Comparison of Different EHG Feature Selection Methods for the Detection of Preterm Labor

Numerous types of linear and nonlinear features have been extracted from the electrohysterogram (EHG) in order to classify labor and pregnancy contractions. As a result, the number of available features is now very large. The goal of this study is to reduce the number of features by selecting only the relevant ones which are useful for solving the classification problem. This paper presents three methods for feature subset selection that can be applied to choose the best subsets for classifying labor and pregnancy contractions: an algorithm using the Jeffrey divergence (JD) distance, a sequential forward selection (SFS) algorithm, and a binary particle swarm optimization (BPSO) algorithm. The two last methods are based on a classifier and were tested with three types of classifiers. These methods have allowed us to identify common features which are relevant for contraction classification.

[1]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[2]  M. Lucovnik,et al.  Noninvasive uterine electromyography for prediction of preterm delivery. , 2011, American journal of obstetrics and gynecology.

[3]  Hualou Liang,et al.  Variance Entropy: A Method for Characterizing Perceptual Awareness of Visual Stimulus , 2012, Appl. Comput. Intell. Soft Comput..

[4]  Russell C. Eberhart,et al.  A discrete binary version of the particle swarm algorithm , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[5]  C. Marque,et al.  Traitement de l'électromyogramme utérin pour la caractérisation des contractions pendant la grossesse , 1999 .

[6]  G. Fele-Zorz,et al.  A comparison of various linear and non-linear signal processing techniques to separate uterine EMG records of term and pre-term delivery groups , 2008, Medical & Biological Engineering & Computing.

[7]  David W. Aha,et al.  A Comparative Evaluation of Sequential Feature Selection Algorithms , 1995, AISTATS.

[8]  Brynjar Karlsson,et al.  Synchronization between EMG at Different Uterine Locations Investigated Using Time-Frequency Ridge Reconstruction: Comparison of Pregnancy and Labor Contractions , 2010, EURASIP J. Adv. Signal Process..

[9]  Russell C. Eberhart,et al.  A new optimizer using particle swarm theory , 1995, MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science.

[10]  Sri Ramakrishna,et al.  FEATURE SELECTION METHODS AND ALGORITHMS , 2011 .

[11]  L. Ladha,et al.  FEATURE SELECTION METHODS AND ALGORITHMS , 2011 .

[12]  Jerzy Sikora,et al.  Recognition of premature threatening labour symptoms from bioelectrical uterine activity signals , 2011 .

[13]  A. Ebrahimzadeh,et al.  Application of the PSO-SVM model for recognition of control chart patterns. , 2010, ISA transactions.

[14]  G. Saade,et al.  Predicting Term and Preterm Delivery With Transabdominal Uterine Electromyography , 2003, Obstetrics and gynecology.

[15]  Mohamad Khalil.  Une approche de la détection et de la classification dans les signaux non stationnaires : application à l'EGM uterin , 1999 .

[16]  Xiaodong Gu,et al.  Histogram similarity measure using variable bin size distance , 2010, Comput. Vis. Image Underst..

[17]  M. A. Gray,et al.  Automated differentiation of pre-diagnosis Huntington's disease from healthy control individuals based on quadratic discriminant analysis of the basal ganglia: The IMAGE-HD study , 2013, Neurobiology of Disease.

[18]  Ahmad Diab,et al.  Quantitative performance analysis of four methods of evaluating signal nonlinearity: Application to uterine EMG signals , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[19]  H ALVAREZ,et al.  Contractility of the human uterus recorded by new methods. , 1950, Surgery, gynecology & obstetrics.

[20]  Tijana T. Ivancevic,et al.  Preterm Birth Analysis Using Nonlinear Methods , 2008 .

[21]  Catherine Marque,et al.  CLASSIFICATION FOR UTERINE EMG SIGNALS: COMPARISON BETWEEN AR MODEL AND STATISTICAL CLASSIFICATION METHOD , 2007 .

[22]  C. Marque,et al.  Abdominal EHG on a 4 by 4 grid: mapping and presenting the propagation of uterine contractions , 2007 .

[23]  W. Maner,et al.  Physiology and electrical activity of uterine contractions. , 2007, Seminars in cell & developmental biology.

[24]  T. Lander,et al.  Neonatal and perinatal mortality: country, regional and global estimates. , 2006 .

[25]  Brynjar Karlsson,et al.  Better Pregnancy Monitoring Using Nonlinear Correlation Analysis of External Uterine Electromyography , 2013, IEEE Transactions on Biomedical Engineering.

[26]  Roberto Romero,et al.  Epidemiology and causes of preterm birth , 2008, The Lancet.

[27]  S. Dudoit,et al.  Comparison of Discrimination Methods for the Classification of Tumors Using Gene Expression Data , 2002 .

[28]  Catherine Marque,et al.  Parameters extraction and monitoring in uterine EMG signals. Detection of preterm deliveries , 2013 .

[29]  C Marque,et al.  Uterine electromyography: a critical review. , 1993, American journal of obstetrics and gynecology.

[30]  E. LESTER SMITH,et al.  AND OTHERS , 2005 .