Journal: Journal of Pharmacy Research

Article Id: JPRS-GS-00001920
Title: Modeling fetal morphologic patterns through cardiotocography data: Decision tree-based approach
Category: General Sciences
  • Abstract
  • Audio Abstract
  • Authors
  • Pdf File
  • Citation
  • My Reference
  • Methodology
  • Abstract

    Objective: The present research aims at decision tree (DT) modeling of fetal morphologic patterns by exploring cardiotocography (CTG). CTG consists of fetal heart rate and topographic measurements and is used for the verification of fetal health. Materials and Methods: In the present study, we have carried out DT modeling for CTGs data classification based on fetal morphologic patterns. Decision tree model is the most commonly used data mining technique for classification and prediction. The dataset employed in the present study comprises ten classes of morphologic patterns with a sample size of 2126 records. The optimum decision tree model is derived by tuning parameters such as min split, min bucket, max depth, and complexity. This model entails recursive partitioning approach implemented in the “rpart” package of R. The performance of the model is evaluated in terms of mean square error estimate of error rate. Results: Thus, derived decision tree model leads to values for tuning parameters such as min split, min bucket, max depth, and complexity are 20, 7, 30, and 0.01, respectively. The 1488 observations from the inputted dataset are considered for the construction of the tree. Root node error is 0.7211. Thus, derived DT model efficiently classifies validation data with very less error. Conclusion: The result suggests that the DT modeling has the potential to exhibit as the best tool for modeling of CTG data.

  • Abstract Audio

    No Audio file found

  • About the authors and Affiliations

    Author(s) Name:

    R. S. Kamath1*, R. K. Kamat2

    Affiliation(s) Name:

    1Department of Computer Studies, Chhatrapati Shahu Institute of Business Education and Research, Kolhapur, Maharashtra, India,
    2Department of Electronics, Shivaji University, Kolhapur, Maharashtra, India

    *Corresponding author: R. S. Kamath, Department of Computer Studies, Chhatrapati Shahu Institute of Business Education and Research, University Road, Kolhapur, Maharashtra, India.

  • View Article File in pdf format.

    Article File
  • View Article Citation Here.

    0 View More
  • How to Cite my Article.

    Author:

    R. S. Kamath1*, R. K. Kamat2

    Title:Modeling fetal morphologic patterns through cardiotocography data: Decision tree-based approach
    Journal:Journal of Pharmacy Research
    Vol(issue):12(1)
    Year:2018
    Page No: (9-12)
  • Experimental Methods Keywords

    Methodology:Classification, Decision tree, Fetal morphologic pattern, Rattle
    Research Materials:cardiotocography data

Keywords

Cardiotocography Classification Decision tree Fetal morphologic pattern Rattle

Our Services

Most Downloaded List