Association of aortic arch and aortic valve calcifications with cardiovascular risk in patients on maintenance hemodialysis

Moderate-severe aortic arch calcification and high serum alkaline phosphatase co-modify the risk of cardiovascular events and mortality among chronic hemodialysis patients

BACKGROUND

Patients with end-stage kidney disease undergoing chronic hemodialysis (HD) have an unparalleled risk of vascular calcification (VC) and high alkaline phosphatase (Alk-P) levels. However, whether VC contributed to the cardiovascular risk modified by serum Alk-P levels was not addressed in the population.

METHODS

A retrospective cohort study was conducted on chronic HD patients, between October 1 and December 31, 2018, with aortic arch calcification (AoAC) scores and serum Alk-P levels. Patients were categorized into four groups: non-to-mild AoAC/low Alk-P, non-to-mild AoAC/high Alk-P, moderate-to-severe AoAC/low Alk-P, and moderate-to-severe AoAC/high Alk-P. The Cox proportional hazard model and Kaplan-Meier analysis were used to evaluate the risks of major adverse cardiovascular effects (MACEs) and cardiovascular and all-cause mortality after multivariate adjustment.

RESULTS

Among 376 chronic HD patients recruited, 125 (33%) had non-to-mild AoAC/low Alk-P, 76 (20%) had non-to-mild AoAC/high Alk-P, 89 (24%) had moderate-to-severe AoAC/low Alk-P, and 86 (23%) had moderate-to-severe AoAC/high Alk-P. After 3 years of follow-up, patients with coexisting moderate-to-severe AoAC and high Alk-P had a higher risk of MACEs (aHR 1.76; 95% CI 1.06-2.92), and cardiovascular (aHR 2.49; 95% CI 1.21-5.11) and all-cause mortality (aHR 2.67; 95% CI 1.39-5.13) compared to those with non-to-mild AoAC/low Alk-P even after adjustments for significant clinical variables.

CONCLUSIONS

In chronic HD patients, moderate to severe AoAC co-existed with high Alk-P levels and enhanced the risk of MACEs and cardiovascular and all-cause mortality. Interventions to attenuate these risk factors simultaneously should be emphasized in this population.

Machine Learning in Predicting Cardiac Events for ESRD Patients: A Framework for Clinical Decision Support

Background/Objectives: Patients with end-stage renal disease (ESRD) are at an increased risk of major adverse cardiac events (MACEs), highlighting the need for accurate risk prediction and personalized interventions. This study aims to develop and evaluate machine learning (ML) models to identify key predictive features and enhance clinical decision-making in MACE risk assessment. Methods: A dataset comprising 84 variables, including patient demographics, laboratory findings, and comorbidities, was analyzed using CatBoost, XGBoost, and LightGBM. Feature selection, cross-validation, and SHAP (SHapley Additive exPlanations) analyses were employed to improve model interpretability and clinical relevance. Results: CatBoost exhibited the highest predictive performance among the models tested, achieving an AUC of 0.745 (0.605-0.83) with balanced sensitivity and specificity. Key predictors of MACEs included antiplatelet use, the grade of left ventricular hypertrophy, and serum albumin levels. SHAP analysis enhanced the interpretability of model outputs, supporting clinician-led risk stratification. Conclusions: This study highlights the potential of ML-based predictive modeling to improve MACE risk assessment in patients with ESRD. The findings support the adoption of ML models in clinical workflows by integrating explainable AI methods to enable individualized treatment planning. Future integration with electronic health record systems may facilitate real-time decision-making and enhance patient outcomes.

Combinations of valvular calcification and serum alkaline phosphatase predict cardiovascular risk among end-stage kidney disease patients

Background

Valvular calcification (VC) refers to the calcified valvular remodeling associated with kidney dysfunction, especially end-stage kidney disease (ESKD). ESKD patients with VC had significantly higher cardiovascular risk than those without. Factors interacted with VC regarding prognostic prediction in this population were seldom investigated. We aimed to examine the potential synergetic effects of VC and alkaline phosphatase (Alk-P) on ESKD patients' cardiovascular risk and mortality.

Methods

ESKD patients undergoing hemodialysis were prospectively enrolled from a medical center in 2018. We identified patients with echocardiography and available serum Alk-P levels. Cox proportional hazard regression was performed to analyze the risk of major adverse cardiovascular events (MACEs), cardiovascular and overall mortality among 4 participant groups (with or without VC versus low or high Alk-P levels). The models were further adjusted for age, sex, and clinical variables.

Results

Of the 309 ESKD patients, 38, 46, 112, and 113 had no VC with low Alk-P, no VC with high Alk-P, VC with low Alk-P, and VC with high Alk-P, respectively. After adjusting for age and sex, patients with VC and high Alk-P had a higher risk of developing MACE, cardiovascular and overall mortality (HR, 3.07, 3.67, 3.65; 95% CI 1.38-6.84, 1.1-12.24, 1.29-10.36, respectively). Patients with VC and high Alk-P remained at higher risk of MACE (HR, 2.76; 95% CI 1.17-6.48) than did those without VC and with low Alk-P.

Conclusion

Serum Alk-P could be used to identify a subgroup of ESKD patients with elevated cardiovascular risk among those with VC.

Vascular Calcification Heterogeneity from Bench to Bedside: Implications for Manifestations, Pathogenesis, and Treatment Considerations

Vascular calcification (VC) is the ectopic deposition of calcium-containing apatite within vascular walls, exhibiting a high prevalence in older adults, and those with diabetes or chronic kidney disease. VC is a subclinical cardiovascular risk trait that increases mortality and functional deterioration. However, effective treatments for VC remain largely unavailable despite multiple attempts. Part of this therapeutic nihilism results from the failure to appreciate the diversity of VC as a pathological complex, with unforeseeable variations in morphology, risk associates, and anatomical and molecular pathogenesis, affecting clinical management strategies. VC should not be considered a homogeneous pathology because accumulating evidence refutes its conceptual and content uniformity. Here, we summarize the pathophysiological sources of VC heterogeneity from the intersecting pathways and networks of cellular, subcellular, and molecular crosstalk. Part of these pathological connections are synergistic or mutually antagonistic. We then introduce clinical implications related to the VC heterogeneity concept. Even within the same individual, a specific artery may exhibit the strongest tendency for calcification compared with other arteries. The prognostic value of VC may only be detectable with a detailed characterization of calcification morphology and features. VC heterogeneity is also evident, as VC risk factors vary between different arterial segments and layers. Therefore, diagnostic and screening strategies for VC may be improved based on VC heterogeneity, including the use of radiomics. Finally, pursuing a homogeneous treatment strategy is discouraged and we suggest a more rational approach by diversifying the treatment spectrum. This may greatly benefit subsequent efforts to identify effective VC therapeutics.

The association of peritoneal dialysis and hemodialysis on mitral and aortic valve calcification associated mortality: a meta-analysis

Cardiac valve calcification (CVC), characterized by the accumulation of calcium in the heart valves, is highly prevalent among patients undergoing dialysis. This meta-analysis aimed to provide an updated summary of recent studies on the prognostic value of CVC in patients undergoing dialysis. We conducted a search of PubMed, Embase, and Web of Science to identify observational studies investigating cardiovascular or all-cause mortality associated with CVC in dialysis patients until March 2023. Hazard ratios (HRs) and the corresponding 95% confidence intervals (CIs) were calculated for the meta-analysis, and the strength and significance of the associations between CVC and mortality outcomes in dialysis patients were assessed. From 6218 initially identified studies, we included 10 critical studies with a total of 3376 dialysis patients in a further meta-analysis. Pooled analyses demonstrated a significant association between CVC and an elevated risk of all-cause and cardiovascular mortality in dialysis patients. In our study, we discovered HRs of 1.592 (95% CI 1.410-1.797) for all-cause mortality and 2.444 (95% CI 1.632-3.659) for cardiovascular mortality. Furthermore, subgroup analysis revealed elevated all-cause mortality among patients with mitral valve calcification (HR 1.572; 95% CI 1.200-2.060) compared to those with aortic valve calcification (HR 1.456; 95% CI 1.105-1.917). Similarly, patients undergoing peritoneal dialysis faced a greater risk for all-cause mortality (HR 2.094; 95% CI 1.374-3.191) than those on hemodialysis (HR 1.553; 95% CI 1.369-1.763). This highlights the possibility of CVC being an independent risk factor for dialysis patients, particularly in relation to mitral valve calcification or peritoneal dialysis.