Methodology for automated detection of fragmentation in QRS complex of Standard 12-lead ECG.

Fragmented QRS (f-QRS) has been found to have higher sensitivity and/or specificity values for several diseases including remote and acute myocardial infarction, cardiac sarcoidosis etc, compared to other conventional bio-markers viz. Q-wave, ST-elevation etc. Several of these diseases do not have a reliable bio-marker and hence, patients suffering from them have to undergo expensive and sometimes invasive tests for diagnosis viz. myocardial biopsy, cardiac catheterization etc. This paper proposes automation of fragmentation detection which will lead to a more reliable diagnosis and therapy reducing human error, time consumption and thereby alleviating the need of enormous training required for detection of fragmentation. In this paper, we propose a novel approach to detect the discontinuities present in QRS complex of standard 12-lead ECG, known as fragmented QRS, using Discrete Wavelet transform (DWT) targeting both hospital-based and remote health monitoring environments. Fragmentation Detection Algorithm (FDA) was designed and modeled using PhysioNet's PTBDB and upon reiterative refinements it successfully detected all discontinuities in the QRS complex. The QRS complexes of 31 patients obtained randomly from PhysioNet's PTBDB were examined by two experienced cardiologists and the measurements obtained were compared with the results of our proposed FDA leading to 89.8\% agreement among them.