TRAP@NCI

Developing a Web Application with built in Predictive Models to perform real time predictions of Parkinson's disease

Ganesh, Achinthya (2018) Developing a Web Application with built in Predictive Models to perform real time predictions of Parkinson's disease. Masters thesis, Dublin, National College of Ireland.

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

Abstract

Parkinsons disease is one of the most common progressive neurodegenerative diseases known to be highly fatal and incurable. It is one of the diseases which directly affects the human nervous system in turn affecting all the motor and non-motor functions of a human. Considering the fact that there is still no means to treat or eradicate the disease completely, a temporary solution can be bought in a way by making early predictions of the disease possible. This research focuses on developing a predictive web application which will perform the predictions of the disease based on the diseases most common symptoms and deliver the results to the user. The machine learning models used in this research are K-NN, logistic regression, support vector machine and decision tree out of which the model with the highest performance will be chosen to develop the web application. The built predictive model is published as a web service in Azure ML Studio which generates the API key enabling the model to be extended and be able to run in the backend of a web application. The predictive models are evaluated on the test data and decision tree stands out as the best performing model with 98% accuracy and 96% sensitivity. Thus, this model will be embedded within the web application that will perform real time predictions of the disease. This is being developed to provide an effective means for the user to predict the disease as early as possible so that necessary treatment measures can be taken.

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: CAOIMHE NI MHAICIN
Date Deposited: 05 Nov 2018 11:27
Last Modified: 05 Nov 2018 11:27
URI: http://trap.ncirl.ie/id/eprint/3427

Actions (login required)

View Item View Item