Beat-to-beat quantification and analysis of ST displacement from Holter ECGs: a new approach to ischemia detection

The authors present an algorithm which develops a set of beat-to-beat time series. The algorithm provides the support for a complete and operator-independent offline analysis of ambulatory electrocardiogram (ECG) recordings, spanning heart rate variability, repolarization duration variability, and detection of transient myocardial ischemia. The algorithm uses variables extracted by the frequency distributions of ST segment displacements. A logistic regression, applied to the data extracted from 20 certified normal and 24 certified ischemic Holter ECGs, enhanced the classification performance of ST segment depression in identifying ischemic episodes. Sensitivity and specificity reached 95.8% and 90%, respectively