A New Approach to Detect Congestive Heart Failure Using Symbolic Dynamics Analysis of ElectrocardiogramSignal

The aim of this study is to show that the measures derived fromElectrocardiogram (ECG) signals many a time perform better than the samemeasures obtained from heart rate (HR) signals. A comparison was made toinvestigate how far the nonlinear symbolic dynamics approach helps to characterizethe nonlinear properties of ECG signals and HR signals, and thereby discriminatebetween normal and congestive heart failure (CHF) subjects. The symbolicdynamics calculations performed on normal and CHF ECG and HR signals showedsignificant differences in the symbol-sequence histogram statistics and complexitymeasures (modified Shannon entropy (MSE) and multi-valued Lempel-Zivcomplexity (MLZC)) of symbol sequences between the two groups. The ability ofthese complexity measures to discriminate normal from CHF subjects was evaluatedusing receiver operating characteristic (ROC) plots. It is found that MSE and MLZCmeasures obtained from ECG signals performed better than the same measuresderived from HR signals of the same subjects.

A New Approach to Detect Congestive Heart Failure Using Symbolic Dynamics Analysis of ElectrocardiogramSignal Keywords:

Congestive heart failure , Complexity measures , Electrocardiogram signal , Heart rate signal , Modified Shannon entropy , Multi-valued Lempel-Ziv complexity , Symbolic dynamics