is an important direction for further clinical management. The study was conducted retrospectively and included patients with SLE. The aim of the study was to assess the measurements of pulse wave velocity (PWV), carotid intima-media thickness (CIMT), ankle-brachial index (ABI) and biochemical parameters. Subclinical atherosclerosis was also assessed. The study included 98 patients with SLE with an age- and sex-matched control group of 68 healthy adults. Statistical significance was found in the SLE group and the controls for N-terminal fragment of pro-B-type natriuretic peptide (NT proBNP) (144.87 vs. 36.41 pg/mL, p = 0.0018), high-sensitivity cardiac troponin (hs-cTn) (25.43 vs. 6.38 ng/L, p = 0.0303) and D-Dimer levels (0.73 vs. 0.36 µg/mL, p = 0.0088), left CIMT (1.03 vs. 0.62 mm, p < 0.0001), right CIMT (0.93 vs. 0.63 mm, p < 0.0001) and PWV CF (9.74 vs. 7.98 m/s, p = 0.0294). A positive correlation was found between NT proBNP and PWV CF (r = 0.6880, p = 0.0498) and hs-cTn and PVW carotid-femoral (CF) (r = 0.8862, p = 0.0499) in SLE. A positive correlation was reported between PWV CF and systolic blood pressure (r = 0.5025, p = 0.0487). The measurement of carotid-femoral PWV is a simple, non-invasive, and reproducible method and may independently predict future CVD events and their cause. Further studies are warranted to establish the prognostic value of PWV in patients with SLE, as it may be superior to CIMT measurements in the early stages of vascular disorders.

Estimation of aortic stiffness by finger photoplethysmography using enhanced pulse wave analysis and machine learning.

Introduction: Aortic stiffness plays a critical role in the evolution of cardiovascular diseases, but the assessment requires specialized equipment. Photoplethysmography (PPG) and single-lead electrocardiogram (ECG) are readily available in healthcare and wearable devices. We studied whether a brief PPG registration, alone or in combination with single-lead ECG, could be used to reliably estimate aortic stiffness. Methods: A proof-of-concept study with simultaneous high-resolution index finger recordings of infrared PPG, single-lead ECG, and finger blood pressure (Finapres) was performed in 33 participants [median age 44 (range 21-66) years, 19 men] and repeated within 2 weeks. Carotid-femoral pulse wave velocity (cfPWV; two-site tonometry with SphygmoCor) was used as a reference. A brachial single-cuff oscillometric device assessed aortic pulse wave velocity (aoPWV; Arteriograph) for further comparisons. We extracted 136 established PPG waveform features and engineered 13 new with improved coupling to the finger blood pressure curve. Height-normalized pulse arrival time (NPAT) was derived using ECG. Machine learning methods were used to develop prediction models. Results: The best PPG-based models predicted cfPWV and aoPWV well (root-mean-square errors of 0.70 and 0.52 m/s, respectively), with minor improvements by adding NPAT. Repeatability and agreement were on par with the reference equipment. A new PPG feature, an amplitude ratio from the early phase of the waveform, was most important in modelling, showing strong correlations with cfPWV and aoPWV (r = -0.81 and -0.75, respectively, both P < 0.001). Conclusion: Using new features and machine learning methods, a brief finger PPG registration can estimate aortic stiffness without requiring additional information on age, anthropometry, or blood pressure. Repeatability and agreement were comparable to those obtained using non-invasive reference equipment. Provided further validation, this readily available simple method could improve cardiovascular risk evaluation, treatment, and prognosis.

Increasing the sensor channels: a solution for the pressing offsets that cause the physiological parameter inaccuracy in radial artery pulse signal acquisition.

Introduction: In studies of pulse wave analysis, single-channel sensors only adopt single temporal pulse signals without spatial information to show pulse-feeling patterns. Multi-channel arterial pulse signals, also named as three-dimensional pulse images (3DPIs), provide the spatial and temporal characteristics of radial pulse signals. When involving single or few-channel sensors, pressing offsets have substantial impacts on obtaining inaccurate physiological parameters like tidal peak (P2). Methods: This study discovers the pressing offsets in multi-channel pulse signals and analyzes the relationship between the pressing offsets and time of P2 (T2) by qualifying the pressing offsets. First, we employ a data acquisition system to capture 3DPIs. Subsequently, the errorT2 is developed to qualify the pressing offsets. Results: The outcomes display a central low and peripheral high pattern. Additionally, the errorT2 increase as the distances from the artery increase, particularly at the radial ends of the blood flow direction. For every 1 mm increase in distances between sensing elements and center sensing elements, the errorT2 in the radial direction escalates by 4.87%. When the distance is greater than 3.42 mm, the errorT2 experiences a sudden increase. Discussion: The results show that increasing the sensor channels can overcome the pressing offsets in radial pulse signal acquisition.

Mortality and Cardiovascular End Points In Relation to the Aortic Pulse Wave Components: An Individual-Participant Meta-Analysis.

BACKGROUND: Wave separation analysis enables individualized evaluation of the aortic pulse wave components. Previous studies focused on the pressure height with overall positive but differing results. In the present analysis, we assessed the associations of the pressure of forward and backward (Pfor and Pref) pulse waves with prospective cardiovascular end points, with extended analysis for time to pressure peak (Tfor and Tref). METHODS: Participants in 3 IDCARS (International Database of Central Arterial Properties for Risk Stratification) cohorts (Argentina, Belgium, and Finland) aged ≥20 years with valid pulse wave analysis and follow-up data were included. Pulse wave analysis was done using the SphygmoCor device, and pulse wave separation was done using the triangular method. The primary end points consisted of cardiovascular mortality and nonfatal cardiovascular and cerebrovascular events. Multivariable-adjusted Cox regression was used to calculate hazard ratios. RESULTS: A total of 2206 participants (mean age, 57.0 years; 55.0% women) were analyzed. Mean±SDs for Pfor, Pref, Tfor, and Tfor/Tref were 31.0±9.1 mm Hg, 20.8±8.4 mm Hg, 130.8±35.5, and 0.51±0.11, respectively. Over a median follow-up of 4.4 years, 146 (6.6%) participants experienced a primary end point. Every 1 SD increment in Pfor, Tfor, and Tfor/Tref was associated with 27% (95% CI, 1.07-1.49), 25% (95% CI, 1.07-1.45), and 32% (95% CI, 1.12-1.56) higher risk, respectively. Adding Tfor and Tfor/Tref to existing risk models improved model prediction (∆Uno's C, 0.020; P<0.01). CONCLUSIONS: Pulse wave components were predictive of composite cardiovascular end points, with Tfor/Tref showing significant improvement in risk prediction. Pending further confirmation, the ratio of time to forward and backward pressure peak may be useful to evaluate increased afterload and signify increased cardiovascular risk.

Angiotensin Receptor-Neprilysin Inhibition (Sacubitril/Valsartan) Reduces Structural Arterial Stiffness in Middle-Aged Mice.

BACKGROUND: Increasing arterial stiffness is a prominent feature of the aging cardiovascular system. Arterial stiffening leads to fundamental alterations in central hemodynamics with widespread detrimental implications for organ function resulting in significant morbidity and death, and specific therapies to address the underlying age-related structural arterial remodeling remain elusive. The present study investigates the potential of the recently clinically available dual angiotensin receptor-neprilysin inhibitor (ARNI) sacubitril/valsartan (LCZ696) to counteract age-related arterial fibrotic remodeling and stiffening in 1-year-old mice. METHODS AND RESULTS: Treatment of in 1-year-old mice with ARNI (sacubitril/valsartan), in contrast to angiotensin receptor blocker monotherapy (valsartan) and vehicle treatment (controls), significantly decreases structural aortic stiffness (as measured by in vivo pulse-wave velocity and ex vivo aortic pressure myography). This phenomenon appears, at least partly, independent of (indirect) blood pressure effects and may be related to a direct antifibrotic interference with aortic smooth muscle cell collagen production. Furthermore, we find aortic remodeling and destiffening due to ARNI treatment to be associated with improved parameters of cardiac diastolic function in aged mice. CONCLUSIONS: This study provides preclinical mechanistic evidence indicating that ARNI-based interventions may counteract age-related arterial stiffening and may therefore be further investigated as a promising strategy to improve cardiovascular outcomes in the elderly.

Examining arterial pulsation to identify and risk-stratify heart failure subjects with deep neural network.

Hemodynamic parameters derived from pulse wave analysis have been shown to predict long-term outcomes in patients with heart failure (HF). Here we aimed to develop a deep-learning based algorithm that incorporates pressure waveforms for the identification and risk stratification of patients with HF. The first study, with a case-control study design to address data imbalance issue, included 431 subjects with HF exhibiting typical symptoms and 1545 control participants with no history of HF (non-HF). Carotid pressure waveforms were obtained from all the participants using applanation tonometry. The HF score, representing the probability of HF, was derived from a one-dimensional deep neural network (DNN) model trained with characteristics of the normalized carotid pressure waveform. In the second study of HF patients, we constructed a Cox regression model with 83 candidate clinical variables along with the HF score to predict the risk of all-cause mortality along with rehospitalization. To identify subjects using the HF score, the sensitivity, specificity, accuracy, F1 score, and area under receiver operating characteristic curve were 0.867, 0.851, 0.874, 0.878, and 0.93, respectively, from the hold-out cross-validation of the DNN, which was better than other machine learning models, including logistic regression, support vector machine, and random forest. With a median follow-up of 5.8 years, the multivariable Cox model using the HF score and other clinical variables outperformed the other HF risk prediction models with concordance index of 0.71, in which only the HF score and five clinical variables were independent significant predictors (p < 0.05), including age, history of percutaneous coronary intervention, concentration of sodium in the emergency room, N-terminal pro-brain natriuretic peptide, and hemoglobin. Our study demonstrated the diagnostic and prognostic utility of arterial waveforms in subjects with HF using a DNN model. Pulse wave contains valuable information that can benefit the clinical care of patients with HF.

Associations between Erectile Dysfunction and Vascular Parameters: A Systematic Review and Meta-Analysis.

PURPOSE: Erectile dysfunction (ED) is associated with several vascular disorders, but the associations between ED and vascular parameters are still unclear. MATERIALS AND METHODS: We analyzed and synthesized a comprehensive range of studies from PubMed, Web of Science, and Scopus regarding the associations between ED and the following measures: ankle-brachial index (ABI), pulse wave velocity (PWV), intima-media thickness (IMT), nitrate-mediated dilation (NMD), flow-mediated dilation (FMD), augmentation index (AI), endothelial progenitor cells (EPCs) and other vascular parameters. Subgroup analysis was conducted according to specific types of parameters. Study quality was assessed by using the Newcastle-Ottawa Scale. Sensitivity analysis was conducted to confirm the robustness of the pooled results. RESULTS: Fifty-seven studies with 7,312 individuals were included. Twenty-eight studies were considered to be high-quality. ED patients had a 0.11 mm higher IMT (95% confidence interval [CI]: 0.07, 0.15), a 2.86% lower FMD (95% CI: -3.56, -2.17), a 2.34% lower NMD (95% CI: -3.37, -1.31), a 2.83% higher AI (95% CI: 0.02, 5.63), a 1.11 m/s higher PWV (95% CI: 0.01, 2.21), and a 0.72% lower percentage of EPCs (95% CI: -1.19, -0.24) compared to those without ED. However, ABI was similar between ED patients and non-ED individuals. According to sensitivity analysis, the pooled results were robust. CONCLUSIONS: Our study confirmed the associations between ED and several vascular parameters and highlighted the importance of prevention and management of vascular and endothelial dysfunction in ED patients.