Abstract

Background. Atrial fibrillation (AF), the most common cardiac arrhythmia worldwide, carries a high risk of severe complications. Patients diagnosed with paroxysmal atrial fibrillation (PAF) may progress to persistent atrial fibrillation (PerAF) following a period. We aimed to identify metabolites associated with PerAF using machine learning (ML) and predict the probability of PAF progressing to PerAF, enabling the adjustment of subsequent treatments in clinical practice.

Methods. We enrolled AF patients without any anticoagulant therapy within the last 7 days between July 2020 and July 2022 in two centers in China. Targeted metabolomic profiling was performed on the patient's plasma. Differential metabolites and clinical features were identified through univariate and multivariate analyses. Patients were divided into discovery and validation cohorts (70%:30%). Four ML models ( logistic regression, random forest, XGBoost, and LightGBM) were developed for PerAF prediction. Model predictive performance was measured mainly by AUC.

Results. One hundred patients (65 PerAF, 35 PAF) were enrolled. Eight metabolites (kynurenine, N-Acetylaspartic acid, glyceric acid, adipic acid, citramalic acid, malic acid, isocitric acid, and oxoglutaric acid) and two clinical features ( NT-proBNP and uric acid ) had significant associations with PerAF. Pathway enrichment analysis highlighted alterations in the citrate cycle and glyoxylate/dicarboxylate metabolism. XGBoost was chosen for establishing the final model, since its predictive performance outperformed that of other algorithms. The model based on clinical parameters, metabolites, and demographics achieved the highest AUC in the discovery cohort ( 0.751 [ 95% CI 0.6 31~0.8 67 ] ) and validation cohort (0.985 [95% CI 0.940~1.000] ). A simplified model with three features (NT-proBNP, citramalic acid, and uric acid) retained robust performance.

Conclusions. This study shows strengths in identifying eight PerAF-related metabolites via targeted metabolomics and ML, and developing accurate predictive models (including a simplified, clinically feasible model ) to guide early PerAF intervention. Future directions include large-scale multi-center validation, incorporating more confounders, and using multiple platforms to deeply explore AF-related metabolic alterations.