Automatic detection of fetal health status from cardiotocography data using machine learning algorithms

Authors

  • Md Tamjid Rayhan Department of Biomedical Physics & Technology, Faculty of Science, University of Dhaka, Dhaka, Bangladesh
  • ASM Shamsul Arefin Department of Biomedical Physics & Technology, Faculty of Science, University of Dhaka, Dhaka, Bangladesh
  • Sabbir Ahmed Chowdhury Institute of Education and Research (IER), University of Dhaka, Dhaka, Bangladesh

DOI:

https://doi.org/10.3329/jbas.v45i2.57206

Keywords:

Cardiotocography, Machine Learning, Fetal health, SDG, Stillbirth.

Abstract

A method for the automatic determination of the fetus health status using Cardiotocography (CTG) and computer-based machine learning algorithms was developed. Five computation friendly machine learning algorithms were used to create multiclass classification models to predict the fetus health status from secondary CTG dataset containing normal, suspected and pathologic data available at University California Irvine Machine Learning Repository. Furthermore, a comparative analysis among the built models was executed. According to the comparative analysis, the best model to automatically detect fetal health was the extreme gradient boosting algorithm-based model with an accuracy of 96.7% and an F1-Score of 0.963 in the pathologic class. This finding thus has the potential to diagnose fetal heart conditions unsupervised, and more efficiently and effectively.

J. Bangladesh Acad. Sci. 45(2); 155-167: December 2021

Downloads

Download data is not yet available.
Abstract
102
PDF
71

Downloads

Published

2022-01-26

How to Cite

Rayhan, M. T. ., Arefin, A. S. ., & Chowdhury, S. A. . (2022). Automatic detection of fetal health status from cardiotocography data using machine learning algorithms. Journal of Bangladesh Academy of Sciences, 45(2), 155–167. https://doi.org/10.3329/jbas.v45i2.57206

Issue

Section

Research Articles