Prediciton of emergency events: a multi-task multi-label learning approach

doi:10.1007/978-3-319-18038-0_18

Submit research Contact DRO

DRO

Prediciton of emergency events: a multi-task multi-label learning approach

Saha, Budhaditya, Gupta, Sunil K. and Venkatesh, Svetha 2015, Prediciton of emergency events: a multi-task multi-label learning approach. In Cao, Tru, Lim, Ee-Peng, Zhou, Zhi-Hua, Ho, Tu-Bao, Cheung, David and Motoda, Hiroshi (ed), Advances in knowledge discovery and data mining 19th Pacific-Asia Conference, PAKDD 2015, Ho Chi Minh City, Vietnam, May 19-22, 2015, Proceedings, Part I, Springer, Berlin, Germany, pp.226-238, doi: 10.1007/978-3-319-18038-0_18.

Attached Files
Name			Description	MIMEType		Size	Downloads

Title	Prediciton of emergency events: a multi-task multi-label learning approach
Author(s)	Saha, Budhaditya orcid.org/0000-0001-8011-6801 Gupta, Sunil K. orcid.org/0000-0002-3308-1930 Venkatesh, Svetha orcid.org/0000-0001-8675-6631
Title of book	Advances in knowledge discovery and data mining 19th Pacific-Asia Conference, PAKDD 2015, Ho Chi Minh City, Vietnam, May 19-22, 2015, Proceedings, Part I
Editor(s)	Cao, Tru Lim, Ee-Peng Zhou, Zhi-Hua Ho, Tu-Bao Cheung, David Motoda, Hiroshi
Publication date	2015
Series	Lecture notes in computer science; v.9077
Chapter number	18
Total chapters	58
Start page	226
End page	238
Total pages	13
Publisher	Springer
Place of Publication	Berlin, Germany
Keyword(s)	Science & Technology Technology Computer Science, Artificial Intelligence Computer Science, Information Systems Computer Science, Theory & Methods Computer Science
Summary	Prediction of patient outcomes is critical to plan resources in an hospital emergency department. We present a method to exploit longitudinal data from Electronic Medical Records (EMR), whilst exploiting multiple patient outcomes. We divide the EMR data into segments where each segment is a task, and all tasks are associated with multiple patient outcomes over a 3, 6 and 12 month period. We propose a model that learns a prediction function for each task-label pair, interacting through two subspaces: the first subspace is used to impose sharing across all tasks for a given label. The second subspace captures the task-specific variations and is shared across all the labels for a given task. The proposed model is formulated as an iterative optimization problems and solved using a scalable and efficient Block co-ordinate descent (BCD) method. We apply the proposed model on two hospital cohorts - Cancer and Acute Myocardial Infarction (AMI) patients collected over a two year period from a large hospital emergency department. We show that the predictive performance of our proposed models is significantly better than those of several state-of-the-art multi-task and multi-label learning methods.
ISBN	9783319180380
ISSN	0302-9743 1611-3349
Language	eng
DOI	10.1007/978-3-319-18038-0_18
Field of Research	080109 Pattern Recognition and Data Mining 08 Information And Computing Sciences
Socio Economic Objective	970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category	B1 Book chapter
ERA Research output type	B Book chapter
Copyright notice	©2015, IEEE
Persistent URL	http://hdl.handle.net/10536/DRO/DU:30077468

Document type:	Book Chapter
Collections:	Faculty of Science, Engineering and Built Environment Centre for Pattern Recognition and Data Analytics (PRADA)


Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Citation counts:	Cited 1 times in TR Web of Science Cited 1 times in Scopus Search Google Scholar
Access Statistics:	665 Abstract Views, 6 File Downloads - Detailed Statistics
Created:	Thu, 07 Apr 2016, 16:30:49 EST

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.