ECG Print-out Features Extraction Using Spatial-Oriented Image Processing Techniques

Abstract

Analyzing cardiovascular activity of patients using ECG clinical paper printouts requires prior knowledge and practice. This research used spatial-oriented image processing methods for analyzing ECG readings by retrieving only the essential features, and not all ECG data, to assist physicians in diagnosis. Different values such as Atrial (rate/min) and Ventricular (rate/min), QRS interval (sec), QT interval (sec), QTc (sec), and PR interval (sec) were successfully extracted with indication as to whether the values are within the accepted normal values, given the patient’s gender and age. Performance of the system was tested based on accuracy, RMSE and normalized RMSE. The methodology achieved average accuracy as high as 95.424 % while the PR interval feature extraction achieved a relatively low average accuracy of 87.196%.