Complexity-Measure-Based Approach To Detect Life Threatening Cardiac Arrhythmias Using First-Order Difference of Electrocardiogram Signals

The aim of this study is to evaluate how far Lempel-Ziv complexity (LZC) of thebinary symbolic sequences resulting from static or dynamic transformation(partitioning first-order difference) of the short-term electrocardiogram (ECG)signals (only 2 seconds duration) has the potential in discriminating normal andventricular tachycardia/ventricular fibrillation (VT/VF) subjects. The statisticalanalyses show that LZC from either transformation is sufficient to distinguishbetween normal and VT/VF subjects. Between the two. LZC of dynamictransformation is found to outperform LZC of static transformation. The receiveroperating characteristic curve analysis confirms the robustness of this newapproach which exhibits an average sensitivity of about 99.1% (100.0%) specificityof about 100.0% (100.0%), precision of around 98.9% (100.0%) and accuracy ofabout 99.5% (100.0%), with LZC to distinguish between normal and VT (VF)subjects. The presented method is simple, computationally efficient, and well suitedfor real time implementation in automatic external or implantable cardioverter-defibrillators.

Keywords:

Electrocardiogram , Lempel-Ziv complexity , Symbolic sequences , Ventricular tachycardia , Ventricular fibrillation