Intrinsic Mode Function Complexity Index Using Empirical Mode Decomposition discriminates Normal Sinus Rhythm and Atrial Fibrillation on a Single Lead ECG

Suganti Shivaram, Divaakar Siva Baala Sundaram, Rogith Balasubramani, Anjani Muthyala, Shivaram P. Arunachalam

Research output: Contribution to journalArticlepeer-review

Abstract

Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia affecting approximately 3 million Americans, and is a prognostic marker for stroke, heart failure and even death. Current techniques to discriminate normal sinus rhythm (NSR) and AF from single lead ECG suffer several limitations in terms of sensitivity and specificity using short time ECG data which distorts ECG and many are not suitable for real-time implementation. The purpose of this research was to test the feasibility of discriminating single lead ECG's with normal sinus rhythm (NSR) and AF using intrinsic mode function (IMF) complexity index. 15 sets of ECG's with NSR and AF were obtained from Physionet database. Custom MATLAB® software was written to compute IMF index for each of the data set and compared for statistical significance. The mean IMF index for NSR across 15 data sets was 0.37 ± 0.08, and the mean IMF index for ECG with AF was 0.21 ± 0.07 showing robust discrimination with statistical significance (p<0.01). IMF complexity robustly discriminates single lead ECG with normal sinus rhythm and AF. Further validation of this result is required on a larger dataset. The results also motivate the use of this technique for analysis of other complex cardiac arrhythmias such as ventricular tachycardia (VT) or ventricular fibrillation (VF).

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Fingerprint Dive into the research topics of 'Intrinsic Mode Function Complexity Index Using Empirical Mode Decomposition discriminates Normal Sinus Rhythm and Atrial Fibrillation on a Single Lead ECG'. Together they form a unique fingerprint.

Cite this