Atrial fibrillation (AF) is often described as a disorganized phenomenon, but many features that qualitatively suggest an underlying order have recently been reported. The present study aimed to disclose this underlying order of AF in a quantitative manner, using a new method of mutual information (MI), which is a measure for gauging the general correlation between 2 time series. Frequency analysis and the MI method were used to analyze 5 epicardial potentials on both atria during AF induced by vagal stimulation (Vs) in 15 dogs. Unipolar electrodes were placed on the right atrial appendage (Rap), the high right atrium (HRA), and the left atrial appendage (Lap). The other 2 electrodes were placed equidistantly between HRA and Rap (RAI-RA2). The power spectrum of AF had a discrete peak around 17 Hz during Vs. After Vs was stopped, the discrete peak shifted from 17 Hz to 7 Hz on all epicardial leads. Taking RA2 as a reference, MI was calculated between RA2 and each of the other electrodes. The MI values (0.066+/-0.005) were greater than 0.047 (the critical value for correlated data) even during Vs. The MI values increased significantly from the highly active process of AF during Vs to the less active one (0.126+/-0.006) before termination of AF. In addition, the MI values increased more at the electrodes close to RA2 (RAI and Rap) than at those far from it (HRA and Lap). These findings suggest that multiple wavelets, which are not random, progressively organize into a few major waves toward the termination of AF; therefore, AF is not a random phenomenon in this model.