Abstract
dc:description.abstractIn the United States, cardiovascular disease is the leading cause of death for both men and women. The factors that contribute to heart disease are well known but it is still an ever-evolving field of research. The possible benefits to being able to determine an individual’s Health Risk could provide the early insights needed to combat cardiovascular disease. However, two major problems within this area are the public availability of a dataset and the label imbalances for the dataset. In this thesis, we present a framework for exploring health risk using a combination of the NHANES dataset and open-source machine learning tools. We apply this framework to both cardiovascular disease risk detection and hypertension risk detection. To address the challenge of data imbalance, we also explore different sampling strategies built on a novel modification to KMeans Under-Sampling. Results are included to demonstrate the performance of the proposed methods.
Degree
thesis:*- Name thesis:degree_name
- MS
- Level thesis:degree_level
- Thesis
- Discipline thesis:degree_discipline
- Lane Department of Computer Science and Electrical Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Cole, Levi Butcher
- Contributors dc:contributor
-
- Donald Adjeroh
- James Bardes
- Gianfranco Doretto
Subjects
dc:subject × 5Identifiers
dc:identifier.*- Identifier
- https://researchrepository.wvu.edu/etd/11456