Detection of ST segment deviation episodes in ECG using KLT with an ensemble neural classifier.

In this paper, we describe a technique for automatic detection of ST segment deviations that can be used in the diagnosis of coronary heart disease (CHD) using ambulatory electrocardiogram (ECG) recordings. Preprocessing is carried out prior to the extraction of the ST segment which involves noise and artifact filtering using a digital bandpass filter, baseline removal and application of a discrete wavelet transform (DWT) based technique for detection and delineation of the QRS complex in ECG. Lead-dependent Karhunen-Loève transform (KLT) bases are used for dimensionality reduction of the ST segment data. ST deviation episodes are detected by a classifier ensemble comprising backpropagation neural networks. Results obtained through the use of our proposed method (sensitivity/positive predictive value = 90.75%/89.2%) compare well with those given in the existing research. Hence, the proposed method exhibits the potential to be adopted in the design of a practical ischemia detection system.