Current Issue : January-March Volume : 2026 Issue Number : 1 Articles : 5 Articles
Background and Objectives: To date, several machine learning (ML) prognostic prediction models have been investigated for patients with acute myocardial infarction (AMI). However, few studies have compared the prognostic performance of ML techniques in AMI patients who underwent percutaneous coronary intervention (PCI). We sought to compare the prognostic performance among various machine learning techniques to determine which one showed the best prediction ability. Materials and Methods: Using data from the large, multicenter COREA-AMI registry, this study analyzed 10,172 patients to predict major adverse cardiac events (MACEs) at 1 and 5 years. MACE was defined as a composite of cardiac death, myocardial infarction, or cerebrovascular accident. Results: Compared with the four other ML techniques and traditional logistic regression, the random forest (RF) model consistently demonstrated the highest predictive performance. At 5 years, the RF model achieved a superior area under the curve (AUC) of 0.822, an accuracy of 0.804, and an F1 score of 0.870. To ensure clinical interpretability, a SHapley Additive exPlanations analysis was performed on the RF model. It identified key independent predictors for MACEs. The top nonmodifiable predictors included age, renal function, and left ventricular ejection fraction, whereas modifiable risk factors included dual antiplatelet therapy, statin therapy, angiotensin-converting enzyme inhibitor/angiotensin receptor blocker therapy, and adherence to these optimal medical therapy. Conclusions: In this real-world patient cohort, the RF model provided modest improvements in long-term risk stratification, and our findings highlight the continuing importance of guideline-directed medical therapy in determining patient prognosis....
Coronary artery disease (CAD) remains a major cause of mortality worldwide. Among the standard therapeutic approaches are percutaneous coronary interventions (PCI) employing stents. The main limitation of the procedure lies in the permanent stiffening of the vessel wall. The DynamX Bioadaptor, representing a new generation of vascular stents, combines the advantages of standard implants with a unique mechanism—“uncaging.” Its helical structure, linked by a biodegradable material, enables the restoration of the vessel’s natural functions. This breakthrough concept in interventional cardiology holds the potential to establish a new standard of care for patients suffering from CAD. In this work, we aim to synthesize the available evidence concerning the characteristics of the DynamX Bioadaptor and its impact on vascular physiology. We provide a comprehensive review and evaluation of current clinical reports on its use, analyzing the available literature in comparison with other stent technologies. Recognizing that the DynamX Bioadaptor is a relatively recent innovation, we also seek to identify existing gaps in the literature and propose future directions for research to fully assess its long-term clinical potential....
Background/Objectives: The objectives of this study were to determine whether the early initiation of cardiac rehabilitation (CR) within 6 weeks of discharge improves long-term outcomes in patients hospitalized for acute heart failure (HF) and to evaluate whether baseline lysyl oxidase-like 2 (LOXL2) levels affect the response to CR. Methods: We prospectively enrolled patients with acute HF who completed a structured Heart Failure Disease Management Program between January 2019 and July 2022. Participants were categorized into an early-CR group (initiating supervised CR within 6 weeks post-discharge and continuing a home-based program) or a non-CR group. The primary outcome was all-cause mortality. The secondary outcomes included HF rehospitalization and changes in scores on the 12-item Kansas City Cardiomyopathy Questionnaire (KCCQ-12) at 6 and 12 months. A post hoc analysis was conducted to stratify patients by baseline LOXL2 levels in order to assess differential CR effects in relation to the severity of cardiac fibrosis. Results: Out of 162 patients, 34 participated in early CR. After 1:1 propensity score matching, each group contained 33 patients. Over a median follow-up of 2.85 years, the early-CR group experienced lower all-cause mortality (0 vs. 87.2 events per 1000 patient-years; rate difference: −0.087). A subgroup analysis revealed the greatest benefit among patients with LOXL2 levels > 200 pg/mL (0 vs. 172.3 events per 1000 patient-years; rate difference: −0.172). Conclusions: Early post-discharge CR was associated with improved survival in patients with acute HF. The survival benefit was more pronounced in patients with an elevated level of LOXL2, suggesting its potential role as a biomarker for fibrosis-guided CR strategies. Health systems seeking scalability may consider embedding exercise-based and biomarker-guided CR programs within clinical networks early on to improve access while advancing patient-centered care. Further randomized trials are warranted to confirm these findings....
Background/Objectives: Clinical observational studies often encounter missing data, which complicates association evaluation with reduced bias while accounting for confounders. This is particularly challenging in multi-national registries such as those for out-of-hospital cardiac arrest (OHCA), a time-sensitive medical emergency with low survival rates. While various methods for handling missing data exist, observational studies frequently rely on complete-case analysis, limiting representativeness and potentially introducing bias. Our objective was to evaluate the impact of various single imputation methods on association analysis with OHCA registries. Methods: Using a complete dataset (N = 13,274) from the Pan-Asian Resuscitation Outcomes Study (PAROS) registry (1 January 2016–31 December 2020) as reference, we intentionally introduced missing values into selected variables via a Missing At Random (MAR) mechanism. We then compared statistical and machine learning (ML) single imputation methods to assess the association between bystander cardiopulmonary resuscitation (BCPR) and the issuance of a mobile app alert, adjusting for confounders. The impacts of complete-case analysis (CCA) and single imputation methods on conclusions in OHCA research were evaluated. Results: CCA was suboptimal for handling MAR data, resulting in more biased estimates and wider confidence intervals compared to single imputation methods. The missingness-indicator (MxI) method offered a trade-off between bias and ease of implementation. The K-Nearest Neighbours (KNN) method outperformed other imputation approaches, whereas miss- Forest introduced bias under certain conditions. Conclusions: KNN and MxI are easy to use and better alternatives to CCA for reducing bias in observational studies. This study highlights the importance of selecting appropriate imputation methods to ensure reliable conclusions in OHCA research and has broader implications for other registries facing similar missing data challenges....
Background: Advanced heart failure (HF) carries high morbidity and mortality, and deterioration on the heart transplantation (HT) waiting list remains a major challenge. Intermittent outpatient levosimendan has been proposed as a bridge strategy, but the optimal regimen and its impact on peri-transplant outcomes remain uncertain. Within a personalized-medicine framework, we targeted a low-output/INTERMACS 3 phenotype and operationalized an adaptable, protocolized levosimendan pathway focused on perfusion/ congestion stabilization to preserve transplant candidacy. Methods: We conducted a single-center, retrospective cohort study of 25 consecutive adults actively listed for HT between 2019 and 2024, treated with a standardized outpatient program of a 14-day interval of 6 h intravenous levosimendan infusions (target 0.2 μg/kg/min infusions) continued until transplant. Personalization in this program was operationalized through (i) phenotypebased eligibility (low CI and elevated filling pressures despite GDMT), (ii) predefined titration and safety rules for blood pressure, arrhythmias, and renal function, and (iii) individualized continuation until transplant with nurse-supervised monitoring and review of patient trajectories. Baseline characteristics, treatment exposure and safety, changes in hospitalizations and biomarkers, and peri-transplant outcomes were analyzed. Results: Patients were predominantly male (68%), with a mean age of 47.9 ± 17.5 years and severe LV dysfunction (LVEF 30.6 ± 9.8%). Median treatment duration was 131 days (IQR 60–241). No infusions required discontinuation for hypotension or arrhythmia, and no adverse events were directly attributed to levosimendan. Two patients (8%) died on the waiting list, both unrelated to therapy. During treatment, HF hospitalizations decreased significantly compared with the previous 6 months (48% vs. 20%, p = 0.033), renal function remained stable, and NT-proBNP trended downward. Of the 23 patients transplanted, two (9%) underwent urgent HT during decompensation. Post-transplant, vasoplegia occurred in 26%(n = 6 of 23), and 30-day mortality was 9% (n = 2 of 23). Conclusions: By defining the target phenotype, therapeutic goals, and adaptation rules, this study shows how a standardized but flexible outpatient levosimendan regimen can function as a personalized bridge strategy for low-output advanced HF. The approach was associated with fewer hospitalizations, stable renal function, and acceptable peri-transplant outcomes, and merits confirmation in multicenter cohorts with attention to patient heterogeneity and treatment effect refinement....
Loading....