DETECTION OF TRANSIENT ST SEGMENT EPISODES DURING AMBULATORY ECG MONITORING

Using the European Society of Cardiology ST-T Database, we have develo ped a Karhunen-Loeve transform-based algorithm for robust automated de tection of transient ST segment episodes during ambulatory ECG monitor ing. We review current approaches and systems to detect transient ST s egment changes and describe the architecture of our algorithm and its development. The algorithm incorporates a single-scan trajectory-recog nition technique in feature space using the Mahalanobis distance funct ion between the feature vectors. The main characteristics of the algor ithm are detection of noisy beats, correction of the reference ST segm ent level to correct for slow ST level drift, detection of sudden sign ificant shifts of ST deviation due to shifts of the mean electrical ax is of the heart, detection of transient ST episodes, and, by tracking the QRS complex morphology, differentiation between ischemic and nonis chemic ST episodes as a result of axis shifts. We compared the algorit hm's performance to other recently developed algorithms and estimated its real-world performance. (C) 1998 Academic Press.