Openly accessible

Machine learning in healthcare : an investigation into model stability

Gopakumar, Shivapratap 2017, Machine learning in healthcare : an investigation into model stability, PhD thesis, School of Information Technology, Deakin University.

Attached Files
Name Description MIMEType Size Downloads
gopakumar-machinelearning-2017.pdf Connect to thesis application/pdf 5.83MB 221

Title Machine learning in healthcare : an investigation into model stability
Author Gopakumar, Shivapratap
Institution Deakin University
School School of Information Technology
Faculty Faculty of Science, Engineering and Built Environment
Degree type Research doctorate
Degree name PhD
Thesis advisor Tran, TruyenORCID iD for Tran, Truyen orcid.org/0000-0001-6531-8907
Phung, DinhORCID iD for Phung, Dinh orcid.org/0000-0002-9977-8247
Venkatesh, SvethaORCID iD for Venkatesh, Svetha orcid.org/0000-0001-8675-6631
Date submitted 2017-02
Keyword(s) healthcare data
electronic medical record (EMR)
model stabilization schemes
forecasting patient outflow from wards
Summary Current machine learning algorithms, when directly applied to medical data, often fail to provide a good understanding of prognosis. This study provides three pathways to make predictive models stable and usable for healthcare. When tested on heart failure and diabetes patients from a local hospital, this study demonstrated 20% improvement over existing methods.
Language eng
Field of Research 170203 Knowledge Representation and Machine Learning
010401 Applied Statistics
Socio Economic Objective 920103 Cardiovascular System and Diseases
Description of original xxi, 194 pages : illustrations, tables, graphs, some coloured
Copyright notice ┬ęThe Author. All Rights Reserved.
Free to Read? Yes
Persistent URL http://hdl.handle.net/10536/DRO/DU:30103475

Document type: Thesis
Collections: Higher degree theses (Open Access)
Open Access Collection
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 105 Abstract Views, 224 File Downloads  -  Detailed Statistics
Created: Wed, 18 Oct 2017, 10:55:48 EST by Asif, Yasmin

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.