Comparison of Transcatheter Mitral Valve Repair Versus Surgical Mitral Valve Repair in Patients With Advanced Kidney Disease (from the National Inpatient Sample)

Application of machine learning to predict in-hospital mortality after transcatheter mitral valve repair

INTRODUCTION

Transcatheter mitral valve repair offers a minimally invasive treatment option for patients at high risk for traditional open repair. We sought to develop dynamic machine-learning risk prediction models for in-hospital mortality after transcatheter mitral valve repair using a national cohort.

METHODS

All adult hospitalization records involving transcatheter mitral valve repair were identified in the 2016-2020 Nationwide Readmissions Database. As a result of initial class imbalance, undersampling of the majority class and subsequent oversampling of the minority class using Synthetic Minority Oversampling TEchnique were employed in each cross-validation training fold. Machine-learning models were trained to predict patient mortality after transcatheter mitral valve repair and compared with traditional logistic regression. Shapley additive explanations plots were also developed to understand the relative impact of each feature used for training.

RESULTS

Among 2,450 patients included for analysis, the in-hospital mortality rate was 1.8%. Naïve Bayes and random forest models were the best at predicting transcatheter mitral valve repair postoperative mortality, with an area under the receiver operating characteristic curve of 0.83 ± 0.05 and 0.82 ± 0.04, respectively. Both models demonstrated superior ability to predict mortality relative to logistic regression (P < .001 for both). Medicare insurance coverage, comorbid liver disease, congestive heart failure, renal failure, and previous coronary artery bypass grafting were associated with greater predicted likelihood of in-hospital mortality, whereas elective surgery and private insurance coverage were linked with lower odds of mortality.

CONCLUSION

Machine-learning models significantly outperformed traditional regression methods in predicting in-hospital mortality after transcatheter mitral valve repair. Furthermore, we identified key patient factors and comorbidities linked with greater postoperative mortality. Future work and clinical validation are warranted to continue improving risk assessment in transcatheter mitral valve repair .

Significance of Kidney Disease in Cardiovascular Disease Patients

Cardiorenal syndrome is a condition where is a bidirectional and mutually detrimental relationship between the heart and kidneys. The mechanisms underlying cardiorenal syndrome are multifactorial and complex. Patients with kidney disease exhibit increased cardiovascular risk, presenting as coronary and peripheral artery disease, structural heart disease, arrhythmias, heart failure, and sudden cardiac death, largely occurring because of a systemic proinflammatory state, causing myocardial and vascular remodeling, manifesting as atherosclerotic lesions, vascular and valvular calcification, and myocardial fibrosis, particularly among those with advanced disease. This review summarizes the current understanding and clinical implications of kidney disease in patients with cardiovascular disease.

Managing Heart Failure in Patients on Dialysis: State-of-the-Art Review

Heart failure (HF) and end-stage kidney disease (ESKD) frequently coexist; 1 comorbidity worsens the prognosis of the other. HF is responsible for almost half the deaths of patients on dialysis. Despite patients' with ESKD composing an extremely high-risk population, they have been largely excluded from landmark clinical trials of HF, and there is, thus, a paucity of data regarding the management of HF in patients on dialysis, and most of the available evidence is observational. Likewise, in clinical practice, guideline-directed medical therapy for HF is often down-titrated or discontinued in patients with ESKD who are undergoing dialysis; this is due to concerns about safety and tolerability. In this state-of-the-art review, we discuss the available evidence for each of the foundational HF therapies in ESKD, review current challenges and barriers to managing patients with HF on dialysis, and outline future directions to optimize the management of HF in these high-risk patients.

Transcatheter Mitral Valve Replacement: Current Evidence and Concepts

Over the past decade, several transcatheter devices have been developed to address the treatment of severe mitral regurgitation (MR) in patients at high surgical risk, mainly aimed at repairing the native mitral valve (MV). MV repair devices have recently been shown to have high efficacy and safety. However, to replicate promising trial results, specific anatomical and pathophysiological criteria have to be met and operators need a high level of experience. As yet, the longer-term durability of transcatheter MV repair remains unknown. Transcatheter MV replacement (TMVR) might be a treatment option able to target various anatomies, reliably abolish MR, and foster ease of use with a standardised implantation protocol. This review presents upcoming TMVR devices and available data and discusses how TMVR might further advance the field of transcatheter treatment of MR.

Cardiovascular Disease in Chronic Kidney Disease: Pathophysiological Insights and Therapeutic Options

Patients with chronic kidney disease (CKD) exhibit an elevated cardiovascular risk manifesting as coronary artery disease, heart failure, arrhythmias, and sudden cardiac death. Although the incidence and prevalence of cardiovascular events is already significantly higher in patients with early CKD stages (CKD stages 1-3) compared with the general population, patients with advanced CKD stages (CKD stages 4-5) exhibit a markedly elevated risk. Cardiovascular rather than end-stage kidney disease (CKD stage 5) is the leading cause of death in this high-risk population. CKD causes a systemic, chronic proinflammatory state contributing to vascular and myocardial remodeling processes resulting in atherosclerotic lesions, vascular calcification, and vascular senescence as well as myocardial fibrosis and calcification of cardiac valves. In this respect, CKD mimics an accelerated aging of the cardiovascular system. This overview article summarizes the current understanding and clinical consequences of cardiovascular disease in CKD.

Does the clinical effectiveness of Mitraclip compare with surgical repair for mitral regurgitation?

BACKGROUND

Surgical repair of the mitral valve has long been the established therapy for degenerative mitral regurgitation (MR). Newer transcatheter methods over the last decade, such as the MitraClip, serve to restore mitral function with reduced procedural burden and enhanced recovery. This study aims to compare the shortterm and midterm outcomes of MitraClip insertion with surgical repair for MR.

METHODS

A systematic review of the literature was conducted for studies comparing outcomes between surgical repair and MitraClip. The initial search returned 1850 titles, from which 12 studies satisfied the inclusion criteria (one randomized controlled trial and 11 retrospective studies).

RESULTS

The final analysis comprised 4219 patients (MitraClip 1210; surgery 3009). Operative mortality was not different between the groups (odds ratio [OR] = 1.63, 95% confidence interval [CI]: [0.63-4.23]; p = .317). Length of hospital stay was significantly shorter in the MitraClip group (standardized mean difference [SMD] = 0.882, 95% CI: [0.77-0.99]; p < .001) with considerable heterogeneity (I²  > 90%; p < .001). The rate of reoperation on the mitral valve was lower in the surgical group (OR = 0.392; 95% CI: [0.188-0.817]; p = .012) as was the rate of MR recurrence grade moderate or above (OR = 0.29; 95% CI: [0.19-0.46]; p < .001) during midterm follow up. Long term survival (4-5 years) was also similar between both groups (hazard ratio = 0.70; 95% CI: [0.35-1.41]; p = .323).

CONCLUSIONS

This study highlights the superior midterm durability of surgical valve repair for MR compared with the MitraClip.

Valvular heart disease in patients with chronic kidney disease

Valvular heart disease (VHD) is common in patients with impaired renal function, especially in those with end-stage renal disease (ESRD) undergoing dialysis. Progressive sclerosis and calcification of the valves and valvular annuli are major components of the etiology. These processes typically affect the aortic and mitral valve and can lead to both valvular insufficiency and stenosis. As recommended by the 2017 ESC/EACTS Guidelines for the management of VHD, surgical treatment remains the standard care for most cases of severe VHD. However, chronic kidney disease (CKD) is associated with increased mortality when compared with patients with preserved renal function. Interventional treatment options have emerged as an effective and safe alternative for patients older than 75 years and/or with increased surgical risk. Consequently, in patients with CKD at increased surgical risk who have suitable anatomical morphology, transcatheter replacement and/or repair should be discussed in the interdisciplinary "heart team."

Machine-Learning-Based In-Hospital Mortality Prediction for Transcatheter Mitral Valve Repair in the United States

BACKGROUND

Transcatheter mitral valve repair (TMVR) utilization has increased significantly in the United States over the last years. Yet, a risk-prediction tool for adverse events has not been developed. We aimed to generate a machine-learning-based algorithm to predict in-hospital mortality after TMVR.

METHODS

Patients who underwent TMVR from 2012 through 2015 were identified using the National Inpatient Sample database. The study population was randomly divided into a training set (n = 636) and a testing set (n = 213). Prediction models for in-hospital mortality were obtained using five supervised machine-learning classifiers.

RESULTS

A total of 849 TMVRs were analyzed in our study. The overall in-hospital mortality was 3.1%. A naïve Bayes (NB) model had the best discrimination for fifteen variables, with an area under the receiver-operating curve (AUC) of 0.83 (95% CI, 0.80-0.87), compared to 0.77 for logistic regression (95% CI, 0.58-0.95), 0.73 for an artificial neural network (95% CI, 0.55-0.91), and 0.67 for both a random forest and a support-vector machine (95% CI, 0.47-0.87). History of coronary artery disease, of chronic kidney disease, and smoking were the three most significant predictors of in-hospital mortality.

CONCLUSIONS

We developed a robust machine-learning-derived model to predict in-hospital mortality in patients undergoing TMVR. This model is promising for decision-making and deserves further clinical validation.

Percutaneous mitral valve repair for secondary mitral valve regurgitation: A systematic review and meta-analysis

BACKGROUND

The first two randomized control trials (RCTs) studying the role of MitraClip in patients with secondary mitral regurgitation (MR) had antagonizing results. We, therefore, performed an updated meta-analysis of RCTs and propensity score-matched observational studies investigating the role of MitraClips in patients with secondary MR. A novel method of Kaplan Meier Curve reconstruction from derived individual patient data will be used to compare the survival probability of control groups in COAPT and MITRA HF trail, and hence, access inter-study heterogeneity.

METHODS

Medline and Cochrane databases was used for systematic search. We used the Mantel-Haenszel method with a random-effect model to calculate risk ratio (RR) with 95% confidence interval (CI) and inverse variance method with a random-effect model to calculate the mean difference (MD) with 95% confidence interval (CI). We used a fixed-effect approach for meta-regression.

RESULTS

MitraClip reduced the risk of all-cause mortality [RR: 0.72, CI: 0.55-0.95, P value = 0.02, I2 = 55%, χ²P-value = 0.08] and readmission [RR: 0.62, CI: 0.42-0.92, P value = 0.02, I² = 90%, χ²P-value<0.01] at two years follow-up. There was no effect of MitraClip on change in cardiovascular mortality and 6 m walking distance at 12 months follow-up. Meta-regression indicated left ventricular end diastolic volume and age among the factors affecting outcomes. Reconstructed Kaplan Meier curves confirmed considerable heterogeneity among patients randomized in MITRA HF and COAPT trial.

CONCLUSION

The present meta-analysis confirms the beneficial role of percutaneous mitral valve repair in patients with secondary MR. However, all the results were associated with considerable heterogeneity.

[Valvular heart disease in patients with chronic kidney disease]

Valvular heart disease is a common comorbidity in patients with impaired renal function, especially in those with end-stage renal disease undergoing dialysis. Sclerosis and calcification of the heart valves and the valve ring are particularly relevant in the etiology of the diseases. These typically occur at the aortic and mitral valves and can lead to both insufficiency and stenosis of the affected valve. In the current guidelines of the European Society for Cardiology published in 2017, surgical treatment remains the standard of care for most forms of severe valvular heart disease; however, the presence of chronic kidney disease impairs clinical outcomes and is associated with higher mortality rates when compared to patients with preserved renal function. Catheter-based treatment options have emerged as an effective and safe alternative for patients >75 years and/or with increased surgical risk. Consequently, in patients with appropriate anatomy and elevated risk, interventional treatment options should also be discussed in the heart team.