Geometrical features for premature ventricular contraction recognition with analytic hierarchy process based machine learning algorithms selection

• Published in: Computer methods and programs in biomedicine Vol. 169; pp. 59 - 69
• Main Authors: Oliveira, Bruno Rodrigues de, Abreu, Caio Cesar Enside de, Duarte, Marco Aparecido Queiroz, Vieira Filho, Jozue
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.02.2019
• Subjects: Algorithms; Diagnosis, Computer-Assisted; Electrocardiogram analysis; Electrocardiography; Geometrical features; Humans; Machine Learning; Neural Networks (Computer); Premature Ventricular Contraction; Signal-To-Noise Ratio; Ventricular Premature Complexes - diagnosis; Wavelet Analysis; Electrocardiogram analysis; Geometrical features; Premature Ventricular Contraction
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2018.12.028

•In this work is proposed a new premature ventricular contraction recognition method based on a simplified set of features, extracted from geometric figures constructed over QRS complexes.•Experiments encompassing eight different classifiers with different approaches.•In order to select the best classifiers, a new methodology is proposed based on the Analytic Hierarchy Process.•The simulations include a balanced dataset built from artificial QRS complexes and ECG signals with QRS complexes misdetection.•Results obtained indicated that the proposed approach performed the best in terms of specificity (98.7%) and sensitivity (91.1%). Using balanced dataset, the results were improved to 99.5% and 98.5% in terms of the precision and sensitivity, respectively. Premature ventricular contraction is associated to the risk of coronary heart disease, and its diagnosis depends on a long time heart monitoring. For this purpose, monitoring through Holter devices is often used and computational tools can provide essential assistance to specialists. This paper presents a new premature ventricular contraction recognition method based on a simplified set of features, extracted from geometric figures constructed over QRS complexes (Q, R and S waves). Initially, a preprocessing stage based on wavelet denoising electrocardiogram signal scaling is applied. Then, the signal is segmented taking into account the ventricular depolarization timing and a new set of geometrical features are extracted. In order to validate this approach, simulations encompassing eight different classifiers are presented. To select the best classifiers, a new methodology is proposed based on the Analytic Hierarchy Process. The best results, achieved with an Artificial Immune System, were 98.4%, 91.1% and 98.7% for accuracy, sensitivity and specificity, respectively. When artificial examples were generated to balance the dataset, the recognition performance increased to 99.0%, 98.5% and 99.5%, employing the Support Vector Machine classifier. The proposed approach is compared with some of latest references and results indicate its effectiveness as a method for recognizing premature ventricular contraction. Besides, the overall system presents low computation load.