COMPUTER-AIDED INTERPRETATION OF ECG FOR DIAGNOSTICS

The paper presents an integrated pattern recognition method for the co mputer-aided interpretation of the ECG for diagnostic purposes. The ov erall process of computer-aided interpretation has been subdivided int o the stages of preprocessing, feature extraction, parameter measureme nt, frontal plane axis (FPA) angle calculation and diagnostics. A nove l method has been developed for the delineation of peaks with boundary detection up to an accuracy of 99.98%. Accuracies have been obtained up to 99.83% in QRS identification and 96% in P and T wave identificat ion, using fuzzy criteria, respectively. A fast and efficient algorith m has been implemented for FPA calculation. A point scoring scheme for left and right ventricular hypertrophy has been used for the diagnost ics. Through this integrated approach the output results are available in a concise tabular form for easy inspection by the cardiologists. T he method is suitable for both off-line and on-line applications in ca rdiac care units. The method has been successfully tested for a large number of ECG waveforms. The test results establish the accuracy, effe ctiveness and reliability of the method.