Redes neuronales

14th European Signal Processing Conference (EUSIPCO 2006), Florence, Italy, September 4-8, 2006, copyright by EURASIP

NEURAL NETWORK BASED ARRHYTHMIA CLASSIFICATION USING HEART RATE VARIABILITY SIGNAL

Babak Mohammadzadeh-Asl, Seyed Kamaledin Setarehdan
Control and Intelligent Processing Center of Excellence, Electrical and Computer Engineering Department, Faculty of Engineering, Universityof Tehran, Tehran, Iran phone: + (98) 21 88020403 Ext 3377, fax: + (98) 21 88633029, email: b.mohammadzadeh@ece.ut.ac.ir

ABSTRACT Heart Rate Variability (HRV) analysis is a non-invasive tool for assessing the autonomic nervous system and specifically it is a measurement of the interaction between sympathetic and parasympathetic activity in autonomic functioning. In recent years, HRV signal ismostly noted for automated arrhythmia detection and classification. In this paper, we have used a neural network classifier to automatic classification of cardiac arrhythmias into five classes. HRV signal is used as the basic signal and linear and nonlinear parameters extracted from it are used to train a neural network classifier. The proposed approach is tested using the MIT-BIH arrhythmiadatabase and satisfactory results were obtained with an accuracy level of 99.38%. 1. INTRODUCTION

One of the methods which is mostly noted by specialists, for assessing the heart activity and discrimination of cardiac abnormalities, is called Heart Rate Variability (HRV). HRV is a nonlinear and nonstationary signal that represents the autonomic activity and its influence on the cardiovascularsystem. Hence, measurement of heart rate variations and computerized analysis of it is a non-invasive tool for assessing the autonomic nervous system and cardiovascular autonomic regulation . Furthermore, it could give us information about heart deficiency at the present or in the future. An automated method for the classification of cardiac arrhythmias is proposed based on linear and non-linearanalysis of HRV. Time and frequency domain measures in heart rate variability analysis are less successful in the classification of multiple rhythm changes. With the help of measures from non-linear dynamics we can quantify some of the complex structures in heart rate time series [1]. Therefore, we have used a combination of linear and non-linear parameters. These features are used as input in anartificial neural network (ANN), which classifies each segment into one of the arrhythmia classes. 2. MATERIALS AND METHODS In this paper, we explore the HRV signal as the basic signal to classify cardiac arrhythmias into five classes : normal sinus rhythm (NSR), premature ventricular contraction

(PVC), atrial fibrillation (AF), ventricular fibrillation (VF) and and 2° heart block (BII). The HRVarrhythmia data, obtained using the ECG data from the MIT-BIH Arrhythmia Database which was digitized at a sampling rate of 360Hz. Moreover, due to the lack of the VF data in the MIT-BIH arrhythmia database, the Creighton University Ventricular Tachyarrhythmia Database was resampled at 360 Hz and then used for the VF arrhythmia class. Our analysis is carried out in three stages. First a preprocessingprocedure is used to extract tachograms from the ECGs. In this stage we have used Tompkins algorithm [2] for detection of R peaks. The tachograms are segmented into small segments. Each segment contains 32 RR-intervals and is characterized using the MIT-BIH arrhythmia database annotation. In the second stage, time and frequency domain and nonlinear methods are applied to extract correspondingfeatures. In the third stage the extracted features are used to train a neural network classifier. Next materials and methods are described. Then the different steps of the proposed algorithm are explained. Finally results obtained on the MIT-BIH arrhythmia database are presented. 3. FEATURE EXTRACTION The methods for HRV analysis can be divided into linear (time and frequency domain) and nonlinear...