The Significance of External Factors on an Individual's Health Determination

Burke, Richard (2020) The Significance of External Factors on an Individual's Health Determination. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Determining health outcomes in the general population is critical to the appropriate development of public policy. Identifying the key drivers of public health outcomes is crucial to effective understanding and implementation of these policies. This research explores the key socioeconomic and locality-based explanatory factors that influence the self-determined health outcomes of the residents in an area. Furthermore, it demonstrates the necessity of quality inputs and technical expertise into the development of public policy. Data was captured from the Ireland Central Statistics Office, Ireland's open data portal, and the Ireland deprivation index. The data was processed to generate health classifications by Small Area in Fingal, County Dublin. Five classification models (Gradient Boosting, Random Forest, Naïve Bayes, Multinomial Regression, and AutoML's automatic model) were trained on sample data to predict the health outcome for the remaining holdout test set. The results demonstrate the capacity to accurately predict the aggregated health determination of a small area from publicly available data. Multinomial Regression was the best performing model with an accuracy scored of 49% compared to a no-information rate of 20%. Furthermore, it uncovers the interrelationship between the availability of local facilities and self-health determination, with the areas identified as having poorer health outcomes having greater access to the facility factors incorporated into this research. On this basis, it is recommended that policymakers ensure data capture and model development is a key part of their policy decision process. Further research is required to identify additional factors that could strengthen the effectiveness of these models and to complete comprehensive model optimisation.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software R Medicine > Healthcare Industry
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	18 Jan 2021 13:38
Last Modified:	18 Jan 2021 13:38
URI:	https://norma.ncirl.ie/id/eprint/4364

Actions (login required)

View Item