An automatic neural network classifier based on a Bayesian framework achieved a minimal sensitivity of 86% and minimal specificity of 90% for classifying six types of heartbeats.
A neural network classifier based on a Bayesian framework can automatically classify heartbeats from ECG signals with high sensitivity and specificity.
This paper presents a method of automatic processing the electrocardiogram (ECG) signal for the classification of heart beats. Data were obtained from 48 records of the MIT-BIH arrhythmia database1 (only one lead). Five types of arrhythmic beats were classified using our method, Premature Ventricular Conduction beat (PVC), Atrial Premature Conduction beat (APC), Right Bundle Branch Block beat (RBBB), Left Bundle Branch Block beat(LBBB), and Paced Rhythm Beat (PRB), in addition to the Normal Beat (NB). A learning dataset for the neural network was obtained from a five records set (124, 214, 111, 100, and 107) which were manually classified using MIT-BIH Arrhythmia Database Directory and documentation, taking advantage of the professional experience of a cardiologist. Feature set was based on ECG morphology and time intervals. Our system resulted in a minimal sensitivity of 86% and minimal specificity of 90%.
Karraz et al. (Tue,) conducted a other in Arrhythmia (n=48). Neural Network Classifier based on a Bayesian Framework was evaluated on Heartbeat classification (sensitivity and specificity). An automatic neural network classifier based on a Bayesian framework achieved a minimal sensitivity of 86% and minimal specificity of 90% for classifying six types of heartbeats.