Computer-assisted diagnosis for chronic heart failure by the analysis of their cardiac reserve and heart sound characteristics

An innovative computer-assisted diagnosis system for chronic heart failure (CHF) was proposed in this study, based on cardiac reserve (CR) indexes extraction, heart sound hybrid characteristics extraction and intelligent diagnosis model definition. Firstly, the modified wavelet packet-based denoising method was applied to data pre-processing. Then, the CR indexes such as the ratio of diastolic to systolic duration (D/S) and the amplitude ratio of the first to second heart sound (S1/S2) were extracted. The feature set consisting of the heart sound characteristics such as multifractal spectrum parameters, the frequency corresponding to the maximum peak of the normalized PSD curve (fPSDmax) and adaptive sub-band energy fraction (sub_EF) were calculated based on multifractal detrended fluctuation analysis (MF-DFA), maximum entropy spectra estimation (MESE) and empirical mode decomposition (EMD). Statistical methods such as t-test and receiver operating characteristic (ROC) curve analysis were performed to analyze the difference of each parameter between the healthy and CHF patients. Finally, least square support vector machine (LS-SVM) was employed for the implementation of intelligent diagnosis. The result indicates the achieved diagnostic accuracy, sensitivity and specificity of the proposed system are 95.39%, 96.59% and 93.75% for the detection of CHF, respectively. The selected cutoff values of the diagnosis features are D/S=1.59, S1/S2=1.31, Δα=1.34 and fPSDmax=22.49, determined by ROC curve analysis. This study suggests the proposed methodology could provide a technical clue for the CHF point-of-care system design and be a supplement for CHF diagnosis.

[1]  Yongwan Park,et al.  Reinvestigation of the relationship between the amplitude of the first heart sound to cardiac dynamics , 2013, Physiological reports.

[2]  N. Andersen,et al.  ON POWER ESTIMATION IN MAXIMUM ENTROPY SPECTRAL ANALYSIS , 1978 .

[3]  João Francisco Valiati,et al.  Document-level sentiment classification: An empirical comparison between SVM and ANN , 2013, Expert Syst. Appl..

[4]  Engin Avci,et al.  A new intelligent diagnosis system for the heart valve diseases by using genetic-SVM classifier , 2009, Expert Syst. Appl..

[5]  Zhu-ming Zhang,et al.  Usefulness of electrocardiographic QRS/T angles with versus without bundle branch blocks to predict heart failure (from the Atherosclerosis Risk in Communities Study). , 2014, The American journal of cardiology.

[6]  S. Barold,et al.  Significance of QRS complex duration in patients with heart failure. , 2005, Journal of the American College of Cardiology.

[7]  Javed Butler,et al.  The sympathetic nervous system in heart failure physiology, pathophysiology, and clinical implications. , 2009, Journal of the American College of Cardiology.

[8]  Zhongwei Jiang,et al.  Segmentation-based heart sound feature extraction combined with classifier models for a VSD diagnosis system , 2014, Expert Syst. Appl..

[9]  Goutam Saha,et al.  Detection of cardiac abnormality from PCG signal using LMS based least square SVM classifier , 2010, Expert Syst. Appl..

[10]  N Doba,et al.  Diastolic Fractional Flow Reserve to Assess the Functional Severity of Moderate Coronary Artery Stenoses: Comparison With Fractional Flow Reserve and Coronary Flow Velocity Reserve , 2000, Circulation.

[11]  Xingming Guo,et al.  Non-invasive monitoring and evaluating cardiac function of pregnant women based on a relative value method. , 2012, Acta physiologica Hungarica.

[12]  H. Stanley,et al.  Multifractal Detrended Fluctuation Analysis of Nonstationary Time Series , 2002, physics/0202070.

[13]  Zheng Zhang,et al.  Denoising method of heart sound signals based on self-construct heart sound wavelet , 2014 .

[14]  D. Doyle,et al.  Comparison of phonocardiographic monitoring locations , 1995, Proceedings of 17th International Conference of the Engineering in Medicine and Biology Society.

[15]  Srimonti Dutta.  Multifractal properties of ECG patterns of patients suffering from congestive heart failure , 2010 .

[16]  L. Amaral,et al.  Multifractality in human heartbeat dynamics , 1998, Nature.

[17]  Peter C Austin,et al.  Outcome of heart failure with preserved ejection fraction in a population-based study. , 2006, The New England journal of medicine.

[18]  Francesco Faita,et al.  Arterial pressure changes monitoring with a new precordial noninvasive sensor , 2008, Cardiovascular ultrasound.

[19]  D. T. Barry,et al.  Time-frequency transforms: a new approach to first heart sound frequency dynamics , 1992, IEEE Transactions on Biomedical Engineering.

[20]  U. Rajendra Acharya,et al.  Linear and nonlinear analysis of normal and CAD-affected heart rate signals , 2014, Comput. Methods Programs Biomed..

[21]  Nelson B Schiller,et al.  The amplitude ratio of the first to second heart sound is reduced in left ventricular systolic dysfunction. , 2010, International journal of cardiology.

[22]  N. Ertugrul,et al.  Automatic Classification and Characterization of Power Quality Events , 2008, IEEE Transactions on Power Delivery.

[23]  M. Lab,et al.  ARRHYTHMIA IN HEART FAILURE: ROLE OF MECHANICALLY INDUCED CHANGES IN ELECTROPHYSIOLOGY , 1989, The Lancet.

[24]  Z Guo,et al.  A virtual instrument for acquisition and analysis of the phonocardiogram and its internet-based application. , 2001, Telemedicine journal and e-health : the official journal of the American Telemedicine Association.

[25]  Joanna Wdowczyk-Szulc,et al.  Comparison of Wavelet Transform Modulus Maxima and Multifractal Detrended Fluctuation Analysis of Heart Rate in Patients with Systolic Dysfunction of Left Ventricle , 2008, Annals of noninvasive electrocardiology : the official journal of the International Society for Holter and Noninvasive Electrocardiology, Inc.

[26]  E. Parzen.  Multiple Time Series: Determining the Order of Approximating Autoregressive Schemes. , 1975 .

[27]  A A Luisada,et al.  Phonocardiography as a monitor of cardiac performance during anesthesia. , 1989, Anesthesia and analgesia.

[28]  Daniel T. L. Shek,et al.  Longitudinal Data Analyses Using Linear Mixed Models in SPSS: Concepts, Procedures and Illustrations , 2011, TheScientificWorldJournal.

[29]  Shigeo Abe,et al.  Fuzzy least squares support vector machines for multiclass problems , 2003, Neural Networks.

[30]  S. Charleston-Villalobos,et al.  Assessment of time-frequency representation techniques for thoracic sounds analysis , 2014, Comput. Methods Programs Biomed..

[31]  Luís A. Nunes Amaral,et al.  From 1/f noise to multifractal cascades in heartbeat dynamics. , 2001, Chaos.

[32]  D. Levy,et al.  Congestive heart failure in subjects with normal versus reduced left ventricular ejection fraction: prevalence and mortality in a population-based cohort. , 1999, Journal of the American College of Cardiology.

[33]  W Frank Peacock,et al.  The combined utility of an S3 heart sound and B-type natriuretic peptide levels in emergency department patients with dyspnea. , 2006, Journal of cardiac failure.

[34]  L. Tan,et al.  CARDIAC PUMPING CAPABILITY AND PROGNOSIS IN HEART FAILURE , 1986, The Lancet.

[35]  John Suckling,et al.  Multifractal characterisation of electrocardiographic RR and QT time-series before and after progressive exercise , 2012, Comput. Methods Programs Biomed..

[36]  Samjin Choi,et al.  A novel cardiac spectral segmentation based on a multi-Gaussian fitting method for regurgitation murmur identification , 2014, Signal Process..

[37]  M. A. Hanson.  On sufficiency of the Kuhn-Tucker conditions , 1981 .

[38]  Kenneth B Margulies,et al.  Decreased cardiac functional reserve in heart failure with preserved systolic function. , 2011, Journal of cardiac failure.

[39]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[40]  Shouzhong Xiao,et al.  A relative value method for measuring and evaluating cardiac reserve , 2002, Biomedical engineering online.

[41]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[42]  Charles E. McCulloch,et al.  Association between phonocardiographic third and fourth heart sounds and objective measures of left ventricular function. , 2005 .

[43]  R. Hainsworth,et al.  Physiological cardiac reserve: development of a non-invasive method and first estimates in man , 1998, Heart.

[44]  Changfu Wu,et al.  On the Closing Sounds of a Mechanical Heart Valve , 2005, Annals of Biomedical Engineering.

[45]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[46]  H. Naseri,et al.  Detection and Boundary Identification of Phonocardiogram Sounds Using an Expert Frequency-Energy Based Metric , 2012, Annals of Biomedical Engineering.

[47]  Raymond L. Watrous,et al.  The Impact of Computer‐assisted Auscultation on Physician Referrals of Asymptomatic Patients with Heart Murmurs , 2008, Clinical cardiology.

[48]  Shouzhong Xiao,et al.  Evaluating two new indicators of cardiac reserve. , 2003, IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society.

[49]  Falko Skrabal,et al.  Adding "hemodynamic and fluid leads" to the ECG. Part I: the electrical estimation of BNP, chronic heart failure (CHF) and extracellular fluid (ECF) accumulation. , 2014, Medical engineering & physics.

[50]  Yineng Zheng,et al.  A novel hybrid energy fraction and entropy-based approach for systolic heart murmurs identification , 2015, Expert Syst. Appl..

[51]  Irini Reljin,et al.  Classification of Prolapsed Mitral Valve versus Healthy Heart from Phonocardiograms by Multifractal Analysis , 2013, Comput. Math. Methods Medicine.