Optimising Heart Attack Prediction: Comparing Deep Learning and Traditional Machine Learning Techniques

-, Melbin Biju (2024) Optimising Heart Attack Prediction: Comparing Deep Learning and Traditional Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (980kB) | Preview
Preview	PDF (Configuration Manual) Download (447kB) | Preview

Abstract

This research focuses on understanding the effect of deep learning techniques for predicting heart attack risk in comparison with the traditional machine learning models. Heart disease, especially heart attack, is a global leading cause of mortality and early risk prediction is important for saving the life of patients and better health outcomes. This study aims at comparing the performance of deep learning model, namely Multilayer Perceptron (MLP), with traditional machine learning models such as Logistic Regression, Random Forest, XGBoost and Support Vector Machine (SVM). Based on a dataset comprising demographic, clinical, and medical features, selected models were trained and tested to assess risks of heart attacks. Different metrics such as accuracy, precision, recall, F1 score, and AUC were used in the evaluation of the models. The findings showed that performance of the MLP model was higher compared to other traditional machine learning models, especially in recall, which is necessary for the identification of high-risk patients and minimising false negatives. Implementation of hyperparameter tuning further increased the model performance and strengthened the applicability of deep learning models in clinical practice. This research adds to the current knowledge in using Artificial Intelligence (AI) for the prediction of heart attacks, emphasising the real-world applicability of the models, and effective resource management.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hamill, David UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence 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:	01 Sep 2025 11:52
Last Modified:	01 Sep 2025 11:52
URI:	https://norma.ncirl.ie/id/eprint/8665

Actions (login required)

View Item