Citation: Kuzu, A.; Santur, Y. Early
Diagnosis and Classification of Fetal
Health Status from a Fetal
Cardiotocography Dataset Using
Ensemble Learning. Diagnostics 2023,
13, 2471. https://doi.org/10.3390/
diagnostics13152471
Academic Editor: Ayman El-Baz
Received: 9 July 2023
Revised: 21 July 2023
Accepted: 22 July 2023
Published: 25 July 2023
Copyright: © 2023 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
diagnostics
Article
Early Diagnosis and Classification of Fetal Health Status from a
Fetal Cardiotocography Dataset Using Ensemble Learning
Adem Kuzu
1
and Yunus Santur
2,
*
1
Department of Software Engineering, Firat University, Elazig 23119, Turkey; ademkuzu@gmail.com
2
Department of Artificial Intelligence and Data Engineering, Firat University, Elazig 23119, Turkey
* Correspondence: ysantur@firat.edu.tr
Abstract: (1) Background: According to the World Health Organization (WHO), 6.3 million intrauter-
ine fetal deaths occur every year. The most common method of diagnosing perinatal death and
taking early precautions for maternal and fetal health is a nonstress test (NST). Data on the fetal
heart rate and uterus contractions from an NST device are interpreted based on a trace printer’s
output, allowing for a diagnosis of fetal health to be made by an expert. (2) Methods: in this study,
a predictive method based on ensemble learning is proposed for the classification of fetal health
(normal, suspicious, pathology) using a cardiotocography dataset of fetal movements and fetal heart
rate acceleration from NST tests. (3) Results: the proposed predictor achieved an accuracy level above
99.5% on the test dataset. (4) Conclusions: from the experimental results, it was observed that a fetal
health diagnosis can be made during NST using machine learning.
Keywords: ensemble learning; fetal health; FHR; NST
1. Introduction
Fetal deaths occurring between the 22nd week of pregnancy and the first 7 days
after birth are known as perinatal mortality [1]. The World Health Organization (WHO)
has reported that 6.3 million perinatal deaths occur every year. In this report, perinatal
cases are scaled to a value per 1000 births, and the development rates of countries are
considered to be a critical factor affecting this rate. While this value is lower than 10 in
developed countries, it is higher in less developed ones and exceeds 30 in underdeveloped
countries [2].
Perinatal cases may result in maternal poisoning/death as well as death for the
fetus/infant. The most effective method of early diagnosis is to perform a periodic nonstress
test (NST). From the 32nd week of pregnancy, an NST procedure is required every week.
The NST device is typically connected to a pregnant woman for 20 min, with two separate
probes recording data on fetal heart rate (FHR) and uterine contractions (UCs) [3,4]. The
NST device has a memory unit and generates a trace by obtaining FHR and UC data with
respect to a basal average of 10 s, as shown in Figure 1.
Figure 1. Example of an NST trace.
Diagnostics 2023, 13, 2471. https://doi.org/10.3390/diagnostics13152471 https://www.mdpi.com/journal/diagnostics