Key result
Machine learning incorporating NLR and TyG index predicts recent-onset AF in CHF with ~0.77 AUC.
Why the study?
Recent-onset AF is a common complication of CHF potentially involving inflammatory and metabolic dysregulation, but interpretable prediction models and pathways linking them remained to be established.
Observational (n=5,149)
Yes
An interpretable machine learning model incorporating the neutrophil-to-lymphocyte ratio and triglyceride-glucose index can effectively predict the risk of recent-onset atrial fibrillation in patients with chronic heart failure.
Answers are grounded in this paper and cite their sources.
ML model integrating NLR/TyG predicts AF in CHF; leaves open prospective validation before clinical use.
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).
No takes yet. Share an insight, caveat, or question.
Yao et al. (2026) conducted an observational in Chronic heart failure (n=5,149). Neutrophil-to-lymphocyte ratio (NLR) and triglyceride-glucose (TyG) index vs. Lower levels/unexposed was evaluated on Prediction of recent-onset atrial fibrillation (AUC 0.766, 95% CI 0.696-0.837). An Extra Trees machine learning model integrating the neutrophil-to-lymphocyte ratio and triglyceride-glucose index predicted recent-onset atrial fibrillation in patients with chronic heart failure with an AUC of 0.766 in external validation.
Synapse has enriched 10 related papers. Consider them for comparative context: