Tools
Tools
Enwereobi, Lilian Ifeoma (2023) Brain Stroke Prediction Using Model Comparison and Feature Selections. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (721kB) | Preview |
Preview |
PDF (Configuration manual)
Download (901kB) | Preview |
Abstract
The prompt identification of strokes is a crucial medical concern that is addressed in this study. The biggest contributor to mortality and disability globally is stroke. We use feature selection methods and machine learning techniques to build prediction models to solve this issue. We investigate the efficiency of Boruta, SelectKBest, and Exhaustive Feature Selection models in enhancing stroke prediction accuracy. Throughout this research, we employed four distinct machine-learning algorithms and one deep-learning model, including XGBoost, AdaBoost, Random Forest (RF), LightGBM, and Artificial neural networks, to estimate numerous parameters such as accuracy, recall, ROC, precision, and F1 score. Our research shows that the AdaBoost classifier has a high promise for early stroke identification and treatment, with an accuracy of 0.991689. This study advances the field of stroke prediction while also emphasizing the value of feature selection in improving the effectiveness of the machine learning algorithms used in applications related to healthcare.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Ul Ain, Qurrat UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 10 Jan 2025 16:35 |
| Last Modified: | 10 Jan 2025 16:35 |
| URI: | https://norma.ncirl.ie/id/eprint/7303 |
Actions (login required)
 |
View Item |