Detection of Atrial Fibrillation by Processing ECG signals

The aim of this study is to detect Atrial Fibrillation (AF) by analyzing Electrocardiogram (ECG) signals and extracting crucial features essential for early onset detection. AF, characterized by irregular heart rhythms, poses significant challenges in ECG signal interpretation, elevating mortality risks and demanding prompt and accurate diagnosis to avert stroke. This work focuses on the development of a Graphical User Interface (GUI) incorporating a customized Pan-Tompkins algorithm for detecting heart abnormality by computing the essential parameters. By utilizing the data sourced from the MIT-BIH arrhythmia database, key features such as RR, PR, QR, QT, and ST mean-intervals, along with the locations of $P, Q, R, S$, and T, Multiscale Teager Energy Operator (MTEO) plots, T-wave Alternans, and heart rate are analyzed. Implemented within the MATLAB environment, this GUI offers an efficient means of diagnosing heart diseases through comprehensive ECG signal analysis, thereby enhancing the detection and comprehension of cardiac irregularities.