Influencing factors and predictive model for left atrial appendage emptying velocity in nonvalvular AF patients

Background: Atrial fibrillation (AF) is the most common cardiac arrhythmia, significantly increasing the risk of death and stroke. The left atrial appendage (LAA) plays a crucial role in the development of AF. Reduced left atrial appendage emptying velocity (LAAEV) is an important indicator of nonvalvular AF, associated with thrombosis and recurrence after catheter ablation. This study aims to identify factors influencing LAAEV and construct a predictive model for LAAEV in nonvalvular AF patients. Methods: This retrospective cohort study included 1,048 nonvalvular AF patients hospitalized at the Second Hospital of Hebei Medical University from January 1, 2015, to December 31, 2021. Patients underwent transthoracic and transesophageal echocardiography and had complete laboratory data. Statistical analyses included binary logistic regression and multiple linear regression to identify independent predictors of reduced LAAEV and construct a predictive model. Results: Patients were divided into two groups: reduced LAAEV (<40 cm/s) and normal LAAEV (>= 40 cm/s). The reduced LAAEV group included 457 patients (43.61%), with significant differences in age, gender, alcohol consumption, heart failure (HF), ischemic stroke, AF type, resting heart rate, CHA2DS2-VASc score, serum creatinine (SCR), serum uric acid (SUA), estimated glomerular filtration rate (eGFR), glycated hemoglobin (HbA1C), beta 2 macroglobulin (B2M), left atrial diameter (LAD), and left ventricular ejection fraction (LVEF) compared to the normal LAAEV group. Logistic regression analysis identified age (OR 0.974, 95% CI 0.951-0.997, P = 0.028), HF (OR 0.637, 95% CI 0.427-0.949, P = 0.027), AF type [Persistent AF vs. PAF (OR 0.063, 95% CI 0.041-0.095, P = 0) Long-standing Persistent AF vs. PAF (OR 0.077, 95% CI 0.043-0.139, P = 0)], LAD (OR 0.872, 95% CI 0.836-0.91, P < 0.001), and LVEF (OR 1.057, 95% CI 1.027-1.089, P = 0) as independent predictors of reduced LAAEV. Multiple linear regression analysis included age, AF type, LAD, and LVEF in the final predictive model, explaining 43.5% of the variance in LAAEV (adjusted R-2 = 0.435). Conclusion: Age, HF, type of AF, LAD, and LVEF are independent predictors of reduced LAAEV. The predictive model (LAAEV = 96.567-15.940 x AFtype-1.309 x LAD-0.18 x Age + 37.069 x LVEF) demonstrates good predictive value, aiding in the initial assessment and management of nonvalvular AF patients.