Neural Network Classification of Premature Heart Beats

In this paper, we analyse features from R waveform of electrocardiogram (ECG) and arterial blood pressure (ABP) signals for classifying premature heart beats. Detection of these beats is important as they could be a pre-cursor for serious arrhythmias. The fusion of ECG and ABP signals to detect premature heart beats are relatively new as most methods use only ECG signals. Two new features, mobility and complexity factor (used in electroencephalogram analysis) derived from R waveform of ECG signal are studied in addition to the conventional ECG features. Three cases of beats are considered: 2 ectopic premature ventricular contraction (PVC) and premature supraventricular contraction (PSC) and normal (N). All the features are normalized with some factor inherent in the signal to reduce the inter-subject variance of the features. Data from 50 subjects totaling 3000 beats (1000 N, 1000 PSC and 1000 PVC) from Massachusetts General Hospital/Marquette Foundation database are used. The 13 features are reduced to 9 using principal component analysis (PCA). These reduced feature sets are classified by the Multilayer Perceptron trained by the Resilient Backpropagation (MLP-RBP) neural network into the 3 classes. The results give classification performance up to 94.47%. It is concluded that ECG and BP features could be used to detect premature beats successfully.