This paper presents the development of novel and efficient algorithms for early detection of cardiac ischemia from ECG signal using different feature extraction techniques. The proposed work mainly involves three stages namely denoising, feature extraction and classification. The removal of noise from ECG signal is achieved by applying wavelet threshold technique. The extraction of clinically useful features is carried out through morphological technique, statistical analysis, principal component analysis (PCA)-based technique and independent component analysis-wavelet packet decomposition (ICA-WPD) technique. The extracted features are used as inputs for artificial neural network (ANN), support vector machines (SVM) and K-nearest neighbour (KNN) classifier models for detecting ischemic beats. The performance of all models are compared and validated with ECG signal acquired from physiobank database in terms of performance indices such as classification accuracy, sensitivity and positive prediction accuracy. The results have confirmed that the ANN model trained and tested with features extracted by ICA-WPD provides highest classification accuracy of 96.85%, PPA of 99.59% and sensitivity of 97.22%. Results clearly demonstrated that the ANN classifier model combined with ICA-WPD-based feature is more effective in diagnosing myocardial ischemia at early stages.