Knowledge-assisted sequential pattern analysis with heuristic parameter tuning for labor contraction prediction

Zifang Huang, Mei-Ling Shyu, James M. Tien, Michael M. Vigoda, David Birnbach

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The optimal dosing regimen of remifentanil for relieving labor pain should achieve maximal efficacy during contractions and little effect between contractions. Toward such a need, we propose a knowledge-assisted sequential pattern analysis with heuristic parameter tuning to predict the changes in intrauterine pressure, which indicates the occurrence of labor contractions. This enables giving the drug shortly before each contraction starts. A sequential association rule mining based patient selection strategy is designed to dynamically select data for training regression models. A novel heuristic parameter tuning method is proposed to decide the appropriate value ranges and searching strategies for both the regularization factor and the Gaussian kernel parameter of least-squares support vector machine with radial basis function (RBF) kernel, which is used as the regression model for time series prediction. The parameter tuning method utilizes information extracted from the training dataset, and it is adaptive to the characteristics of time series. The promising experimental results show that the proposed framework is able to achieve the lowest prediction errors as compared to some existing methods.

Original languageEnglish
Article number6600763
Pages (from-to)492-499
Number of pages8
JournalIEEE Journal of Biomedical and Health Informatics
Volume18
Issue number2
DOIs
StatePublished - Jan 1 2014

Fingerprint

Tuning
Personnel
Labor Pain
Time series
Least-Squares Analysis
Patient Selection
Association rules
Support vector machines
Pressure
Pharmaceutical Preparations
Heuristics
remifentanil
Support Vector Machine
Datasets

Keywords

  • Association rule mining
  • labor contraction prediction
  • least-squares support vector machine (LS-SVM)
  • parameter tuning
  • time series prediction

ASJC Scopus subject areas

  • Biotechnology
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Health Information Management

Cite this

Knowledge-assisted sequential pattern analysis with heuristic parameter tuning for labor contraction prediction. / Huang, Zifang; Shyu, Mei-Ling; Tien, James M.; Vigoda, Michael M.; Birnbach, David.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 18, No. 2, 6600763, 01.01.2014, p. 492-499.

Research output: Contribution to journalArticle

@article{f518c149dbb64f19b3a1d7bd1e67a3c5,
title = "Knowledge-assisted sequential pattern analysis with heuristic parameter tuning for labor contraction prediction",
abstract = "The optimal dosing regimen of remifentanil for relieving labor pain should achieve maximal efficacy during contractions and little effect between contractions. Toward such a need, we propose a knowledge-assisted sequential pattern analysis with heuristic parameter tuning to predict the changes in intrauterine pressure, which indicates the occurrence of labor contractions. This enables giving the drug shortly before each contraction starts. A sequential association rule mining based patient selection strategy is designed to dynamically select data for training regression models. A novel heuristic parameter tuning method is proposed to decide the appropriate value ranges and searching strategies for both the regularization factor and the Gaussian kernel parameter of least-squares support vector machine with radial basis function (RBF) kernel, which is used as the regression model for time series prediction. The parameter tuning method utilizes information extracted from the training dataset, and it is adaptive to the characteristics of time series. The promising experimental results show that the proposed framework is able to achieve the lowest prediction errors as compared to some existing methods.",
keywords = "Association rule mining, labor contraction prediction, least-squares support vector machine (LS-SVM), parameter tuning, time series prediction",
author = "Zifang Huang and Mei-Ling Shyu and Tien, {James M.} and Vigoda, {Michael M.} and David Birnbach",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/JBHI.2013.2281974",
language = "English",
volume = "18",
pages = "492--499",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Knowledge-assisted sequential pattern analysis with heuristic parameter tuning for labor contraction prediction

AU - Huang, Zifang

AU - Shyu, Mei-Ling

AU - Tien, James M.

AU - Vigoda, Michael M.

AU - Birnbach, David

PY - 2014/1/1

Y1 - 2014/1/1

N2 - The optimal dosing regimen of remifentanil for relieving labor pain should achieve maximal efficacy during contractions and little effect between contractions. Toward such a need, we propose a knowledge-assisted sequential pattern analysis with heuristic parameter tuning to predict the changes in intrauterine pressure, which indicates the occurrence of labor contractions. This enables giving the drug shortly before each contraction starts. A sequential association rule mining based patient selection strategy is designed to dynamically select data for training regression models. A novel heuristic parameter tuning method is proposed to decide the appropriate value ranges and searching strategies for both the regularization factor and the Gaussian kernel parameter of least-squares support vector machine with radial basis function (RBF) kernel, which is used as the regression model for time series prediction. The parameter tuning method utilizes information extracted from the training dataset, and it is adaptive to the characteristics of time series. The promising experimental results show that the proposed framework is able to achieve the lowest prediction errors as compared to some existing methods.

AB - The optimal dosing regimen of remifentanil for relieving labor pain should achieve maximal efficacy during contractions and little effect between contractions. Toward such a need, we propose a knowledge-assisted sequential pattern analysis with heuristic parameter tuning to predict the changes in intrauterine pressure, which indicates the occurrence of labor contractions. This enables giving the drug shortly before each contraction starts. A sequential association rule mining based patient selection strategy is designed to dynamically select data for training regression models. A novel heuristic parameter tuning method is proposed to decide the appropriate value ranges and searching strategies for both the regularization factor and the Gaussian kernel parameter of least-squares support vector machine with radial basis function (RBF) kernel, which is used as the regression model for time series prediction. The parameter tuning method utilizes information extracted from the training dataset, and it is adaptive to the characteristics of time series. The promising experimental results show that the proposed framework is able to achieve the lowest prediction errors as compared to some existing methods.

KW - Association rule mining

KW - labor contraction prediction

KW - least-squares support vector machine (LS-SVM)

KW - parameter tuning

KW - time series prediction

UR - http://www.scopus.com/inward/record.url?scp=84896463897&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896463897&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2013.2281974

DO - 10.1109/JBHI.2013.2281974

M3 - Article

C2 - 24058036

AN - SCOPUS:84896463897

VL - 18

SP - 492

EP - 499

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 2

M1 - 6600763

ER -