State based hidden markov models for temporal pattern discovery in critical care

Inibhunu, C; Am, CMG

State based hidden markov models for temporal pattern discovery in critical care

Inibhunu, C Am, CMG

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2018 IEEE Life Sciences Conference, LSC 2018, 2018, 00, pp. 77-80
Issue Date:: 2018-12-10

Recently Added

	Filename	Description	Size
	Binder1.pdf	Accepted Manuscript	937.72 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is new to OPUS and is not currently available.

Full metadata record

Field	Value	Language
dc.contributor.author	Inibhunu, C
dc.contributor.author	Am, CMG
dc.date	2018-10-28
dc.date.accessioned	2021-02-05T01:41:31Z
dc.date.available	2021-02-05T01:41:31Z
dc.date.issued	2018-12-10
dc.identifier.citation	2018 IEEE Life Sciences Conference, LSC 2018, 2018, 00, pp. 77-80
dc.identifier.isbn	9781538667095
dc.identifier.uri	http://hdl.handle.net/10453/145859
dc.description.abstract	© 2018 IEEE. We are studying the challenge of finding a good set of features that represent well the temporal aspects in time series data. We argue that discovery of such features could be crucial to understanding hidden relationships in data. In particular, in critical care where time oriented data is generated every second on patients physiological features, discovery of any hidden relationships could aid in discovery of unknown and potentially life threatening conditions before they happen. Additionally, this discovery could help in better dissemination of healthcare services leading to better outcomes and experiences for patients. To facilitate this process, this research explores two research questions; (a) can discovery of temporal relationships in data help in learning hidden aspects in differing patient cohort and (b) with respect to elderly patients receiving telehealth services, can detection of abnormal patterns help in identifying patients at risk of adverse events before they happen. In this paper, we introduce a model for temporal pattern mining by; (1) applying principles from finite state machines augmented with hidden markov models and temporal abstraction for identifying temporal relations in data, (2) generating temporal patterns by augmenting similar relationships, (3) formulating a process for mining frequently occurring temporal patterns and (4) using the resulting mined patterns to build a temporal classification system. Such a classification system can be effective at characterizing normal and abnormal behaviors in patients data and flag when a patient is at risk of a potential adverse event.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	2018 IEEE Life Sciences Conference, LSC 2018
dc.relation.ispartof	IEEE Life Sciences Conference (LSC)
dc.relation.isbasedon	10.1109/LSC.2018.8572190
dc.rights	© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.	en_US
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.title	State based hidden markov models for temporal pattern discovery in critical care
dc.type	Conference Proceeding
utslib.citation.volume	00
utslib.location.activity	Montreal, CANADA
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	recently_added	*
dc.date.updated	2021-02-05T01:41:10Z
pubs.finish-date	2018-10-30
pubs.publication-status	Published
pubs.start-date	2018-10-28
pubs.volume	00

Abstract:

© 2018 IEEE. We are studying the challenge of finding a good set of features that represent well the temporal aspects in time series data. We argue that discovery of such features could be crucial to understanding hidden relationships in data. In particular, in critical care where time oriented data is generated every second on patients physiological features, discovery of any hidden relationships could aid in discovery of unknown and potentially life threatening conditions before they happen. Additionally, this discovery could help in better dissemination of healthcare services leading to better outcomes and experiences for patients. To facilitate this process, this research explores two research questions; (a) can discovery of temporal relationships in data help in learning hidden aspects in differing patient cohort and (b) with respect to elderly patients receiving telehealth services, can detection of abnormal patterns help in identifying patients at risk of adverse events before they happen. In this paper, we introduce a model for temporal pattern mining by; (1) applying principles from finite state machines augmented with hidden markov models and temporal abstraction for identifying temporal relations in data, (2) generating temporal patterns by augmenting similar relationships, (3) formulating a process for mining frequently occurring temporal patterns and (4) using the resulting mined patterns to build a temporal classification system. Such a classification system can be effective at characterizing normal and abnormal behaviors in patients data and flag when a patient is at risk of a potential adverse event.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/145859