ECG arrhythmia classification based on optimum-path forest

• Published in: Expert systems with applications Vol. 40; no. 9; pp. 3561 - 3573
• Main Authors: Luz, Eduardo José da S., Nunes, Thiago M., de Albuquerque, Victor Hugo C., Papa, João P., Menotti, David
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 01.07.2013; Elsevier
• Subjects: Accuracy; Applied sciences; Arrhythmia; Artificial intelligence; Bayesian; Bayesian analysis; Biological and medical sciences; Classification; Classifiers; Computer science; control theory; systems; Connectionism. Neural networks; Data processing. List processing. Character string processing; ECG classification; Electrocardiography. Vectocardiography; Electrodiagnosis. Electric activity recording; Exact sciences and technology; Feature extraction; Forests; Information retrieval. Graph; Investigative techniques, diagnostic techniques (general aspects); Medical sciences; Memory organisation. Data processing; Multilayer artificial neural network; Optimum-path forest; Signal classification; Software; Support vector machine; Support vector machines; Theoretical computing; Feature extraction; Multilayer artificial neural network; Support vector machine; Optimum-path forest; ECG classification; Bayesian; Heart; Measurement; Costs; Forests; Disease; Segmentation; Arrhythmia; Irregularity; Expert system; Cardiovascular disease; Optimization; Specificity; Vector support machine; Electrocardiography; Bayes network; Selection criterion; Anomaly; Diagnosis; Cardiology; Medical application; Pattern extraction; Bayes estimation; Data analysis; Graph theory; Pattern recognition; Neural network; Non invasive method; Signal processing; Arrhythmia (physiology); Graph method; Signal analysis; Multilayer network
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2012.12.063

► Investigation of the application of the OPF classifier for the task of Arrhythmic ECG signal classification. ► Six main feature representations from works in the literature. ► Performance comparison of the OPF classifier with the SVM, MLP and Bayesian classifiers. ► In terms of computational cost and accuracy/generalization rate, the OPF and Bayes classifiers has shown a better efficiency performance than SVM and MLP classifiers. ► The OPF and Bayes classifiers present the best general balance, once that SVM and MLP classifiers not correctly detect the arrhythmic classes. An important tool for the heart disease diagnosis is the analysis of electrocardiogram (ECG) signals, since the non-invasive nature and simplicity of the ECG exam. According to the application, ECG data analysis consists of steps such as preprocessing, segmentation, feature extraction and classification aiming to detect cardiac arrhythmias (i.e., cardiac rhythm abnormalities). Aiming to made a fast and accurate cardiac arrhythmia signal classification process, we apply and analyze a recent and robust supervised graph-based pattern recognition technique, the optimum-path forest (OPF) classifier. To the best of our knowledge, it is the first time that OPF classifier is used to the ECG heartbeat signal classification task. We then compare the performance (in terms of training and testing time, accuracy, specificity, and sensitivity) of the OPF classifier to the ones of other three well-known expert system classifiers, i.e., support vector machine (SVM), Bayesian and multilayer artificial neural network (MLP), using features extracted from six main approaches considered in literature for ECG arrhythmia analysis. In our experiments, we use the MIT-BIH Arrhythmia Database and the evaluation protocol recommended by The Association for the Advancement of Medical Instrumentation. A discussion on the obtained results shows that OPF classifier presents a robust performance, i.e., there is no need for parameter setup, as well as a high accuracy at an extremely low computational cost. Moreover, in average, the OPF classifier yielded greater performance than the MLP and SVM classifiers in terms of classification time and accuracy, and to produce quite similar performance to the Bayesian classifier, showing to be a promising technique for ECG signal analysis.