Cardiac Arrhythmia Detection Using Ensemble of Machine Learning Algorithms

Abstract

An ECG signal is a bioelectrical signal which records the electrical activity of the heart. ECG signals are used as the parameter for detecting various heart diseases. Cardiac arrhythmia can be detected using ECG signals. Arrhythmia is a condition in which the rhythm of the heart is irregular, too slow or too fast. The data for this work is obtained from the University of California, Irvine machine learning repository. The data obtained from the repository is preprocessed. Feature selection is made, and machine learning models are applied to the preprocessed data. Finally, data is classified into two classes, namely normal and arrhythmia. Feature selections were made to optimize the performance of machine learning algorithms. Features with more number of missing values and which showed no variation for all the instances have been deleted. Accuracy achieved using ensemble of machine learning algorithms is 85%. The objective of this research is to design a robust machine learning algorithm to predict cardiac arrhythmia. The prediction of cardiac arrhythmia is performed using ensemble of machine learning algorithms. This is to boost the accuracy achieved by individual machine learning algorithms. The technique of combining two or more machine learning models to improve the accuracy of the results is called ensemble prediction. More accurate results can be achieved using ensemble methods than the results achieved using single machine learning model.