Automatic Diagnostic System for Long-Term ECG Data from Holter Monitor

Abstract

An Electrocardiogram (ECG) gives significant information for the cardiologist to detect cardiac diseases. Automation algorithm is essential to analyse long ECG data. In this paper, we have proposed fully automated, high efficiency, accurate and fast algorithm to detect abnormalities in ECG based on wavelet transform. The algorithm consists of pre-processing, feature extraction and diagnosis. Number of heart beats and Premature Ventricular Contraction (PVC), Premature Atrial Contractions (PACs), Supraventricular tachyarrhythmia and Bradycardia are diagnosed accurately and result matches with doctors opinion. The average sensitivity of algorithm is 99.70%.