Computer-aided diagnosis of diabetic subjects by heart rate variability signals using discrete wavelet transform method

Acharya, U.R. and Sudarshan, V.K. and Ghista, D.N. and Lim, W.J.E. and Molinari, F. and Sankaranarayanan, M. (2015) Computer-aided diagnosis of diabetic subjects by heart rate variability signals using discrete wavelet transform method. Knowledge-Based Systems, 81. pp. 56-64.

[img] PDF (Computer-aided diagnosis of diabetic subjects by heart rate variability signals using discrete wavelet transform method)
Computer-aided_diagnosis_of_diabetic_subjects_by_heart_rate_variability_signals_using.pdf - Published Version
Restricted to Repository staff only

Download (1MB) | Request a copy
Official URL: http://www.sciencedirect.com/science/article/pii/S...

Abstract

Diabetes Mellitus (DM), a chronic lifelong condition, is characterized by increased blood sugar levels. As there is no cure for DM, the major focus lies on controlling the disease. Therefore, DM diagnosis and treatment is of great importance. The most common complications of DM include retinopathy, neuropathy, nephropathy and cardiomyopathy. Diabetes causes cardiovascular autonomic neuropathy that affects the Heart Rate Variability (HRV). Hence, in the absence of other causes, the HRV analysis can be used to diagnose diabetes. The present work aims at developing an automated system for classification of normal and diabetes classes by using the heart rate (HR) information extracted from the Electrocardiogram (ECG) signals. The spectral analysis of HRV recognizes patients with autonomic diabetic neuropathy, and gives an earlier diagnosis of impairment of the Autonomic Nervous System (ANS). Significant correlations with the impaired ANS are observed of the HRV spectral indices obtained by using the Discrete Wavelet Transform (DWT) method. Herein, in order to diagnose and detect DM automatically, we have performed DWT decomposition up to 5 levels, and extracted the energy, sample entropy, approximation entropy, kurtosis and skewness features at various detailed coefficient levels of the DWT. We have extracted relative wavelet energy and entropy features up to the 5th level of DWT coefficients extracted from HR signals. These features are ranked by using various ranking methods, namely, Bhattacharyya space algorithm, t-test, Wilcoxon test, Receiver Operating Curve (ROC) and entropy. The ranked features are then fed into different classifiers, that include Decision Tree (DT), K-Nearest Neighbor (KNN), Naive Bayes (NBC) and Support Vector Machine (SVM). Our results have shown maximum diagnostic differentiation performance by using a minimum number of features. With our system, we have obtained an average accuracy of 92.02, sensitivity of 92.59 and specificity of 91.46, by using DT classifier with ten-fold cross validation. (C) 2015 Elsevier B.V. All rights reserved.

Item Type: Article
Additional Information: ISI Document Delivery No.: CH0UX Times Cited: 1 Cited Reference Count: 60 Cited References: Aaron I, 2003, DIABETES CARE, V26, P1553 Acharya U. R., 2004, PHYSIOL MEAS, V25, P1139 Acharya UR, 2013, COMPUT BIOL MED, V43, P1523, DOI 10.1016/j.compbiomed.2013.05.024 Acharya UR, 2013, COMPUT METHOD BIOMEC, V16, P222, DOI 10.1080/10255842.2011.616945 Acharya UR, 2006, MED BIOL ENG COMPUT, V44, P1031, DOI 10.1007/s11517-006-0119-0 Acharya UR, 2012, EXPERT SYST APPL, V39, P9072, DOI 10.1016/j.eswa.2012.02.040 Ahamed Seyd P.T., 2008, WORLD ACAD SCI ENG T, V2, P583 Akselrod S, 1985, AM J PHYSIOL, V249, P867 American diabetes association (ADA), 2004, DIABETES CARE, V27 Anonymous, 2006, DEF DIAGN DIAB MELL Anonymous, 2013, INT DIABETES FEDERAT Anonymous, 2013, FAST FACTS DAT STAT Aurelien P., 2006, J ELECTROCARDIOL, V39, P31 Awdah A., 2002, ANN SAUDI MED, V22, P5 BELLAVERE F, 1992, DIABETES, V41, P633, DOI 10.2337/diabetes.41.5.633 Bhaskar Roy, 2013, ARQ BRAS CARDIOL Box J.F., 1987, STAT SCI, V2, P52 Cerutti S., 1989, P ANN INT C IEEE ENG, V1, P12 Chemla D, 2005, INT J CARDIOL, V104, P307, DOI 10.1016/j.ijcard.2004.12.018 Chu Duc Hoang Chu, 2013, APCBEE P, V7, P80 Dash M., 1999, ACM SIGMOD WORKSH RE Donna G., 2012, KNOWL-BASED SYST, V37, P274 Edgar E.O., 1997, TECHNICAL REPORT Faust O, 2012, BIOMED SIGNAL PROCES, V7, P295, DOI 10.1016/j.bspc.2011.06.002 Flynn Allyson C, 2005, Aust J Rural Health, V13, P77, DOI 10.1111/j.1440-1854.2005.00658.x Han J., 2005, DATA MINING CONCEPTS Herbert F.J., 2013, FRONT PHYSL COMPUT P, P4 Isabelle C., 1999, CLIN SCI, V97, P391 KAILATH T, 1967, IEEE T COMMUN TECHN, VCO15, P52, DOI 10.1109/TCOM.1967.1089532 Kheder G., 2007, 6 WSEAS INT C CIRC S Kirvela M, 1996, ACTA ANAESTH SCAND, V40, P804 Larose D.T., 2004, DISCOVERING KNOWLEDG, P90 Lee Wei Jian, 2013, J MED IMAGING HTLH I, V3, P440 MALLIANI A, 1994, BRIT HEART J, V71, P1 Metin A., 2000, NONLINEAR BIOMEDICAL, V1 Molinari F, 2013, COMPUT METH PROG BIO, V112, P518, DOI 10.1016/j.cmpb.2013.08.018 Nasim Karim, 2011, J BASIC APPL SCI, V7, P71 Nolan RP, 2009, DIABETES VASC DIS RE, V6, P276, DOI 10.1177/1479164109339965 Obuchowski NA, 2003, RADIOLOGY, V229, P3, DOI 10.1148/radiol.2291010898 Pachori R.B., 2015, EXPERT SYST IN PRESS PAN J, 1985, IEEE T BIO-MED ENG, V32, P230, DOI 10.1109/TBME.1985.325532 PFEIFER MA, 1982, DIABETES, V31, P339, DOI 10.2337/diabetes.31.4.339 Pincus A.M., 1991, P NAT ACAD SCI, V88, P2297 PINCUS SM, 1992, AM J PHYSIOL, V262, pE741 Pincus S.M., 1991, J CLIN MONITOR, P7 Pomeranz B., 1985, AM J PHYSIOL, V248, P151 Ratnakar M., 2009, INT J RECENT TRENDS, P2 Richman JS, 2000, AM J PHYSIOL-HEART C, V278, P2039 Roshan J.M., 2013, BIOMED SIGNAL PROCES, V8, P437 Schroeder EB, 2005, DIABETES CARE, V28, P668, DOI 10.2337/diacare.28.3.668 Schumacher Autumn, 2004, Biol Res Nurs, V5, P211, DOI 10.1177/1099800403260619 Shi P, 2008, J MED BIOL ENG, V28, P173 Shrah W, 2004, DIABETES CARE, V27, P1047 Singh JP, 2000, AM J CARDIOL, V86, P309, DOI 10.1016/S0002-9149(00)00920-6 Suykens JAK, 1999, NEURAL PROCESS LETT, V9, P293, DOI 10.1023/A:1018628609742 Swapna G, 2013, INTELL DATA ANAL, V17, P309, DOI 10.3233/IDA-130580 Tale Sarika, 2011, INT C BIOM ENG TECHN, V11 Trunkvalterova Z, 2008, PHYSIOL MEAS, V29, P817, DOI 10.1088/0967-3334/29/7/010 Watanabe K, 2012, DIABETES RES CLIN PR, V97, P468, DOI 10.1016/j.diabres.2012.03.004 WILCOXON F, 1945, BIOMETRICS BULL, V1, P80, DOI 10.2307/3001968 Acharya, U. Rajendra Sudarshan, Vidya K. Ghista, Dhanjoo N. Lim, Wei Jie Eugene Molinari, Filippo Sankaranarayanan, Meena Engineering, Faculty /I-7935-2015 Engineering, Faculty /0000-0002-4848-7052 1 ELSEVIER SCIENCE BV AMSTERDAM KNOWL-BASED SYST
Uncontrolled Keywords: Diabetes, hrv, classifier, dwt, feature extraction, feature ranking, spectral-analysis, entropy analysis, algorithm, features, pattern,
Subjects: T Technology > T Technology (General)
T Technology > TA Engineering (General). Civil engineering (General)
Divisions: Faculty of Engineering
Depositing User: Mr Jenal S
Date Deposited: 14 Apr 2016 06:44
Last Modified: 14 Apr 2016 06:44
URI: http://eprints.um.edu.my/id/eprint/15756

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year