Topographic analysis and diagnosis of congestive heart failure using second-order difference plot

Abstract

In this study, in order to diagnose congestive heart failure (CHF) patients, second-order difference map (SDOP) features obtained from raw electrocardiogram (EEG) data is used. CHF and normal patients' electrocardiogram data, which are distributed freely via internet, is analyzed. By U-matrix presentation of Self-Organized Maps, distances between groups and clusters are examined. 1×16 sixed SODP features of raw EEG data obtained from normal and CHF patients can successfully be classified using U-matrix presentation of SOM. As a classifier Neural Network based classifier is applied and %99.9 over all accuracy performance is reached.