Barthur Prakash, Prakruthi (2024) Utilizing Advanced Machine Learning Techniques for Predicting Fetal Health Risks. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (529kB) | Preview |
Preview |
PDF (Configuration Manual)
Download (221kB) | Preview |
Abstract
The research study focuses on the application of machine learning algorithms to predict fetal health in the context of antenatal care. A predictive model is developed from such a dataset, including the baseline value, accelerations, fetal movement, uterine contractions, decelerations, without accelerations, and variability measures. Predictive models are developed, and the Boruta feature selection technique is utilized to identify the most critical features for the models. To address class imbalance, the SMOTE technique is used to increase the ability of the models to make reliable predictions across classes. Different machine learning models, such as Random Forests, GBM, Decision Trees, and K-Nearest Neighbors, are implemented on the dataset. Accuracy is combined with precision, among other performance metrics to inform the validity of the models and assess their predictive power. Among all the models implemented GBM performed well with 98% accuracy. The implications of such findings can change antenatal practices, reducing the risks associated with birthing and improving women and newborn health outcomes. The need for models capable of predicting abnormal fetal health is the research objective.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Kelly, John UNSPECIFIED |
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > Healthcare Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
Divisions: | School of Computing > Master of Science in Data Analytics |
Depositing User: | Ciara O'Brien |
Date Deposited: | 07 Aug 2025 10:21 |
Last Modified: | 07 Aug 2025 10:21 |
URI: | https://norma.ncirl.ie/id/eprint/8461 |
Actions (login required)
![]() |
View Item |