Automatic detection of premature ventricular contraction using quantum neural networks

Abstract

Premature ventricular contractions (PVCs) are ectopic heart beats originating from ventricular area. It is a common form of heart arrhythmia. Electrocardiogram (ECG) recordings have been widely used to assist cardiologists to diagnose the problem. In this paper, we study the automatic detection of PVC using a fuzzy artificial neural network named Quantum Neural Network (QNN). With the quantum neurons in the network, trained QNN can model the levels of uncertainty arising from complex classification problems. This fuzzy feature is expected to enhance the reliability of the algorithm, which is critical for the applications in the biomedical domain. Experiments were conducted on ECG records in the MIT-BIH Arrhythmia Database. Results showed consistently higher or same reliability of QNN on all the available records compared to the backpropagation network. QNN, however, has a relatively higher resource requirement for training.