Objective <p>This study aimed to investigate the association between the blood urea nitrogen-to-albumin ratio (BAR) and both short- and long-term all-cause mortality in critically ill patients with atrial fibrillation (AF).</p> Methods <p>A retrospective cohort study was conducted using the Medical Information Mart for Intensive Care IV (MIMIC-IV) database, including 4,697 critically ill AF patients. Participants were stratified into tertiles based on their BAR levels (Q1: &lt;6.36, Q2: 6.36–12.43, Q3:&gt;12.43). The primary outcomes were 30-day and 365-day all-cause mortality. Kaplan-Meier survival curves, multivariable Cox proportional hazards models, and restricted cubic spline (RCS) analyses were employed to assess the association. A two-piecewise linear model was used to identify the threshold effect. Subgroup analyses were performed to evaluate the consistency of the association.</p> Results <p>Patients in higher BAR tertiles had significantly higher mortality rates at all time points (<i>P</i> &lt; 0.001). After full adjustment for demographics, comorbidities, laboratory parameters, and treatment measures, the highest BAR tertile (Q3) was independently associated with increased risks of 30-day (hazard ratio [HR] = 2.34, 95% confidence interval [CI]: 1.94–2.82) and 365-day mortality (HR = 2.04, 95% CI: 1.78–2.35), compared to the lowest tertile (Q1). RCS analysis revealed a nonlinear, L-shaped relationship between BAR and mortality. A threshold effect was identified, with inflection points at BAR levels of 11.52 for 30-day mortality and 14.41 for 365-day mortality. The association remained robust across all predefined subgroups.</p> Conclusion <p>In intensive care unit (ICU) patients with AF, elevated BAR levels independently predicted increased 30-day and 365-day all-cause mortality risks. The BAR may serve as a useful prognostic indicator for risk stratification and clinical management of AF patients in ICUs.</p> Graphical Abstract <p></p>