Classification of Coronary Artery Disease Stress ECGs using Uncertainty Modeling

Abstract

This paper discusses the use of combined uncertainty methods in the diagnosis of coronary artery disease using ECG stress signals. Combined uncertainty computes a composite of two types of uncertainties, fuzzy and probabilistic. First, we introduce basic definitions for fuzzy and probabilistic uncertainty types. Next, the ECG analysis problem is discussed in the context of classifying ECG signals using traditional methods. Three examples of models that compute fuzzy, probabilistic, and combined uncertainty models are introduced in the next section. Our experimental results show that models developed by combined uncertainty produce better results, in terms of ECG signals correct classification percentage, compared to those computed using only fuzzy or probabilistic uncertainty.