Application of machine learning techniques to analyse the effects of physical exercise in ventricular fibrillation

This work presents the application of machine learning techniques to analyse the influence of physical exercise in the physiological properties of the heart, during ventricular fibrillation. To this end, different kinds of classifiers (linear and neural models) are used to classify between trained and sedentary rabbit hearts. The use of those classifiers in combination with a wrapper feature selection algorithm allows to extract knowledge about the most relevant features in the problem. The obtained results show that neural models outperform linear classifiers (better performance indices and a better dimensionality reduction). The most relevant features to describe the benefits of physical exercise are those related to myocardial heterogeneity, mean activation rate and activation complexity.

[1]  J Guerrero,et al.  Analysis of spatial and temporal evolution of regularity maps during ventricular fibrillation , 2009, 2009 36th Annual Computers in Cardiology Conference (CinC).

[2]  J Guerrero,et al.  Modifications on regularity and spectrum of ventricular fibrillation signal induced by physical training , 2009, 2009 36th Annual Computers in Cardiology Conference (CinC).

[3]  S. Harrison,et al.  Different regional effects of voluntary exercise on the mechanical and electrical properties of rat ventricular myocytes , 2002, The Journal of physiology.

[4]  G. Billman,et al.  Aerobic exercise conditioning: a nonpharmacological antiarrhythmic intervention. , 2002, Journal of applied physiology.

[5]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[6]  Sohail Asghar,et al.  A REVIEW OF FEATURE SELECTION TECHNIQUES IN STRUCTURE LEARNING , 2013 .

[7]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[8]  Zhen-Xing Zhang,et al.  Comparison of feature selection methods in ECG signal classification , 2010, ICUIMC '10.

[9]  OmerBerenfeld,et al.  Spectral Analysis Identifies Sites of High-Frequency Activity Maintaining Atrial Fibrillation in Humans , 2005 .

[10]  Antonio J. Serrano,et al.  Analysis of ventricular fibrillation signals using feature selection methods , 2012, 2012 3rd International Workshop on Cognitive Information Processing (CIP).

[11]  Chunyun Zhang,et al.  Support vector machine for arrhythmia discrimination with TCI feature selection , 2011, 2011 IEEE 3rd International Conference on Communication Software and Networks.

[13]  Luca Faes,et al.  A method for quantifying atrial fibrillation organization based on wave-morphology similarity , 2002, IEEE Transactions on Biomedical Engineering.

[14]  G. Calcagnini,et al.  Descriptors of wavefront propagation , 2006, IEEE Engineering in Medicine and Biology Magazine.

[15]  José David Martín-Guerrero,et al.  Neural networks for analysing the relevance of input variables in the prediction of tropospheric ozone concentration , 2006 .

[16]  M. Allessie,et al.  Configuration of unipolar atrial electrograms during electrically induced atrial fibrillation in humans. , 1997, Circulation.

[17]  J. Millet,et al.  Effects of chronic exercise on myocardial refractoriness: a study on isolated rabbit heart , 2008, Acta physiologica.

[18]  Pedro Larrañaga,et al.  A review of feature selection techniques in bioinformatics , 2007, Bioinform..

[19]  Antonio J. Serrano,et al.  Survival prediction in patients undergoing ischemic cardiopathy , 2009, 2009 International Joint Conference on Neural Networks.

[20]  R Bolognesi,et al.  Cardiovascular adaptations to physical exercise. , 2000, Italian heart journal : official journal of the Italian Federation of Cardiology.

[21]  G. Billman,et al.  Effect of carbachol and cyclic GMP on susceptibility to ventricular fibrillation , 1990, FASEB journal : official publication of the Federation of American Societies for Experimental Biology.

[22]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[23]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[24]  Guy Salama,et al.  Life Span of Ventricular Fibrillation Frequencies , 2002, Circulation research.

[25]  Sophia Decker,et al.  Logistic Regression A Self Learning Text , 2016 .

[26]  R. Schulz,et al.  Isolated heart perfusion according to Langendorff---still viable in the new millennium. , 2007, Journal of pharmacological and toxicological methods.

[27]  Gustavo Camps-Valls,et al.  Unbiased sensitivity analysis and pruning techniques in neural networks for surface ozone modelling , 2005 .