Advancing Chronic Disease Analytics by Predicting Cardiovascular Disease Risk Based on Demographic and Health Factors in the US

Yeliyuru Ramu, Tej Patel (2024) Advancing Chronic Disease Analytics by Predicting Cardiovascular Disease Risk Based on Demographic and Health Factors in the US. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (707kB) | Preview
Preview	PDF (Configuration Manual) Download (517kB) | Preview

Abstract

Cardiovascular Diseases (CVD) still remains as one of the leading causes of death in the United States. The current predictive models often give different results about how age, gender, race, and location impact the risk of CVD. Studying and research on these factors can support our healthcare providers in targeting disease prevention on high-risk populations in the US and help reduce the risk of CVD in the society. In this research we start by analysing how demographic and other health related factors are dependent on CVD risk, focusing on the demographic diversity in the US. Our main goal is to develop different analytical machine learning models and compare them with different parameters that finds out significant risks across these demographic groups, which could improve the understanding of CVD risk distribution. We use a large healthcare dataset from a US government website named US Chronic Disease Indicators and apply different data mining, machine learning models such as Logistic regression, Gradient boosting, Random Forest, SVM, KNN and analysis techniques to see investigate these factors are related to CVD. We measured and analysed the model’s accuracy, sensitivity, and specificity. Logistic regression, Random Forest and Gradient boosting demonstrated commendable consistency with a score of 0.84 across all metrics, such as accuracy, precision, recall and F1 score showing a balance between model complexity and its performance. The findings of this study will give us a data driven basis for modifying CVD risk and which could increase the effectiveness of preventing healthcare programs in different groups across the United States.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Muntean, Cristina Hava UNSPECIFIED
Subjects:	E History America > E151 United States (General) Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > Diseases 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:	08 Sep 2025 09:25
Last Modified:	08 Sep 2025 09:25
URI:	https://norma.ncirl.ie/id/eprint/8840

Actions (login required)

View Item