Detection of heart disorders using an advanced intelligent swarm algorithm

Electrocardiogram (ECG) is a well-known diagnostic tool, which is applied by cardiologists to diagnose cardiac disorders. Despite the simple shape of the ECG, various informative measures are included in each recording, which causes complexity for cardiac specialists to recognize the heart problem. Recent studies have concentrated on designing automatic decision-making systems to assist physicians in ECG interpretation and detecting the disorders using ECG signals. This paper applies one optimization algorithm known as Kinetic Gas Molecule Optimization (KGMO) that is based on swarm behavior of gas molecules to train a feedforward neural network for classification of ECG signals. Five types of ECG signals are used in this work including normal, supraventricular, brunch bundle block, anterior myocardial infarction (Anterior MI), and interior myocardial infarction (Interior MI). The classification performance of the proposed KGMO neural network (KGMONN) was evaluated on the Physiobank database and compared against conventional algorithms. The obtained results show the proposed neural network outperformed the Particle Swarm Optimization (PSO) and back propagation (BP) neural networks, with the accuracy of 0.85 and a Mean Square Error (MSE) of less than 20% for the training and test sets. The swarm based KGMONN provides a successful approach for detection of heart disorders with efficient performance.