Classification of severity of mitral regurgitation patients using multifractal analysis

Abstract

Owing to its efficiency and cost effectiveness, auscultation using a stethoscope is the primary diagnosis method preferred by most medical examiners for cardiovascular disease. Phonocardiography (PCG) is the next level of auscultation and an effective analysis technique in cardiology. This paper presents a method to quantify Mitral Regurgitation (MR) using PCG. MR is one of the most common cardiovascular diseases associated with a defect in mitral valve. We analyzed the multifractal nature of heart sounds with murmur followed by classification and clustering using Hurst exponents. Thus, we were able to project the difference between severities of MR patients by correlating the complexity of heart sounds from four major auscultation sites, using a complexity analysis tool called singularity spectra. The simulation results show that the method can quantify the severity of MR using PCG.

Heartbeat Cardiac Sounds Analysis

“…As an example, in statistical analysis, a dynamic programming algorithm can be employed in order to find the most possible context-free derivation (analysis) of a string, commonly called "Viterbi analysis" [27][28][29]. A second application is in target tracking, where the trail is computed that assigns maximum likelihood to a sequence of observations [30].…”

“…Rijil Thomas et al [29] presented a method to quantify mitral regurgitation (MR) using the PCG signal. Mitral regurgitation is one of the most common cardiovascular diseases associated with a mitral valve defect.…”

Multifractal Characterization and Modeling of Blood Pressure Signals

“…In this work, to give a complete multifractal characterization of the BPd signal, we use the detrended fluctuation analysis (DFA) [17] and its counterpart, the multifractal detrended fluctuation analysis (MFDFA) [18]. DFA and MFDFA are used in many fields to investigate the complexity of signals from biological and physiological data to finance, engineering and physics [19][20][21][22][23][24][25][26][27][28][29][30][31][32][33]. As an example, the DFA is found to be very useful in characterizing intracranial pressure (ICP) signals and to predict TBI [34].…”