Automated detection of premature delivery using empirical mode and wavelet packet decomposition techniques with uterine electromyogram signals

U. Rajendra Acharya, Vidya K. Sudarshan, Soon Qing Rong, Zechariah Tan, Choo Min Lim, Joel EW Koh, Sujatha Nayak, Sulatha V. Bhandary

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

An accurate detection of preterm labor and the risk of preterm delivery before 37 weeks of gestational age is crucial to increase the chance of survival rate for both mother and the infant. Thus, the uterine contractions measured using uterine electromyogram (EMG) or electro hysterogram (EHG) need to have high sensitivity in the detection of true preterm labor signs. However, visual observation and manual interpretation of EHG signals at the time of emergency situation may lead to errors. Therefore, the employment of computer-based approaches can assist in fast and accurate detection during the emergency situation. This work proposes a novel algorithm using empirical mode decomposition (EMD) combined with wavelet packet decomposition (WPD), for automated prediction of pregnant women going to have premature delivery by using uterine EMG signals. The EMD is performed up to 11 levels on the normal and preterm EHG signals to obtain the different intrinsic mode functions (IMFs). These IMFs are further subjected to 6 levels of WPD and from the obtained coefficients, eight different features are extracted. From these extracted features, only the significant features are selected using particle swarm optimization (PSO) method and selected features are ranked by Bhattacharyya technique. All the ranked features are fed to support vector machine (SVM) classifier for automated differentiation and achieved an accuracy of 96.25%, sensitivity of 95.08%, and specificity of 97.33% using only ten EHG signal features. Our proposed algorithm can be used in gynecology departments of hospitals to predict the preterm or normal delivery of pregnant women.

Original languageEnglish
Pages (from-to)33-42
Number of pages10
JournalComputers in Biology and Medicine
Volume85
DOIs
Publication statusPublished - 01-06-2017

Fingerprint

Premature Obstetric Labor
Electromyography
Pregnant Women
Emergencies
Decomposition
Uterine Contraction
Hospital Departments
Gynecology
Gestational Age
Survival Rate
Mothers
Observation
Personnel
Sensitivity and Specificity
Particle swarm optimization (PSO)
Support vector machines
Classifiers
Support Vector Machine

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Health Informatics

Cite this

Acharya, U. Rajendra ; Sudarshan, Vidya K. ; Rong, Soon Qing ; Tan, Zechariah ; Lim, Choo Min ; Koh, Joel EW ; Nayak, Sujatha ; Bhandary, Sulatha V. / Automated detection of premature delivery using empirical mode and wavelet packet decomposition techniques with uterine electromyogram signals. In: Computers in Biology and Medicine. 2017 ; Vol. 85. pp. 33-42.
@article{22a93c1e64d74e349066f4abb037e9de,
title = "Automated detection of premature delivery using empirical mode and wavelet packet decomposition techniques with uterine electromyogram signals",
abstract = "An accurate detection of preterm labor and the risk of preterm delivery before 37 weeks of gestational age is crucial to increase the chance of survival rate for both mother and the infant. Thus, the uterine contractions measured using uterine electromyogram (EMG) or electro hysterogram (EHG) need to have high sensitivity in the detection of true preterm labor signs. However, visual observation and manual interpretation of EHG signals at the time of emergency situation may lead to errors. Therefore, the employment of computer-based approaches can assist in fast and accurate detection during the emergency situation. This work proposes a novel algorithm using empirical mode decomposition (EMD) combined with wavelet packet decomposition (WPD), for automated prediction of pregnant women going to have premature delivery by using uterine EMG signals. The EMD is performed up to 11 levels on the normal and preterm EHG signals to obtain the different intrinsic mode functions (IMFs). These IMFs are further subjected to 6 levels of WPD and from the obtained coefficients, eight different features are extracted. From these extracted features, only the significant features are selected using particle swarm optimization (PSO) method and selected features are ranked by Bhattacharyya technique. All the ranked features are fed to support vector machine (SVM) classifier for automated differentiation and achieved an accuracy of 96.25{\%}, sensitivity of 95.08{\%}, and specificity of 97.33{\%} using only ten EHG signal features. Our proposed algorithm can be used in gynecology departments of hospitals to predict the preterm or normal delivery of pregnant women.",
author = "Acharya, {U. Rajendra} and Sudarshan, {Vidya K.} and Rong, {Soon Qing} and Zechariah Tan and Lim, {Choo Min} and Koh, {Joel EW} and Sujatha Nayak and Bhandary, {Sulatha V.}",
year = "2017",
month = "6",
day = "1",
doi = "10.1016/j.compbiomed.2017.04.013",
language = "English",
volume = "85",
pages = "33--42",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",

}

Automated detection of premature delivery using empirical mode and wavelet packet decomposition techniques with uterine electromyogram signals. / Acharya, U. Rajendra; Sudarshan, Vidya K.; Rong, Soon Qing; Tan, Zechariah; Lim, Choo Min; Koh, Joel EW; Nayak, Sujatha; Bhandary, Sulatha V.

In: Computers in Biology and Medicine, Vol. 85, 01.06.2017, p. 33-42.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated detection of premature delivery using empirical mode and wavelet packet decomposition techniques with uterine electromyogram signals

AU - Acharya, U. Rajendra

AU - Sudarshan, Vidya K.

AU - Rong, Soon Qing

AU - Tan, Zechariah

AU - Lim, Choo Min

AU - Koh, Joel EW

AU - Nayak, Sujatha

AU - Bhandary, Sulatha V.

PY - 2017/6/1

Y1 - 2017/6/1

N2 - An accurate detection of preterm labor and the risk of preterm delivery before 37 weeks of gestational age is crucial to increase the chance of survival rate for both mother and the infant. Thus, the uterine contractions measured using uterine electromyogram (EMG) or electro hysterogram (EHG) need to have high sensitivity in the detection of true preterm labor signs. However, visual observation and manual interpretation of EHG signals at the time of emergency situation may lead to errors. Therefore, the employment of computer-based approaches can assist in fast and accurate detection during the emergency situation. This work proposes a novel algorithm using empirical mode decomposition (EMD) combined with wavelet packet decomposition (WPD), for automated prediction of pregnant women going to have premature delivery by using uterine EMG signals. The EMD is performed up to 11 levels on the normal and preterm EHG signals to obtain the different intrinsic mode functions (IMFs). These IMFs are further subjected to 6 levels of WPD and from the obtained coefficients, eight different features are extracted. From these extracted features, only the significant features are selected using particle swarm optimization (PSO) method and selected features are ranked by Bhattacharyya technique. All the ranked features are fed to support vector machine (SVM) classifier for automated differentiation and achieved an accuracy of 96.25%, sensitivity of 95.08%, and specificity of 97.33% using only ten EHG signal features. Our proposed algorithm can be used in gynecology departments of hospitals to predict the preterm or normal delivery of pregnant women.

AB - An accurate detection of preterm labor and the risk of preterm delivery before 37 weeks of gestational age is crucial to increase the chance of survival rate for both mother and the infant. Thus, the uterine contractions measured using uterine electromyogram (EMG) or electro hysterogram (EHG) need to have high sensitivity in the detection of true preterm labor signs. However, visual observation and manual interpretation of EHG signals at the time of emergency situation may lead to errors. Therefore, the employment of computer-based approaches can assist in fast and accurate detection during the emergency situation. This work proposes a novel algorithm using empirical mode decomposition (EMD) combined with wavelet packet decomposition (WPD), for automated prediction of pregnant women going to have premature delivery by using uterine EMG signals. The EMD is performed up to 11 levels on the normal and preterm EHG signals to obtain the different intrinsic mode functions (IMFs). These IMFs are further subjected to 6 levels of WPD and from the obtained coefficients, eight different features are extracted. From these extracted features, only the significant features are selected using particle swarm optimization (PSO) method and selected features are ranked by Bhattacharyya technique. All the ranked features are fed to support vector machine (SVM) classifier for automated differentiation and achieved an accuracy of 96.25%, sensitivity of 95.08%, and specificity of 97.33% using only ten EHG signal features. Our proposed algorithm can be used in gynecology departments of hospitals to predict the preterm or normal delivery of pregnant women.

UR - http://www.scopus.com/inward/record.url?scp=85018509302&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018509302&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2017.04.013

DO - 10.1016/j.compbiomed.2017.04.013

M3 - Article

VL - 85

SP - 33

EP - 42

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

ER -