Usefulness of Estimated Pulse Wave Velocity in Prediction of Cardiovascular Mortality in Patients With Acute Myocardial Infarction

Predictive value of machine learning for in-hospital mortality risk in acute myocardial infarction: A systematic review and meta-analysis

BACKGROUND

Machine learning (ML) models have been constructed to predict the risk of in-hospital mortality in patients with myocardial infarction (MI). Due to diverse ML models and modeling variables, along with the significant imbalance in data, the predictive accuracy of these models remains controversial.

OBJECTIVE

This study aimed to review the accuracy of ML in predicting in-hospital mortality risk in MI patients and to provide evidence-based advices for the development or updating of clinical tools.

METHODS

PubMed, Embase, Cochrane, and Web of Science databases were searched, up to June 4, 2024. PROBAST and ChAMAI checklist are utilized to assess the risk of bias in the included studies. Since the included studies constructed models based on severely unbalanced datasets, subgroup analyses were conducted by the type of dataset (balanced data, unbalanced data, model type).

RESULTS

This meta-analysis included 32 studies. In the validation set, the pooled C-index, sensitivity, and specificity of prediction models based on balanced data were 0.83 (95 % CI: 0.795-0.866), 0.81 (95 % CI: 0.79-0.84), and 0.82 (95 % CI: 0.78-0.86), respectively. In the validation set, the pooled C-index, sensitivity, and specificity of ML models based on imbalanced data were 0.815 (95 % CI: 0.789-0.842), 0.66 (95 % CI: 0.60-0.72), and 0.84 (95 % CI: 0.83-0.85), respectively.

CONCLUSIONS

ML models such as LR, SVM, and RF exhibit high sensitivity and specificity in predicting in-hospital mortality in MI patients. However, their sensitivity is not superior to well-established scoring tools. Mitigating the impact of imbalanced data on ML models remains challenging.

Estimated Pulse Wave Velocity Is Associated With All-Cause Mortality and Cardiovascular Mortality Among Adults With Chronic Kidney Disease

This study aimed to assess the correlation between estimated pulse wave velocity (ePWV) and mortality rates related to all-cause and cardiovascular disease (CVD) among individuals diagnosed with chronic kidney disease (CKD) in the United States. A total of 4669 participants with CKD were identified from the National Health and Nutrition Examination Survey conducted between 1999 and 2018. We calculated the incidence of CKD using an estimated glomerular filtration rate (eGFR) of < 60 mL/min/1.73 m2. Our study examined the association between ePWV and mortality risk based on weighted Kaplan-Meier plots and multivariate Cox regression. Linear testing between ePWV and mortality from all causes and CVD was performed using restricted cubic splines and Cox regression. This study included 4669 patients with CKD from the NHANES, representing 37 million Americans with CKD. There was a mean age of 71.9 years, and 48.1% of participants were male. With every increase of 1 m/s in ePWV measurement, there is a corresponding 31% (hazard ratio [HR]: 1.31, 95% confidence interval [CI]: 1.28-1.34) increase in the rate of mortality from all causes and a 32% (HR: 1.32, 95% CI: 1.27-1.37) increase in the rate of mortality from CVD. A significantly higher rate of cardiovascular and all-cause mortality was observed in patients with CKD with elevated ePWV than in those with lower ePWV, as shown in the weighted Kaplan-Meier plots. Patients with CKD have a significant relationship between ePWV and all-cause and cardiovascular mortality.

Association between estimated pulse wave velocity and the risk of mortality in patients with subarachnoid hemorrhage: a retrospective cohort study based on the MIMIC database

BACKGROUND

The estimated pulse wave velocity (ePWV) is a recently developed, simple and useful tool to measure arterial stiffness and to predict long-term cardiovascular mortality. However, the association of ePWV with mortality risk in patients with subarachnoid hemorrhage (SAH) is unclear. Herein, this study aims to assess the potential prediction value of ePWV on short- and long-term mortality of SAH patients.

METHODS

Data of adult patients with no traumatic SAH were extracted from the Medical Information Mart for Intensive Care (MIMIC) III and IV database in this retrospective cohort study. Weighted univariate and multivariable Cox regression analyses were used to explore the associations of ePWV levels with 30-day mortality and 1-year mortality in SAH patients. The evaluation indexes were hazard ratios (HRs) and 95% confidence intervals (CIs). In addition, subgroup analyses of age, the sequential organ failure assessment (SOFA) score, surgery, atrial fibrillation (AF), renal failure (RF), hepatic diseases, chronic obstructive pulmonary disease (COPD), sepsis, hypertension, and diabetes mellitus (DM) were also performed.

RESULTS

Among 1,481 eligible patients, 339 died within 30 days and 435 died within 1 year. After adjusting for covariates, ePWV ≥ 12.10 was associated with higher risk of both 30-day mortality (HR = 1.77, 95%CI: 1.17-2.67) and 1-year mortality (HR = 1.97, 95%CI: 1.36-2.85), compared to ePWV < 10.12. The receiver operator characteristic (ROC) curves showed that compared to single SOFA score, ePWV combined with SOFA score had a relative superior predictive performance on both 30-day mortality and 1-year mortality, with the area under the curves (AUCs) of 0.740 vs. 0.664 and 0.754 vs. 0.658. This positive relationship between ePWV and mortality risk was also found in age ≥ 65 years old, SOFA score < 2, non-surgery, non-hepatic diseases, non-COPD, non-hypertension, non-DM, and sepsis subgroups.

CONCLUSION

Baseline ePWV level may have potential prediction value on short- and long-term mortality in SAH patients. However, the application of ePWV in SAH prognosis needs further clarification.

Estimated pulse wave velocity as a predictor of all-cause and cardiovascular mortality in patients with hypertension in China: a prospective cohort study

Background

Whether the estimated pulse wave velocity (ePWV) in Chinese patients with hypertension can serve as an independent predictor of cardiovascular and all-cause mortality remains unknown. Therefore, this study investigated the associations between ePWV and cardiovascular and all-cause mortalities and explored potential effect modifiers influencing these relationships. Finally, we compared the ePWV with the brachial-ankle pulse wave velocity (baPWV) to determine which parameter better predicts mortality.

Methods

The population of this longitudinal cohort study was selected from the China H-type Hypertension Registry Study. The exposure and outcome variables were ePWV and all-cause and cardiovascular mortalities, respectively. The Cox proportional hazard regression model was applied to assess the associations between ePWV and all-cause and cardiovascular mortalities. The performances of ePWV and baPWV in predicting death were compared using the receiver operating characteristic (ROC) curve area, net reclassification improvement index (NRI), and integrated discrimination improvement index (IDI).

Results

This prospective study enrolled 14,232 patients with hypertension. Following an average follow-up of 48 months, 806 individuals succumbed to all-cause mortality, with 397 cases specifically attributed to cardiovascular diseases. The Cox proportional regression analysis revealed a significant association between a 1 m/s increase in ePWV and a 37% higher risk of all-cause mortality (hazard ratio [HR]: 1.37, 95% confidence interval [CI]: 1.31-1.43) as well as a 52% higher risk of cardiovascular mortality (HR: 1.52, 95% CI: 1.43-1.62) in the fully adjusted model. The findings for ePWV according to quartile demonstrated hazard ratios for all-cause mortality for Q2 (10.25 < ePWV < 11.32), Q3 (11.32 < ePWV < 12.40), and Q4 (ePWV ≥ 12.40) of 1.50 (HR: 1.50, 95% CI: 1.07-2.10), 2.34 (HR: 2.34, 95% CI: 1.73-3.18), and 4.09 (HR: 4.09, 95% CI: 3.05-5.49), respectively, compared with Q1 (ePWV < 10.25). The risk of cardiovascular death also increased in proportion to the rise in ePWV. The results of the area under the ROC curve, NRI, and IDI all indicated that ePWV outperformed baPWV in predicting mortality. The results of the subgroup analysis demonstrated that body mass index (BMI) and hypoglycemic drug use modified the association between ePWV and mortality.

Conclusions

The performance of ePWV in predicting all-cause and cardiovascular mortalities was superior to that of baPWV alone. Patients who were overweight or obese with higher ePWV values exhibited a significantly increased risk of all-cause death. The correlation between elevated ePWV and the risk of cardiovascular death was more pronounced in patients who had not received hypoglycemic drugs.

Predictive value of estimated pulse wave velocity with all-cause and cause-specific mortality in the hypertensive population: the National Health and Nutrition Examination Surveys 1999-2014

BACKGROUND

Estimated pulse wave velocity (ePWV) has been proposed as a potential approach to assess carotid-femoral pulse wave velocity (cfPWV). However, the potential ability of ePWV to predict all-cause and cause-specific mortality in the population group with hypertension remains unresolved.

METHODS

We conducted a prospective cohort study using the data of 14 044 adults (age ≥18 years) from the National Health and Nutrition Examination Survey (NHANES) from 1999 to 2014, and followed this cohort until the end of December 2019. ePWV was calculated by using a regression equation for age and mean blood pressure (MBP), derived by the Arterial Stiffness Collaborative Group.

RESULTS

The weighted mean age of the 14 044 adults included was 54.79 years; 49.42% of all participants were men. During the median follow-up period of 11 years, 3795 deaths were recorded. In the fully adjusted cox regression model, each 1 m/s increase in ePWV was associated with an increased risk of 56% [hazard ratio 1.61; 95% confidence interval (CI) 1.49-1.64] risk for all-cause mortality. Every 1 m/s increase in ePWV resulted in an increased risk of mortality from cardiovascular disease, cerebrovascular disease, respiratory disease, Alzheimer's disease, accidents, cancer, influenza and pneumonia by 60, 70, 47, 118, 73, 41 and 103%, respectively. ePWV has a robust predictive value for 5- and 10-year all-cause mortality in the hypertensive population with AUCs of 0.749 and 0.741, respectively.

CONCLUSION

Elevated ePWV is positively correlated with all-cause mortality and most cause-specific mortalities, independent of traditional risk factors. Moreover, ePWV demonstrates high accuracy in predicting 5-year and 10-year all-cause mortality, outperforming Framingham Risk Score.

Predictive value of estimated pulse wave velocity for cardiovascular and all-cause mortality in individuals with obesity

BACKGROUND

Estimated pulse wave velocity (ePWV) has revealed excellent performance in predicting cardiovascular disease (CVD) risk. However, whether ePWV predicts all-cause mortality and CVD mortality in populations with obesity remains elusive.

METHODS

We performed a prospective cohort including 49,116 participants from the National Health and Nutrition Examination Survey from 2005 to 2014. Arterial stiffness was evaluated by ePWV. Weighted univariate, multivariate Cox regression and receiver operating characteristic curve (ROC) analysis was used to assess the effects of ePWV on the risk of all-cause and CVD mortality. In addition, the two-piecewise linear regression analysis was used to describe the trend of ePWV affecting mortality and identify the thresholds that significantly affect mortality.

RESULTS

A total of 9929 participants with obesity with ePWV data and 833 deaths were enrolled. Based on the multivariate Cox regression results, the high ePWV group had a 1.25-fold higher risk of all-cause mortality and a 5.76-fold higher risk of CVD mortality than the low-ePWV group. All-cause and CVD mortality risk increased by 123% and 44%, respectively, for every 1 m/s increase in ePWV. ROC results showed that ePWV had an excellent accuracy in predicting all-cause mortality (AUC = 0.801) and CVD mortality (AUC = 0.806). Furthermore, the two-piecewise linear regression analysis exhibited that the minimal threshold at which ePWV affected participant mortality was 6.7 m/s for all-cause mortality and 7.2 m/s for CVD mortality.

CONCLUSIONS

ePWV was an independent risk factor for mortality in populations with obesity. High ePWV levels were associated with an increased all-cause and CVD mortality. Thus, ePWV can be considered a novel biomarker to assess mortality risk in patients with obesity.

Association of Systemic Immune Inflammation Index with Estimated Pulse Wave Velocity, Atherogenic Index of Plasma, Triglyceride-Glucose Index, and Cardiovascular Disease: A Large Cross-Sectional Study

In the U.S. general population, there is a lack of understanding regarding the association between the systemic immune inflammation (SII) index and estimated pulse wave velocity (ePWV), atherogenic index of plasma (AIP), and triglyceride-glucose (TyG) index and cardiovascular disease (CVD). As a result, the objective of our research was to investigate the association between the SII index and ePWV, AIP, and TyG index and incident CVD. We used the National Health and Nutrition Examination Survey (NHANES) data from 1999 to 2018 to conduct this study. The correlation between the SII index and ePWV, AIP, and TyG index was examined using generalized additive models with smooth functions. In addition, the association between SII index and triglyceride (TC), high-density lipoprotein cholesterol (HDL-C), and fast glucose (FBG) also were explored. Finally, we further performed multivariable logistic regression analysis, restricted cubic spline (RCS) plots, and subgroup analysis to study the connection between the SII index and CVD. Our analysis included 17389 subjects from the NHANES database. A substantial positive association existed between SII, WV, and the TyG index. In addition, with the increase of the SII index, AIP showed a trend of decreasing first, then rising, and then decreasing. The SII index was inversely and linearly associated with triglyceride (TG), while positively and linearly associated with fast glucose (FBG). However, high-density lipoprotein cholesterol (HDL-C) had a tendency of first declining, then climbing, and finally falling with the rise in the SII index. After adjusting for potential confounders, compared with the lowest quartiles, the odds ratios with 95% confidence intervals for CVD across the quartiles were 0.914 (0.777, 1.074), 0.935 (0.779, 1.096), and 1.112 (0.956, 1.293) for SII index. The RCS plot showed an inverse U-shaped curve relationship between the SII index and CVD. Overall, this study found a strong correlation between a higher SII index and ePWV and the TyG index. Additionally, these cross-sectional data also revealed a U-shaped connection between the SII index and CVD.

Association of Estimated Pulse Wave Velocity with Abdominal Aortic Calcification: A Large Cross-Sectional Study

Objectives

There is evidence that pulse wave velocity (PWV) can predict the occurrence of abdominal aortic calcification (AAC), while the association between estimated PWV (ePWV) and AAC has not been reported, so our study aimed to analyze the association between ePWV and AAC.

Methods

The study enrolled 3140 adults between the ages of 40 and 80 who participated in the 2013–2014 National Health and Nutrition Examination Survey. Using multivariate logistic regression analysis, multivariate linear regression and receiver operating characteristic (ROC) curve to evaluate the association between ePWV and AAC.

Results

The ePWV was significantly higher in participants with AAC compared with those without AAC. And ePWV had a high correlation with age and AAC (correlation coefficient = 0.906 and 0.332, both P < 0.001). Individuals in high ePWV group had significantly higher percentage of AAC compared to low ePWV group (OR = 2.971, 95% CI 2.529–3.490, P < 0.001) in the crude model. After adjusting for all confounding variables, ePWV was still significantly higher (Model 3, OR = 1.962, 95% CI 1.612–2.389, P < 0.001). While after adjusting for all confounding variables plus age (Model 4), ePWV, when as a categorical variable, was no longer significantly positively associated with AAC. Additionally, the ROC curve indicated that both ePWV and age had some diagnostic value for AAC (AUC = 0.690, P < 0.001; AUC = 0.708, P < 0.001).

Conclusions

In the age range of 40–80 years, ePWV did have an association with AAC but did not have predictive power beyond age.

Estimated pulse wave velocity is associated with all-cause and cardio-cerebrovascular disease mortality in stroke population: Results from NHANES (2003-2014)

Background

Arterial stiffness is a significant determinant and evaluation of cardio-cerebrovascular disease and all-cause mortality risk in the stroke population. Estimated pulse wave velocity (ePWV) is a well-established indirect measure of arterial stiffness. We examined the association of ePWV with all-cause and cardio-cerebrovascular disease (CCD) mortality in the stroke population in a large sample of US adults.

Methods

The study design was a prospective cohort study with data from the National Health and Nutrition Examination Survey (NHANES) from 2003 to 2014, between the ages of 18-85 years, with follow-up through December 31, 2019. 1,316 individuals with stroke among 58,759 participants were identified and ultimately, 879 stroke patients were included in the analysis. ePWV was calculated from a regression equation using age and mean blood pressure according to the following formula: ePWV = 9.587 - (0.402 × age) + [4.560 × 0.001 × (age²)] - [2.621 × 0.00001 × (age²) × MBP] + (3.176 × 0.001 × age × MBP) - (1.832 × 0.01 × MBP). Survey-weighted Cox regression models were used to assess the association between ePWV and all-cause and CCD mortality risk.

Results

The high ePWV level group had a higher increased risk of all-cause mortality and CCD mortality compared to the low ePWV level group after fully adjusting for covariates. With an increase in ePWV of 1 m/s, the risk of all-cause and CCD mortality increased by 44%-57% and 47%-72% respectively. ePWV levels were linearly correlated with the risk of all-cause mortality (P for nonlinear = 0.187). With each 1 m/s increase in ePWV, the risk of all-cause mortality increased by 44% (HR 1.44, 95% CI: 1.22-1.69; P < 0.001). When ePWV was <12.1 m/s, an increase in ePWV per 1 m/s was associated with a 119% (HR 2.19, 95% CI: 1.43-3.36; P < 0.001) increase in CCD mortality risk; when ePWV was ≥12.1 m/s, an increase in ePWV per 1 m/s was not associated with in CCD mortality risk.

Conclusion

ePWV is an independent risk factor for all-cause and CCD mortality in stroke patients. Higher levels of ePWV are associated with higher all-cause mortality and CCD mortality in stroke patients.

Association of arterial stiffness with all-cause and cause-specific mortality in the diabetic population: A national cohort study

BACKGROUND

Estimated pulse wave velocity (ePWV) has been proposed as a potential alternative to carotid-femoral pulse wave velocity to assess the degree of aortic stiffness, and may predict cardiovascular disease (CVD) outcomes and mortality in the general population. However, whether arterial stiffness estimated by ePWV predicts all-cause and cause-specific mortality in patients with diabetes mellitus (DM) has not been reported.

METHODS

This was a prospective cohort study with data from the National Health and Nutrition Examination Survey (NHANES) from 1999 to 2014 and followed up until the end of December 2019. 5,235U.S. adults with DM (age≥20years) were included in the study. Arterial stiffness was estimated by ePWV. Survey-weighted Cox proportional hazards models were performed to assess the hazard ratios (HRs), and 95% confidence intervals (CIs) for the associations of ePWV with all-cause and cause-specific mortality. Meanwhile, the generalized additive model was used to visually assess the dose-dependent relationship between ePWV and mortality. As a complementary analysis, the relationship between mean blood pressure (MBP) and risk of mortality was also examined. Multiple imputations accounted for missing data.

RESULTS

For the 5,235 DM patients, the weighted mean age was 57.4 years, and 51.07% were male. During a median follow-up period of 115 months (interquartile range 81-155 months; 53,159 person-years), 1,604 all-cause deaths were recorded. In the fully adjusted Cox regression model, every 1 m/s increase in ePWV was associated with 56% (HR 1.56; 95% CI, 1.44 to 1.69) increase in the risk of all-cause. In addition, a nonlinear relationship between ePWV and all-cause mortality was observed (P for non-linear=0.033). Similar results were obtained after subgroup analysis and multiple imputations. Besides, the risk of most cause-specific mortality, except for accident and renal disease-specific mortality, increased from 53% to 102% for every 1 m/s increase in ePWV.

CONCLUSIONS

In the diabetic population, ePWV is independently associated with all-cause and most cause-specific mortality risks. ePWV may be a useful tool for assessing mortality risk.

Association of Increased Pulse Wave Velocity With Long-Term Clinical Outcomes in Patients With Preserved Ankle-Brachial Index After Acute Myocardial Infarction

BACKGROUND

Low ankle-brachial index (ABI) is an established risk factor for long-term cardiovascular outcomes in patients with acute myocardial infarction (AMI), and brachial-ankle pulse wave velocity (ba-PWV) may also be a risk factor. However, there is a significant overlap between low ABI and high ba-PWV. The purpose of this retrospective study was to examine whether increased ba-PWV was associated with long-term clinical outcomes in AMI patients with normal ABI.

METHODS

We included 932 AMI patients with normal ABI and divided them into the high PWV group (≥1,400 cm/s; n=646) and the low PWV group (<1400 cm/s; n=286) according to the ba-PWV values measured during the AMI hospitalisation. The primary endpoint was the major adverse cardiovascular events (MACE) defined as the composite of all-cause death, nonfatal myocardial infarction, and hospitalisation for heart failure.

RESULTS

During the median follow-up duration of 541 days (Q1: 215 days-Q3: 1,022 days), a total of 154 MACE were observed. The Kaplan-Meier curves showed that MACE was more frequently observed in the high PWV group than in the low PWV group (p<0.001). The multivariate Cox hazard analysis revealed that high ba-PWV was significantly associated with MACE (hazard ratio [HR] 1.587; 95% CI 1.002-2.513; p=0.049) after controlling multiple confounding factors.

CONCLUSIONS

High ba-PWV was significantly associated with long-term adverse events in AMI patients with normal ABI. Our results suggest the usefulness of PWV as a prognostic marker in AMI with normal ABI.

Estimated Pulse Wave Velocity Is Associated With All-Cause Mortality During 8.5 Years Follow-up in Patients Undergoing Elective Coronary Angiography

Background

Estimated pulse wave velocity (ePWV) calculated by equations using age and blood pressure has been suggested as a new marker of mortality and cardiovascular risk. However, the prognostic potential of ePWV during long‐term follow‐up in patients with symptoms of stable angina remains unknown.

Methods and Results

In this study, ePWV was calculated in 25 066 patients without diabetes, previous myocardial infarction (MI), stroke, heart failure, or valvular disease (mean age 63.7±10.5 years, 58% male) with stable angina pectoris undergoing elective coronary angiography during 2003 to 2016. Multivariable Cox models were used to assess the association with incident all‐cause mortality, MI, and stroke. Discrimination was assessed using Harrell´s C‐index. During a median follow‐up period of 8.5 years (interquartile range 5.5–11.3 years), 779 strokes, 1233 MIs, and 4112 deaths were recorded. ePWV was associated with all‐cause mortality (hazard ratio [HR] per 1 m/s, 1.13; 95% CI, 1.05–1.21) and MI (HR per 1 m/s 1.23, 95% CI, 1.09–1.39) after adjusting for age, systolic blood pressure, body mass index, smoking, estimated glomerular filtration rate, Charlson Comorbidity Index score, antihypertensive treatment, statins, aspirin, and number of diseased coronary arteries. Compared with traditional risk factors, the adjusted model with ePWV was associated with a minor but likely not clinically relevant increase in discrimination for mortality, 76.63% with ePWV versus 76.56% without ePWV, P<0.05.

Conclusions

In patients with stable angina pectoris, ePWV was associated with all‐cause mortality and MI beyond traditional risk factors. However, the added prediction of mortality was not improved to a clinically relevant extent.