A MIXTURE MODEL CLASSIFIER AND ITS APPLICATION ON THE BIOMEDICAL TIME SERIES

This article presents a methodology based on the mixture model to classify the real biomedical time series. The mixture model is shown to be an efficient probabilistic density estimation scheme aimed at approximating the posterior probability distribution of a certain class of data. The approximation is conducted by employing a weighted mixture of a finite number of Gaussian kernels whose parameters and mixing coefficients are estimated iteratively through a maximum likelihood method. A database of the real electrocardiogram (ECG) time series of out-of-hospital cardiac arrest patients suffering ventricular fibrillation (VF) with known defibrillation outcomes was adopted to evaluate the performance of this model and confirm its efficiency compared with other classification methods.

[1]  P. Kuo,et al.  Cardiac Electrophysiology: From Cell to Bedside , 1991 .

[2]  D. McClish,et al.  Comparing the Areas under More Than Two Independent ROC Curves , 1987, Medical decision making : an international journal of the Society for Medical Decision Making.

[3]  P. Steen,et al.  Quality assessment of defribrillation and advanced life support using data from the medical control module of the defibrillator. , 1999, Resuscitation.

[4]  N. Thakor,et al.  Ventricular tachycardia and fibrillation detection by a sequential hypothesis testing algorithm , 1990, IEEE Transactions on Biomedical Engineering.

[5]  R. Dzwonczyk,et al.  Signal analysis of the human electrocardiogram during ventricular fibrillation: frequency and amplitude parameters as predictors of successful countershock. , 1996, Annals of emergency medicine.

[6]  Petter Andreas Steen,et al.  The 1998 European Resuscitation Council guidelines for adult advanced life support , 1998, BMJ.

[7]  Trygve Eftestøl,et al.  A probabilistic neural network as the predictive classifier of out-of-hospital defibrillation outcomes. , 2005, Resuscitation.

[8]  Roy L. Streit,et al.  Maximum likelihood training of probabilistic neural networks , 1994, IEEE Trans. Neural Networks.

[9]  Bernard W. Silverman,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[10]  Andrew D. Krahn,et al.  Cardiac Arrest and Sudden Cardiac Death , 2014 .

[11]  S. O. Aase,et al.  Predicting Outcome of Defibrillation by Spectral Characterization and Nonparametric Classification of Ventricular Fibrillation in Patients With Out-of-Hospital Cardiac Arrest , 2000, Circulation.

[12]  Kenneth A. Ellenbogen,et al.  Sudden cardiac death : past, present, and future , 1997 .

[13]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[14]  Sheng Chen,et al.  Robust maximum likelihood training of heteroscedastic probabilistic neural networks , 1998, Neural Networks.

[15]  Nopadol Uchaipichat,et al.  Improved prediction of defibrillation success for out-of-hospital VF cardiac arrest using wavelet transform methods. , 2004, Resuscitation.

[16]  P. J. Green,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[17]  E A Davis,et al.  The effect of epinephrine versus methoxamine on regional myocardial blood flow and defibrillation rates following a prolonged cardiorespiratory arrest in a swine model. , 1987, The American journal of emergency medicine.

[18]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[19]  R. Hamlin,et al.  Myocardial oxygen delivery/consumption during cardiopulmonary resuscitation: a comparison of epinephrine and phenylephrine. , 1988, Annals of emergency medicine.

[20]  F. Takens.  Detecting strange attractors in turbulence , 1981 .