Page 63 - AIH-1-1

Artificial Intelligence in Health

ORIGINAL RESEARCH ARTICLE
Unveiling the unborn: Advancing fetal health

classification through machine learning

Sujith K. Mandala*
Department of Information Technology, St. Martin’s Engineering College, Hyderabad, Telangana, India

Abstract

Fetal health classification is a critical task in obstetrics, which enables early
identification and management of potential health problems. However, it remains a
challenging task due to data complexity and limited labeled samples. This research
paper presents a novel machine-learning approach for fetal health classification,
leveraging a LightGBM classifier trained on a comprehensive dataset. The proposed
model achieves an impressive accuracy of 98.31% on a test set. The findings
demonstrate machine learning can potentially enhance fetal health classification,
offering a more objective and accurate assessment. Notably, the presented approach
combines various features, such as fetal heart rate, uterine contractions, and maternal
blood pressure, to provide a comprehensive evaluation. This methodology holds
promise for improving early detection and treatment of fetal health issues, ensuring
better outcomes for both mothers and babies. In addition to the high accuracy, the
novelty of this approach lies in its comprehensive feature selection and assessment
methodology. By incorporating multiple data points, this model offers a more holistic
and reliable evaluation compared to traditional methods. This research has significant
implications in the field of obstetrics, paving the way for advancements in early
*Corresponding author: detection and intervention of fetal health concerns. Future work involves validating
Sujith K. Mandala
(sujithkmandala15@gmail.com) the model on a larger dataset and developing a clinical application. Ultimately, we
anticipate that our research will revolutionize the assessment and management of
Citation: Mandala SK, 2024,
Unveiling the unborn: Advancing fetal health, contributing to improved healthcare outcomes for expectant mothers
fetal health classification through and their fetuses.
machine learning. Artif Intell
Health, 1(1): 57-67.
https://doi.org/10.36922/aih.2121 Keywords: LightGBM; Fetal health; Machine learning; Cardiotocography; Artificial
Received: October 26, 2023 intelligence
Accepted: December 20, 2023
Published Online: December 26, 2023
Copyright: © 2024 Author(s). 1. Introduction
This is an Open-Access article Fetal health classification is a critical task in obstetrics, as it can help identify and manage
distributed under the terms of the
Creative Commons Attribution fetal health problems at early stage. Accurate assessment of fetal health is crucial for timely
License, permitting distribution, intervention and improved health-care outcomes for both mothers and their babies.
and reproduction in any medium, Traditional methods of fetal health assessment rely on subjective interpretations and
provided the original work is
properly cited. limited sets of features, which may lead to inconsistent results and delayed interventions.
Publisher’s Note: AccScience In recent years, machine learning (ML) techniques have emerged as powerful tools for
Publishing remains neutral with medical data analysis and classification tasks. ML models have the potential to provide
regard to jurisdictional claims in
published maps and institutional a more objective and accurate assessment regarding the fetal health by leveraging a wide
affiliations. range of data points and complex patterns. Through learning from vast amounts of

Volume 1 Issue 1 (2024) 57 https://doi.org/10.36922/aih.2121