Risk of Chronic Kidney Disease and Implications in Patients with Atrial Fibrillation for the Development of Major Adverse Cardiovascular Events with Machine Learning

BACKGROUND: Atrial fibrillation (AF) and chronic kidney disease (CKD) often overlap and may amplify cardiovascular risk. Whether renal dysfunction should be incorporated into composite cardiovascular endpoints in AF remains uncertain. We aimed to quantify AF-associated risk of MACE and evaluate the incremental prognostic value of kidney measures (eGFR and albuminuria) to inform composite outcomes and clinical management. METHODS: = 2574) were followed for 5 years. MACE and components were ascertained from linked health records; only events after AF diagnosis were analyzed. Cox models estimated adjusted hazard ratios (HRs). Risk was further stratified by eGFR stages and urine albumin-to-creatinine ratio (UACR) categories. Exploratory machine learning (ML) was developed to predict MACE in patients with AF and CKD, with model interpretability assessed by feature importance analysis. RESULTS: < 0.001). Among patients with AF, a graded eGFR-risk relationship was observed: compared with higher eGFR, MACE risk increased across G3a-G5, peaking in G5 (HR 2.08). Albuminuria showed a parallel gradient: versus UACR <30 mg/g, UACR 30-299 mg/g and ≥300 mg/g were associated with an increased risk of MACE (HR 1.51 and 1.76, respectively). CONCLUSIONS: Newly diagnosed AF confers a substantial excess risk of MACE and its components. The consistent eGFR and albuminuria in AF support considering clinically meaningful renal endpoints within composite outcomes and prioritizing integrated cardiorenal management. These findings provide actionable evidence to refine risk stratification and endpoint selection in AF research and care.