Explore the vast range of titles available.

Background and Objectives: Contrast-associated acute kidney injury (CA-AKI) is a frequent and clinically significant complication in patients with acute myocardial infarction (AMI) undergoing coronary angiography. Early and accurate risk stratification remains challenging with conventional models that rely on linear assumptions and limited variable integration. This study aimed to evaluate and compare the predictive performance of multiple machine learning (ML) algorithms with traditional logistic regression and the Mehran risk score for CA-AKI prediction and to explore key determinants of risk using explainable artificial intelligence methods. Materials and Methods: This retrospective, single-center study included 1741 patients with AMI who underwent coronary angiography. CA-AKI was defined according to KDIGO criteria. Multiple ML models, including gradient boosting machine (GBM), random forest (RF), XGBoost, support vector machine, elastic net, and standard logistic regression were developed using routinely available clinical and laboratory variables. A weighted ensemble model combining the best-performing algorithms was constructed. Model discrimination was assessed using area under the receiver operating characteristic curve (AUC), along with sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Model interpretability was evaluated using feature importance and SHapley Additive exPlanations (SHAP). Results: CA-AKI occurred in 356 patients (20.4%). In multivariable logistic regression, lower left ventricular ejection fraction, higher contrast volume, lower sodium, lower hemoglobin, and higher neutrophil-to-lymphocyte ratio (NLR) were independently associated with CA-AKI. Among ML approaches, the weighted ensemble model demonstrated the highest discriminative performance (AUC 0.721), outperforming logistic regression and the Mehran risk score (AUC 0.608). Importantly, the ensemble model achieved a consistently high NPV (0.942), enabling reliable identification of low-risk patients. Explainability analyses revealed that inflammatory markers, particularly NLR, along with sodium, uric acid, baseline renal indices, and contrast burden, were the most influential predictors across models. Conclusions: In patients with AMI undergoing coronary angiography, interpretable ML models, especially ensemble and gradient boosting-based approaches, provide superior risk stratification for CA-AKI compared with conventional methods. The high negative predictive value highlights their clinical utility in safely identifying low-risk patients and supporting individualized, risk-adapted preventive strategies.

Background and Objectives: In this study, we aimed to investigate the prognostic value of the C-reactive protein to albumin ratio (CAR) for all-cause mortality in patients with chronic heart failure with reduced ejection fraction (HFrEF). Materials and Methods: In total, 404 chronic HFrEF patients were included in this observational and retrospective study. The CAR value of each patient included in this analysis was calculated. We stratified the study population into tertiles (T1, T2, and T3) according to CAR values. The primary outcome of the analysis was to determine all-cause mortality. Results: The median follow-up period in our study was 30 months. In the follow-up, 162 (40%) patients died. The median value of CAR was higher in patients who did not survive during the follow-up [6.7 (IQR = 1.6–20.4) vs. 0.6 (IQR = 0.1–2.6), p < 0.001]. In addition, patients in the T3 tertile (patients with the highest CAR) had a higher rate of all-cause mortality [n = 90 cases (66.2%), p < 0.001]. Multivariate Cox regression analysis revealed that CAR was an independent predictor of mortality in patients with HFrEF (hazard ratio: 1.852, 95% confidence interval: 1.124–2.581, p = 0.005). In a receiver operating characteristic curve analysis, the optimal cut-off value of CAR was >2.78, with a sensitivity of 66.7% and specificity of 76%. Furthermore, older age, elevated N-terminal pro-brain natriuretic peptide levels, and absence of a cardiac device were also independently associated with all-cause death in HFrEF patients after 2.5 years of follow-up. Conclusions: The present study revealed that CAR independently predicts long-term mortality in chronic HFrEF patients. CAR may be used to predict mortality among these patients as a simple and easily obtainable inflammatory marker.

: Conventional risk models may not adequately capture key biological determinants of mortality following transcatheter aortic valve implantation (TAVI), such as inflammation, malnutrition, and immune dysfunction. The Osaka Prognostic Score (OPS), incorporating CRP, albumin, and lymphocyte count, may address this gap. We aimed to evaluate the prognostic value of OPS for predicting in-hospital and one-year all-cause mortality after TAVI. : In this retrospective single-center cohort study, 244 patients who underwent transfemoral TAVI between December 2022 and January 2024 were analyzed. OPS was calculated at baseline (range: 0-3), and its prognostic value for in-hospital and one-year all-cause mortality was evaluated using multivariable Cox regression, ROC analysis, and restricted cubic spline (RCS) modeling. : In-hospital and one-year mortality rates were 11.5% and 21.7%, respectively. Higher OPS scores were significantly associated with mortality in both periods. OPS independently predicted in-hospital mortality (HR: 2.018; 95% CI: 1.632-2.521; = 0.017) and one-year mortality (HR: 2.125; 95% CI: 1.300-3.473; = 0.003). ROC analysis yielded AUC values of 0.776 and 0.859 for in-hospital and one-year mortality, respectively. Kaplan-Meier curves revealed significantly reduced survival in patients with higher OPS (log-rank < 0.001), and RCS analysis demonstrated a significant nonlinear association between increasing OPS values and mortality risk ( < 0.001). : OPS is a simple, cost-effective, and biologically relevant prognostic index that independently predicts both in-hospital and one-year mortality following TAVI. By integrating markers of inflammation, nutrition, and immune competence, OPS may offer additional value in risk stratification and support clinical decision-making in this high-risk population.

Background: Early risk stratification in acute decompensated heart failure with reduced ejection fraction (ADHF-rEF) remains challenging. The Endothelial Activation and Stress Index (EASIX)—a composite of lactate dehydrogenase, creatinine, and platelet count—reflects endothelial dysfunction, a pathophysiological contributor to early deterioration in ADHF-rEF. This study evaluated the prognostic utility of admission-based EASIX for in-hospital mortality. Methods: In this retrospective single-center cohort, 850 consecutive patients hospitalized with ADHF-rEF between January 2022 and June 2025 were analyzed. EASIX was calculated from first-day laboratory values. Logistic regression, ROC analysis, restricted cubic splines, and Kaplan–Meier survival methods were used to assess the association between EASIX and in-hospital mortality, and to evaluate its incremental value beyond established clinical and laboratory predictors. Results: In-hospital mortality was 12.4%. Higher EASIX values were significantly associated with mortality in both univariable and multivariable models (adjusted OR 1.273; p < 0.001). EASIX demonstrated moderate discriminative performance among evaluated biomarkers (AUC 0.751) and showed a clear dose–response risk gradient, with mortality rising from 1.4% in the lowest tertile to 26.2% in the highest. Incorporating EASIX into clinical and laboratory prediction models yielded substantial continuous net reclassification improvement (0.59 and 0.38, respectively). Survival curves diverged early and remained distinctly separated across EASIX strata. Conclusions: Admission EASIX is an independent predictor of in-hospital mortality in ADHF-rEF and provides complementary prognostic information beyond conventional models. This is the first study to demonstrate the prognostic value of EASIX in the ADHF-rEF setting, supporting its potential utility as an accessible endothelial stress biomarker for early risk stratification.

Background Prosthetic heart valve thrombosis (PHVT) is a serious and potentially life-threatening complication that affects patients with mechanical heart valves. Timely and precise prediction of PHVT is essential for prompt intervention. This study aims to assess the association between the ratio of red blood cell distribution width (RDW) and platelet (PLT) count with PHVT. Methods We conducted a retrospective analysis of 297 transesophageal echocardiography examinations performed between January 2007 and October 2022 on patients with mechanical mitral prosthetic valves. This cohort included 161 patients diagnosed with PHVT and 136 patients with functional prosthetic valves. Results Patients with PHVT were, on average, older than those with normofunctional valves (56 vs 53 years, p = .046). Univariable analysis indicated that advanced age, heart failure (HF), chronic renal failure, COPD, reduced LVEF, ineffective anticoagulation, elevated D-dimer levels, and an elevated RDW-to-PLT ratio were associated with PHVT. The multivariable logistic regression analysis identified elevated RDW-to-PLT ratio (OR: 1.278, 95% CI: 1.142-1.327, p = .001), ineffective anticoagulation, HF, and D-dimer were independently associated with PHVT. The ROC curve analysis demonstrated that the RDW-to-PLT ratio exhibited moderate diagnostic performance, with a cut-off value of 0.065, sensitivity of 65%, and specificity of 66%. Conclusion This is the first study demonstrating that the higher RDW-to-PLT ratio is associated with PHVT. Further studies are necessary to validate these findings in broader clinical settings.