It has been recognized that heart rate variability (HRV), defined as the fluctuation of ventricular response intervals in atrial fibrillation (AFib) patients, is not completely random, and its nonlinear characteristics, such as multiscale entropy (MSE), contain clinically significant information. We investigated the relationship between ischemic stroke risk and HRV with a large number of stroke-naive AFib patients (628 patients), focusing on those who had never developed an ischemic/hemorrhagic stroke before the heart rate measurement. The CHA2DS2-VASc score was calculated from the baseline clinical characteristics, while the HRV analysis was made from the recording of morning, afternoon, and evening. Subsequently, we performed Kaplan-Meier method and cumulative incidence function with mortality as a competing risk to estimate the survival time function. We found that patients with sample entropy (SE(s)) >/= 0.68 at 210 s had a significantly higher risk of an ischemic stroke occurrence in the morning recording. Meanwhile, the afternoon recording showed that those with SE(s)&nbsp;>/= 0.76 at 240 s and SE(s)&nbsp;>/= 0.78 at 270 s had a significantly lower risk of ischemic stroke occurrence. Therefore, SE(s) at 210 s (morning) and 240 s </= s </= 270 s (afternoon) demonstrated a statistically significant predictive value for ischemic stroke in stroke-naive AFib patients.