Atrial Fibrillation Detection Based on Electrocardiogram Features Using Modified Windowing Algorithm

The most prevalent kind of heart disease, Atrial Fibrillation (AF), is said to increase the risk of stroke, heart failure, and other health concerns. Clinical observation of the electrocardiogram (ECG) waveform needs an experienced person to observe and takes long hours. We provide an approach to identify AF in the MIT-BIH Arrhythmia and AF databases in this study. Several parameters, including QRS complex, RR Interval, heart rate, coefficient of variance (CV), normalized root mean square of successive difference (nRMSSD) and peak frequency are calculated from the features of the ECG signal. With holdout validation, we analyse the AF classification performance of various classifiers. With the input parameters mentioned, the greatest outcome in AF classification is obtained by the weighted KNN classifier using the DWT algorithm and modified windowing algorithm in holdout validation, with sensitivity, specificity, and accuracy of 90%, 100%, and 92.31%, accordingly. On this basis, it is recommended that classifying ECG signals using machine learning methods will assist in improving the research’s accuracy. Further research is needed to test the proposed algorithm on a large database for better accuracy. This algorithm will be involved in hardware and implemented in the detection of real-time AF ECG patients.