This is a population pharmacokinetic (PopPK) analysis to predict PK of edoxaban, a direct-acting oral anticoagulant, in nonvalvular atrial fibrillation (NVAF) patients with severe renal impairment (SRI; creatinine clearance [CLcr] <30 mL/min). Data from a phase 3 study recently conducted in Japanese NVAF patients (n = 90), including patients with SRI, were used to update the ENGAGE PopPK model that had been developed based on pooled data from the phase 3 ENGAGE AF-TIMI 48 study and 13 phase 1 PK studies, which included few patients with SRI. The final model indicated that the ENGAGE PopPK model was applicable to Japanese patients in that the model-simulated and study-observed concentration-time profiles were in agreement. Estimated model parameters after the addition of Japanese SRI data were consistent with those derived from the original ENGAGE PopPK data set. The model-predicted exposure in NVAF patients with SRI who received edoxaban at a 15-mg, once-daily dose was similar to that in patients with normal renal function or with mild renal impairment receiving a 30-mg dose. This suggests that efficacy and safety data from the ENGAGE AF study can be used to support dose setting for NVAF patients with SRI.