Enhancing Cardiovascular Health Prediction Through Machine Learning and Deep Learning

Kutcharlapati, Haritha (2024) Enhancing Cardiovascular Health Prediction Through Machine Learning and Deep Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (899kB) | Preview
Preview	PDF (Configuration Manual) Download (660kB) | Preview

Abstract

Cardiovascular disease continues to be a major cause of death globally calling for increased application of efficient predictive models to enable early detection of the disease. In this research, predictors were employed from a structured population dataset of demographic and physiological characteristics and some lifestyle parameters and diseases as independent variables i.e., age, sex, blood pressure, cholesterol, glucose, etc. to differentiate between healthy patients and those having cardiovascular disease. A range of models used like Logistic Regression, Random Forest, SVC, Decision Tree, Deep Neural network, Recurrent Neural network, and Long Short-Term Memory. Feature scaling, encoding, and other data preprocessing steps were done to improve model accuracy of prediction. Logistic Regression exercised the highest performance among all the traditional models with a test accuracy of 72.41%, precision of 72.65%, recall of 72.26% and the F1-score was 70.08 %. This study has also used other deep learning architectures such as DNN, RNN, and LSTM to show the capacity of models to learn complicated unstructured data patterns where LSTM and DNN give closer outcomes based on the alternate use of sequential and nonlinear features. It was found that when using specific options of linear models, strengths as well as weaknesses including class imbalance, and bias in the datasets were observed. This work aims to show the significance of the concept of applying artificial intelligence in health care, especially by incorporating enhanced predictive models in the identification of cardiovascular diseases.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Rustam, Furqan UNSPECIFIED
Uncontrolled Keywords:	Cardiovascular disease prediction; machine learning; deep learning; Logistic Regression; Random Forest; Support Vector Classifier
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:	03 Sep 2025 11:02
Last Modified:	03 Sep 2025 11:02
URI:	https://norma.ncirl.ie/id/eprint/8732

Actions (login required)

View Item