Multi-layer Attribute Selection and Classification Algorithm for the Diagnosis of Cardiac Autonomic Neuropathy Based on HRV Attributes

Herbert F. Jelinek; Jemal H. Abawajy; David J. Cornforth; Adam Kowalczyk; Michael Negnevitsky; Morshed U. Chowdhury; Robert Krones; Andrei V. Kelarev; Herbert F. Jelinek; Jemal H. Abawajy; David J. Cornforth; Adam Kowalczyk; Michael Negnevitsky; Morshed U. Chowdhury; Robert Krones; Andrei V. Kelarev

doi:10.3934/medsci.2015.4.396

AIMS Medical Science

2015, Volume 2, Issue 4: 396-409. doi: 10.3934/medsci.2015.4.396

Previous Article Next Article

Research article

Multi-layer Attribute Selection and Classification Algorithm for the Diagnosis of Cardiac Autonomic Neuropathy Based on HRV Attributes

1.
Centre for Research in Complex Systems and School of Community Health, Charles Sturt University, Albury, NSW, Australia;
2.
School of Information Technology, Deakin University, 221 Burwood Hwy, Melbourne, Victoria 3125, Australia;
3.
School of Design Communication and IT, University of Newcastle, University Drive, Callaghan, NSW 2308, Australia;
4.
Department of Computer Science and Software Engineering, University of Melbourne, Parkville, Victoria 3010, Australia;
5.
School of Engineering & ICT, University of Tasmania, Private Bag 65, Hobart 7001, Australia;
6.
Rural Medical School, University of Melbourne, Wangaratta, Victoria, Australia

Received: 18 August 2015 Accepted: 25 November 2015 Published: 02 December 2015

Cardiac autonomic neuropathy (CAN) poses an important clinical problem, which often remains undetected due difficulty of conducting the current tests and their lack of sensitivity. CAN has been associated with growth in the risk of unexpected death in cardiac patients with diabetes mellitus. Heart rate variability (HRV) attributes have been actively investigated, since they are important for diagnostics in diabetes, Parkinson's disease, cardiac and renal disease. Due to the adverse effects of CAN it is important to obtain a robust and highly accurate diagnostic tool for identification of early CAN, when treatment has the best outcome. Use of HRV attributes to enhance the effectiveness of diagnosis of CAN progression may provide such a tool. In the present paper we propose a new machine learning algorithm, the Multi-Layer Attribute Selection and Classification (MLASC), for the diagnosis of CAN progression based on HRV attributes. It incorporates our new automated attribute selection procedure, Double Wrapper Subset Evaluator with Particle Swarm Optimization (DWSE-PSO). We present the results of experiments, which compare MLASC with other simpler versions and counterpart methods. The experiments used our large and well-known diabetes complications database. The results of experiments demonstrate that MLASC has significantly outperformed other simpler techniques.
- diabetes,
- cardiac autonomic neuropathy,
- neurology,
- heart rate variability,
- data mining,
- knowledge discovery,
- Rényi entropy
Citation: Herbert F. Jelinek, Jemal H. Abawajy, David J. Cornforth, Adam Kowalczyk, Michael Negnevitsky, Morshed U. Chowdhury, Robert Krones, Andrei V. Kelarev. Multi-layer Attribute Selection and Classification Algorithm for the Diagnosis of Cardiac Autonomic Neuropathy Based on HRV Attributes[J]. AIMS Medical Science, 2015, 2(4): 396-409. doi: 10.3934/medsci.2015.4.396

Related Papers:

Abstract

Cardiac autonomic neuropathy (CAN) poses an important clinical problem, which often remains undetected due difficulty of conducting the current tests and their lack of sensitivity. CAN has been associated with growth in the risk of unexpected death in cardiac patients with diabetes mellitus. Heart rate variability (HRV) attributes have been actively investigated, since they are important for diagnostics in diabetes, Parkinson's disease, cardiac and renal disease. Due to the adverse effects of CAN it is important to obtain a robust and highly accurate diagnostic tool for identification of early CAN, when treatment has the best outcome. Use of HRV attributes to enhance the effectiveness of diagnosis of CAN progression may provide such a tool. In the present paper we propose a new machine learning algorithm, the Multi-Layer Attribute Selection and Classification (MLASC), for the diagnosis of CAN progression based on HRV attributes. It incorporates our new automated attribute selection procedure, Double Wrapper Subset Evaluator with Particle Swarm Optimization (DWSE-PSO). We present the results of experiments, which compare MLASC with other simpler versions and counterpart methods. The experiments used our large and well-known diabetes complications database. The results of experiments demonstrate that MLASC has significantly outperformed other simpler techniques.

References

[1]	Colagiuri S, Colagiuri R, Ward J (1998) National diabetes strategy and implementation plan. Canberra: Paragon Printers.
[2]	Pop-Busui R, Evans GW, Gerstein HC, et al. (2010) The ACCORD Study Group. Effects of cardiac autonomic dysfunction on mortality risk in the Action to Control Cardiovascular Risk in Diabetes (ACCORD) Trial. Diab Care 33: 1578-1584.
[3]	Spallone V, Ziegler D, Freeman R, et al. (2011) Cardiovascular autonomic neuropathy in diabetes: clinical impact, assessment, diagnosis, and management. Diab Metab Res Rev 27: 639-653.
[4]	Dimitropoulos G, Tahrani AA, Stevens MJ (2014) Cardiac autonomic neuropathy in patients with diabetes mellitus. World J Diab 5: 17-39. doi: 10.4239/wjd.v5.i1.17
[5]	Vinik AI, Erbas T, Casellini CM (2013) Diabetic cardiac autonomic neuropathy, inflammation and cardiovascular disease. J Diabetes Investig 4: 4-18. doi: 10.1111/jdi.12042
[6]	Task Force of The European Society of Cardiology and The North American Society of Pacing and Electrophysiology (1996) Special report: heart rate variability standards of measurement, physiological interpretation, and clinical use. Circulation 93: 1043-1065. doi: 10.1161/01.CIR.93.5.1043
[7]	Jelinek HF, Abawajy JH, Kelarev AV, et al. (2014) Decision trees and multi-level ensemble classifiers for neurological diagnostics. AIMS Med Sci 1: 1-12.
[8]	Dietrich DF, Schindler C, Schwartz J, et al. (2006) Heart rate variability in an ageing population and its association with lifestyle and cardiovascular risk factors: results of the SAPALDIA study. Europace 8: 521-529.
[9]	Lake DE, Richman JS, Griffin MP, et al. (2002) Sample entropy analysis of neonatal heart rate variability. Am J Physiol 283: 789-797.
[10]	La Rovere MT, Pinna GD, Maestri R, et al. (2003) Short-term heart rate variability strongly predicts sudden cardiac death in chronic heart failure patients. Circulation 107: 565-570. doi: 10.1161/01.CIR.0000047275.25795.17
[11]	Huikuri HV, Linnaluoto MK, Seppänen T, et al. (1992) Circadian rhythm of heart rate variability in survivors of cardiac arrest. Am J Cardiol 70: 610-615. doi: 10.1016/0002-9149(92)90200-I
[12]	Cornforth DJ, Tarvainen MP, Jelinek HF (2014) Visualization methods for assisting detection of cardiovascular neuropathy. Engineering in Medicine and Biology Society (EMBC2014) 36th Annual International Conference of the IEEE, 26-30 Aug. 2014, 6675-6678.
[13]	Tarvainen MP, Cornforth DJ, Jelinek HF (2014) Principal component analysis of heart rate variability data in assessing cardiac autonomic neuropathy. Engineering in Medicine and Biology Society (EMBC2014), 36th Annual International Conference of the IEEE, 26-30 Aug. 2014, 6667-6670.
[14]	Abawajy J, Kelarev A, Chowdhury M (2013) Multistage approach for clustering and classification of ECG data. Comp Meth Pro Biomed 112: 720-730.
[15]	Abawajy J, Kelarev A, Chowdhury M, et al. (2013) Predicting cardiac autonomic neuropathy category for diabetic data with missing values, Comp Bio Med 43: 1328-1333.
[16]	Stranieri A, Abawajy J, Kelarev A, et al. (2013) An approach for Ewing test selection to support the clinical assessment of cardiac autonomic neuropathy. Art Intel Med 58: 185-193. doi: 10.1016/j.artmed.2013.04.007
[17]	Jelinek HF, Yatsko A, Stranieri A, et al. (2015) Diagnostic with incomplete nominal/discrete data. Art Intel Med 4: 22-35.
[18]	Cornforth D, Jelinek HF (2007) Automated classification reveals morphological factors associated with dementia, App Soft Compu 8: 182-190.
[19]	Ewing DJ, Campbell JW, Clarke BF (1980) The natural history of diabetic autonomic neuropathy. Q J Med 49: 95-100.
[20]	Ewing DJ, Martyn CN, Young RJ, et al. (1985) The value of cardiovascular autonomic functions tests: 10 years experience in diabetes. Diab Care 8: 491-498. doi: 10.2337/diacare.8.5.491
[21]	Khandoker AH, Jelinek HF, Palaniswami M (2009) Identifying diabetic patients with cardiac autonomic neuropathy by heart rate complexity analysis. BioMed Engine Online 8: 1-12. doi: 10.1186/1475-925X-8-1
[22]	Thayer JF, Yamamoto SS, Brosschot JF (2010) The relationship of autonomic imbalance, heart rate variability and cardiovascular disease risk factors, Int J Cardiol 141: 122-131.
[23]	Karmakar CK, Khandoker AH, Jelinek HF, et al. (2013) Risk stratification of cardiac autonomic neuropathy based on multi-lag Tone-Entropy. Med Bio Engine Comp 51: 537-546. doi: 10.1007/s11517-012-1022-5
[24]	Tan CO (2013) Heart rate variability: are there complex patterns? Front Physiol 4: 1-3.
[25]	Imam MH, Karmakar C, Khandoker AH, et al. (2014) Analysing cardiac autonomic neuropathy in diabetes using electrocardiogram derived systolic-diastolic interval interactions. Compu Cardiol 41: 85-88.
[26]	Spallone V, Menzinger G (1997) Diagnosis of cardiovascular autonomic neuropathy in diabetes. Diabetes 46: 67-76. doi: 10.2337/diab.46.2.S67
[27]	Jelinek HF, Pham P, Struzik ZR, et al. (2007) Short term ECG recording for the identification of cardiac autonomic neuropathy in people with diabetes mellitus. Proceedings of the 19th International Conference on Noise and Fluctuations, Tokyo, Japan, pp. 683-686.
[28]	Khandoker AH, Weiss DN, Skinner JE, et al. (2011) PD2i heart rate complexity measure can detect cardiac autonomic neuropathy: an alternative test to Ewing battery. Compu Cardiol 38: 525-528.
[29]	TFESC/NASPE (1996) Heart rate variability. Standards of measurement, physiological interpretation, and clinical use. Task Force of the European Society of Cardiology and the North American Society of Pacing and Electrophysiology. Euro Heart J 17: 354-381.
[30]	Goldberger AL, Amaral LAN, Hausdorff JM, et al. (2002) Fractal dynamics in physiology: Alterations with disease and aging. Pro Nat Aca Sci USA 99: 2466-2472. doi: 10.1073/pnas.012579499
[31]	Peng CK, Havlin S, Stanley HE, et al. (1995) Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series. Chaos 5: 82-87. doi: 10.1063/1.166141
[32]	Ho YL, Lin C, Lin YH, et al. (2011). The prognostic value of non-linear analysis of heart rate variability in patients with congestive heart failure—a pilot study of multiscale entropy. PLoS ONE 6: 1-6.
[33]	Sturmberg JP, Bennett JM, Picard M, et al. (2015) The trajectory of life. Decreasing physiological network complexity through changing fractal patterns. Front Physiol 6: 1-11.
[34]	Oida ET, Moritani KT, Yamori Y (1999) Diabetic alteration of cardiac vago-sympathetic modulation assessed with tone-entropy analysis. Acta Physiol Scandi 165: 129-135. doi: 10.1046/j.1365-201x.1999.00494.x
[35]	Lake DE, Moorman JR (2011) Accurate estimation of entropy in very short physiological time series: the problem of atrial fibrillation detection in implanted ventricular devices. Am J Physiol Heart Cicul Physiol 300: H319-325. doi: 10.1152/ajpheart.00561.2010
[36]	Jelinek HF, Khandoker A, Palaniswami M, et al. (2010) Tone-entropy analysis as a cardiac risk stratification tool. Compu Cardiol 37: 955-958.
[37]	Quinlan R (1993) C4.5: Programs for Machine Learning. San Mateo, CA: Morgan Kaufmann Publishers.
[38]	Breiman L (2001) Random Forests. Machine Learning 45:5-32. doi: 10.1023/A:1010933404324
[39]	Williams G (2011) Data mining with Rattle and R: the art of excavating data for knowledge discovery (use R!). New York, Dordrecht, Heidelberg, London: Springer.
[40]	Platt J (1998) Fast training of support vector machines using sequential minimal optimization. In: Schoelkopf B, Burges C, Smola A, editors, Advances in Kernel Methods—Support Vector Learning 41-64.
[41]	Witten H, Frank E, Hall MA (2011) Data mining: practical machine learning tools and techniques with java implementations. 3ed, New York, Sydney: Morgan Kaufmann, 2011.
[42]	Bouckaert, RR, Frank E, Hall M, et al. WEKA manual for version 3-7-13, http://www.cs.waikato.ac.nz/ml/weka/, viewed 15 July 2015.
[43]	Hall M, Frank E, Holmes G, et al. (2009) The WEKA data mining software: an update. SIGKDD Explor 11: 10-18.
[44]	Negnevitsky M (2011) Artificial intelligence: a guide to intelligent systems. 3rd eds., New York: Addison Wesley.
[45]	Williams GJ (2009) Rattle: a data mining GUI for R, The R J 1: 45-55.
[46]	Kohavi R, John GH (1997) Wrappers for feature subset selection. Art Intell 97:273-324. doi: 10.1016/S0004-3702(97)00043-X
[47]	Goldberg DE (1989) Genetic algorithms in search, optimization and machine learning. New York: Addison-Wesley.
[48]	Cornforth DJ, Jelinek HF, Teich MC, et al. (2004) Wrapper subset evaluation facilitates the automated detection of diabetes from heart rate variability measures. Proceedings of the International Conference on Computational Intelligence for Modelling Control and Automation (CIMCA'2004), University of Canberra, Australia, pp. 446-455.
[49]	Moraglio A, Di Chio C, Poli R (2007) Geometric Particle Swarm Optimisation. Proceedings of the 10th European Conference on Genetic Programming, Berlin, Heidelberg, 125-136.
[50]	Demsar J (2006) Statistical comparisons of classifiers over multiple data sets. J Machine Learning Res 7: 1-30.
[51]	Dietterich TG (1998) Approximate statistical tests for comparing supervised classification learning algorithms. Neural Compu 10: 1895-1924. doi: 10.1162/089976698300017197
[52]	Cornforth D, Tarvainen M, Jelinek HF (2014) How to calculate Rényi entropy from Heart Rate Variability, and why it matters for detecting cardiac autonomic neuropathy. Front Bioeng Biotecho 2: 1-7.
[53]	Ziegler DA, Rathmann VW, Strom A, et al. (2015) Increased prevalence of cardiac autonomic dysfunction at different degrees of glucose intolerance in the general population: the KORA S4 survey. Diabetologia 58:1118-1128. doi: 10.1007/s00125-015-3534-7

Reader Comments

Your name:*

Email:*
© 2015 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)