Heart failure (HF) as the final stage of cardiovascular disease in the elderly leads to frequent readmissions and seriously affects their quality of life. This study aimed to develop a predictive model for hospital readmission or death during the vulnerable phase in elderly HF patients, and to identify the key associated risk factors. The dataset was randomly divided into 70% training sets and 30% validation sets. Three feature selection methods were applied to the training data, followed by the construction of 18 predictive models using six machine learning (ML) algorithms (XGBoost, LightGBM, AdaBoost, GBDT, GNB, and SVM). The performance of each model was assessed on the validation set using receiver operating characteristic (ROC) curves, sensitivity, accuracy, specificity, F1 score, and Brier score. SHapley Additive exPlanations (SHAP) were used to interpret the feature contributions both globally and locally. Eleven models achieved an area under the ROC curve (AUC) greater than 0.8, with the Boruta‐XGBoost model performing best, showing an AUC of 0.873 in the validation set, along with a sensitivity of 0.839, accuracy of 0.769, specificity of 0.747, F1 score of 0.634, and Brier score of 0.130. SHAP analysis revealed that the top five important features were hemoglobin (HGB), serum free thyroxine (FT4), age, diabetes, and serum potassium (K). The Boruta‐XGBoost based risk prediction model, combined with SHAP interpretation, demonstrated high predictive accuracy and robust interpretability for forecasting hospital readmission or death during the vulnerable phase in elderly HF patients.

Background: Obesity is a major public health concern and has been implicated in the pathogenesis of heart failure (HF). However, the causal nature of this relationship remains to be comprehensively elucidated through robust genetic epidemiological approaches. Objective: This systematic review and meta-analysis aimed to synthesize evidence from Mendelian randomization (MR) studies regarding the causal effects of genetically predicted obesity and related anthropometric traits on HF and its subtypes. Methods: A comprehensive literature search was conducted across PubMed, Google Scholar, Web of Science, Embase, and the Cochrane Library for studies published up to October 2025. Study quality was assessed, and random-effects meta-analysis were performed where applicable. Result: Genetically predicted adult BMI was significantly associated with increased HF risk across European (OR _SD : 1.79; 95% CI: 1.64–1.94), and East Asian ancestries (OR _kg/m ² : 2.17; 95% CI: 1.79–2.63). A significant association was also observed for HF with preserved ejection fraction (HFpEF) in European-ancestry individuals (OR _SD : 2.68; 95% CI: 1.07–4.28). Childhood body size traits were associated with HF (OR _SD : 1.30; 95% CI: 1.21–1.39). Fat mass, WC, WHR, and unfavorable adiposity were also identified as causal risk factors. Tissue-specific analyses indicated that both brain- and adipose-tissue-specific genetic instruments for BMI were associated with elevated HF risk. Conclusion: This study provides robust MR evidence supporting a causal role of multiple obesity-related traits, particularly adult BMI, in the development of HF across diverse populations. Further MR studies in non-European populations and investigations into specific pathways are warranted to enhance generalizability and mechanistic understanding. Systematic Review Registration: crd.york.ac.uk/PROSPERO/display_record.php?RecordID=576216 identifier, CRD42024576216.

Was not provided for this article.

Background: Atherosclerotic risk factors are increasingly prevalent among younger populations, contributing to a rise in premature coronary artery disease. This study aims to investigate the clinical and angiographic characteristics of this specific demographic. Methods: This retrospective study enrolled 215 consecutive patients aged 35 years or younger (181 men) who underwent coronary angiography (CAG) at our center. Clinical data and angiographic images were collected and analyzed. Independent predictors of ischemic heart disease (IHD) were evaluated using logistic regression analysis. Discriminative performance was assessed using receiver operating characteristic curve analysis. Results: In the selected cohort of 215 young patients, the prevalence rates of obesity/overweight, smoking, dyslipidemia, hypertension, and diabetes mellitus were 56.7%, 53.0%, 31.2%, 23.3%, and 8.4%, respectively. Within this cohort, 92 (42.8%) patients exhibited various forms of IHD, with 85.9% of cases attributed to atherosclerotic cause and 14.1% attributed to nonatherosclerotic etiologies. A total of 202 (94.0%) patients underwent CAG due to chest pain, ischemic electrocardiogram changes, and/or elevated high-sensitivity cardiac troponin T (hs-cTn T) levels. IHD prevalence was highest at 73.8% for those with all three indications, compared to 44.1% with two, and 9.2% with one or none (all p < 0.001). Multivariate logistic regression analysis identified diabetes mellitus (odds ratio [OR], 14.71; 95% confidence interval [CI], 1.59-135.76; p = 0.018), ischemic electrocardiogram changes (OR, 3.11; 95% CI, 1.09-8.91; p = 0.034), interventricular septum thickness (OR, 1.46; 95% CI, 1.08-1.98; p = 0.015), and elevated hs-cTn T levels (OR, 8.26; 95% CI, 3.17-21.51; p < 0.001) as independent predictors of IHD. The combined multivariable model demonstrated a robust discriminative performance (AUC, 0.85; 95% CI, 0.79-0.90; p < 0.001). Conclusions: The present study demonstrated a significant prevalence of modifiable atherosclerotic risk factors among very young patients undergoing CAG. Although atherosclerosis was identified as the primary cause of IHD, nonatherosclerotic etiologies also contributed substantially. The presence of two or more angiographic indications—namely, chest pain, ischemic electrocardiogram changes, and/or elevated hs-cTn T levels—was associated with an increased risk of IHD. Furthermore, diabetes mellitus, ischemic electrocardiogram changes, interventricular septum thickness, and elevated hs-cTn T levels were independent predictors of premature IHD.