NORMA eResearch @NCI Library

Forecasting IHD Mortality: A Comparative Analysis of European Drivers

Garcia Roman, Diana (2025) Forecasting IHD Mortality: A Comparative Analysis of European Drivers. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (898kB) | Preview
[thumbnail of Configuration Manual]
Preview
PDF (Configuration Manual)
Download (368kB) | Preview

Abstract

Background: Heart disease is the main cause of death in Europe, but the number of deaths differs greatly between countries and age groups. This study investigates why these differences exist, focusing on the contrast between working-age adults (under 65) and older people (65 and over).

Methods: The research used public data from 31 European countries, covering the years 2011 to 2022. A statistical method called a Random Effects model was used to identify the key factors driving death rates, with advanced techniques applied to ensure the findings were reliable. Additionally, three forecasting models (ETS, SARIMAX, and the machine learning model XGBoost) were compared across five diverse countries to find the most accurate way to predict future trends.

Results: The analysis confirms that higher national income and education are linked to fewer heart disease deaths (p<0.001). In theory, this supports the social gradient of health and reveals a key synergy: the protective effect of income is amplified by education (p<0.001). In practice, the machine learning model (XGBoost) proved to be a powerful forecasting tool, reducing prediction errors by over 70% in some cases, offering a key benefit for public health planning.

Conclusion: The findings suggest that public policy should focus on improving both economic conditions and education together. This research provides clear, age-specific evidence for smarter health strategies across Europe. However, the precise impact of specific preventive health policies and the role of lifestyle factors like diet and smoking remain unresolved and require further investigation.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Khan, Sallar
UNSPECIFIED
Uncontrolled Keywords: Ischaemic Heart Disease (IHD); Panel Data Analysis; Social Determinants of Health; Forecasting; European Health Policy; Health Economics
Subjects: R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine
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 Jul 2026 10:33
Last Modified: 01 Jul 2026 10:33
URI: https://norma.ncirl.ie/id/eprint/9427

Actions (login required)

View Item View Item