TRAP@NCI

Machine Learning algorithms in Health Questionnaires: Multiple Correspondence Analysis and Classification model

Blake, Louise (2017) Machine Learning algorithms in Health Questionnaires: Multiple Correspondence Analysis and Classification model. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (1MB) | Preview

Abstract

This paper describes the development of a unique multiple disease classification tool to expose and pre-screen for chronic diseases and can be applied to individual surveys. Through data mining of NHANES questionnaires, a transparent and straightforward model is developed which be could apply to future survey data. We show machine learning and dimensional reduction can be beneficial to survey data to determine the risk of multiple chronic diseases in individuals surveyed. The results are used to create a prototype tool that can predict the presence of multiple chronic diseases through fundamental questions. The number of questions are reduced to 5 questions to achieve an acceptable result. The researchers know of no tool currently available that delivers this kind of functionality.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

R Medicine > Healthcare Industry
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 27 Aug 2018 13:20
Last Modified: 28 Aug 2018 10:00
URI: http://trap.ncirl.ie/id/eprint/3073

Actions (login required)

View Item View Item