ECG signal for artrial fibrillation detection

Atrial Fibrillation (AF) is one of the most common cardiac arrhythmias. The number of patients related to heart failure due to AF is increasing day by day. Early detection of AF may reduce the risk of death due to heart failure. So, it has become more important to detect AF. There are various methods to detect AF. In this paper, we use ECG signal for AF detection based on RR interval. The MIT-BIH Atrial Fibrillation database is used to import ECG data for analysis. We use the algorithm that mainly follows statistical method for detection of AF. Parametric statistic RMSSD and SE, and non-parametric statistic, TPR are used for this purpose. The threshold value of RMSSD divided by Mean RR is 0.1, SE is 0.7 and TPR is greater than 0.54 and less than 0.77 is considered for AF detection. The resultant value of RMSSD, SE and TPR of every beat is checked weather it crosses the threshold level or not. If all the three parameters cross the threshold level then the beat flagged as AF. The result is compared with the annotations of the database and the sensitivity, specificity and accuracy is determined. The algorithm has the sensitivity of 98%, specificity of 98% and accuracy of 95%. The result obtained in this study is appreciable compared to the other study found in the literature.