Targeted metabolomic profiling and machine learning-based prediction models for persistent atrial fibrillation: a multi-center observational study

Large-Scale Plasma Proteomics Profiles for Predicting Atrial Fibrillation Associated Stroke Risk

The metabolic-inflammatory axis in chronic heart failure: integrating the NLR and TyG index for recent-onset atrial fibrillation prediction via machine learning and mediation analysis

Introduction Recent-onset atrial fibrillation (AF) is a common complication of chronic heart failure (CHF), potentially involving both inflammatory and metabolic dysregulation. This study aimed to develop and externally validate an interpretable machine learning (ML) model for predicting recent-onset AF in patients with CHF and to explore the relationships among inflammatory dysregulation, metabolic dysregulation, and recent-onset AF. Methods In this retrospective multicenter study, 4,872 hospitalized patients with CHF from Guang’anmen Hospital and Xiyuan Hospital were included, with external validation performed in 277 additional patients. Demographic, clinical, and laboratory variables, including the triglyceride-glucose (TyG) index and neutrophil-to-lymphocyte ratio (NLR), were analyzed. Nine ML algorithms were compared for AF prediction. Model interpretability was assessed using SHapley Additive exPlanations (SHAP). Segmented regression was used to examine nonlinear threshold effects, and mediation analysis was performed to explore the immunometabolic pathway linking TyG, NLR, and AF. Results The Extra Trees model performed best, achieving an area under the receiver operating characteristic curve of 0.853 in the training cohort and 0.766 in the external validation cohort. NLR showed a nonlinear association with AF risk, with a steeper increase below 4.24, whereas TyG showed a threshold-dependent J-shaped relationship, with the risk increasing significantly above 5.91. The combination of TyG and NLR further improved model discrimination. Mediation analysis suggested that the estimated indirect association through NLR accounted for a substantial proportion of the observed association between TyG and AF. Conclusions An interpretable ML framework identified the immune-metabolic axis as an important predictive component of recent-onset AF in CHF. NLR and TyG are inexpensive, clinically accessible biomarkers that may improve early risk stratification and identify a high-risk phenotype characterized by concurrent metabolic stress and inflammation. Trial registration: ChiCTR (ITMCTR2025001576).

Machine Learning Models Integrating CYP2C19 Genotypes for Long-Term Risk Prediction and Personalized Antiplatelet Therapy Selection in Myocardial Infarction.

Machine learning (ML) models integrating genetic and clinical data show promise for personalizing antiplatelet therapy after myocardial infarction (MI). This study aimed to develop an ML model using clinical features and CYP2C19 genotype to predict long-term major adverse cardiac events (MACEs) and guide P2Y12 inhibitor selection. In a prospective observational study of 218 MI patients undergoing percutaneous coronary intervention, with up to 9-year follow-up for MACEs, we trained and evaluated multiple models incorporating clinical, genetic, and angiographic variables. Uplift modeling principles were applied to assess treatment heterogeneity, and feature importance was analyzed using Shapley Additive Explanations (SHAP). The optimal model (CatBoost with SHAP-based feature selection) achieved an area under the receiver operating characteristic curve of 0.721. Discrimination remained stable under bootstrap resampling and across both infarction presentations. Key prognostic predictors included age, comorbidity index, number of significant coronary lesions, P2Y12 inhibitor type, stent type, and CYP2C19 loss-of-function/gain-of-function variants. Notably, CYP2C19 variants were significant MACE predictors, while drug-eluting stents and ticagrelor were associated with lower predicted long-term risk. These findings suggest that an ML framework incorporating CYP2C19 genotype can stratify long-term MACE risk. This data-driven approach points to the prognostic utility of genetic testing and supports the potential role of ticagrelor, particularly in genetically defined high-risk MI patients, for optimizing secondary prevention.

Plasma proteomic profiling reveals potential biomarkers for sinus node dysfunction in persistent atrial fibrillation

Aims: In patients with persistent atrial fibrillation (PerAF), detecting sinus node dysfunction (SND) before rhythm control therapy is challenging, which may increase the risk of post-cardioversion bradyarrhythmia and complicate clinical management. This study aimed to identify plasma proteomic signatures associated with prolonged sinus node recovery time (SNRT) and to explore potential predictors of SND in PerAF patients. Methods: A total of 226 consecutive patients with PerAF undergoing catheter ablation were screened, and 177 eligible patients were included. SNRT was measured after cardioversion, with 1,500 ms used as the cutoff to define prolonged SNRT. Propensity score matching was applied to select matched controls. Plasma samples were analyzed using proteomic techniques to compare protein expression profiles between the prolonged-SNRT and normal-SNRT groups. A weighted gene co-expression network analysis (WGCNA) was conducted to determine the most significant module and hub proteins associated with SNRT. An enzyme-linked immunosorbent assay was used for further assessment of candidate biomarkers. Results: Proteomic analysis identified 435 differentially expressed proteins, including 138 upregulated and 297 downregulated proteins in the prolonged-SNRT group. Integrated data-independent acquisition-based proteomics and WGCNA revealed a distinct plasma proteomic signature associated with prolonged SNRT in patients with PerAF, characterized by enrichment of extracellular matrix remodeling and metabolic reprogramming pathways. Acid phosphatase 5 (ACP5) was selected as a candidate biomarker, which was significantly elevated in patients complicated by SND in the validation set. Conclusions: This study revealed distinct plasma proteomic features in PerAF patients with prolonged SNRT. ACP5 may serve as a potential biomarker to assess sinoatrial node function in PerAF patients prior to rhythm control therapy.

Multiple machine learning models for predicting major adverse cardiovascular events in dialysis with clinical and echocardiographic parameters: a retrospective cohort study

Abstract Background Patients undergoing dialysis are at an elevated risk of cardiovascular events. This study aimed to develop machine learning (ML) prediction models to identify risk factors for major adverse cardiovascular events (MACE) in dialysis patients. Materials and Methods This retrospective study included 203 patients undergoing dialysis with a median age of 45.0 years and 64.0% male. The participants were divided into training and test sets in a 7:3 ratio. LASSO regression selected characteristic variables from patients’general information, laboratory tests, and echocardiographic parameters (including global longitudinal strain [GLS]). Eight ML models were constructed,and SHAP analysis evaluated feature importance. Results The incidence of MACE (including myocardial infarction, unstable angina, heart failure, and cardiovascular death) in dialysis patients was 38.92%. The average follow-up period was 18 months. LASSO regression identified eight feature variables. Among the ML models, AdaBoost demonstrated superior performance, with an AUC of 0.883 (95% CI: 0.830–0.937), accuracy of 0.804, sensitivity of 0.864 and specificity of 0.762 in the training set, and an AUC of 0.809 (95% CI: 0.706–0.912), accuracy of 0.750, sensitivity of 0.90 and specificity of 0.675 in the test set. The SHAP analysis identified N-terminal pro-brain natriuretic peptide (NT-proBNP) level, estimated glomerular filtration rate (eGFR), GLS and age as the four most important features for predicting MACE in patients undergoing dialysis (mean absolute SHAP values: 0.199, 0.176, 0.096 and 0.091, respectively). Conclusion Elevated NT-proBNP, advanced age, reduced eGFR and impaired GLS were independently associated with an increased risk of MACE in patients undergoing dialysis.

Metabolomic profiling refines cardiovascular risk stratification beyond SCORE2-diabetes in patients with concurrent type 2 diabetes and pulmonary dysfunction

In participants with T2D and LFI, adding a metabolomic signature to SCORE2-Diabetes produced a statistically significant but moderate improvement in risk discrimination, which supports further evaluation in independent cohorts and prospective impact studies.