You are not logged in.
Openly accessible

Multi-task transfer learning for in hospital-death prediction for ICU patients

Karmakar, Chandan, Saha, Budhaditya, Palaniswami, Marimuthu and Venkatesh, Svetha 2016, Multi-task transfer learning for in hospital-death prediction for ICU patients, in EMBC 2016: Proceedings of the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, Piscataway, N.J., pp. 3321-3324, doi: 10.1109/EMBC.2016.7591438.

Attached Files
Name Description MIMEType Size Downloads
karmakar-multitask-post-2016.pdf Accepted version application/pdf 371.50KB 29

Title Multi-task transfer learning for in hospital-death prediction for ICU patients
Author(s) Karmakar, ChandanORCID iD for Karmakar, Chandan orcid.org/0000-0003-1814-0856
Saha, BudhadityaORCID iD for Saha, Budhaditya orcid.org/0000-0001-8011-6801
Palaniswami, Marimuthu
Venkatesh, SvethaORCID iD for Venkatesh, Svetha orcid.org/0000-0001-8675-6631
Conference name Engineering in Medicine and Biology Society. Annual International Conference (38th : 2016 : Orlando, Florida)
Conference location Orlando, Florida
Conference dates 16-20 Aug. 2016
Title of proceedings EMBC 2016: Proceedings of the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Editor(s) [Unknown]
Publication date 2016
Conference series Annual International Conference of the Engineering in Medicine and Biology Society
Start page 3321
End page 3324
Total pages 4
Publisher IEEE
Place of publication Piscataway, N.J.
Summary Multi-Task Transfer Learning (MTTL) is an efficient approach for learning from inter-related tasks with small sample size and imbalanced class distribution. Since the intensive care unit (ICU) data set (publicly available in Physionet) has subjects from four different ICU types, we hypothesizethat there is an underlying relatedness amongst various ICU types. Therefore, this study aims to explore MTTL model for in-hospital mortality prediction of ICU patients. We used singletask learning (STL) approach on the augmented data as well as individual ICU data and compared the performance with the proposed MTTL model. As a performance measurement metrics, we used sensitivity (Sens), positive predictivity (+Pred), and Score. MTTL with class balancing showed the best performance with score of 0.78, 0.73, o.52 and 0.63 for ICU type 1(Coronary care unit), 2 (Cardiac surgery unit), 3 (Medical ICU) and 4 (Surgical ICU) respectively. In contrast the maximum score obtained using STL approach was 0.40 for ICU type 1 & 2. These results indicates that the performance of in-hospital mortality can be improved using ICU type information and by balancing the ’non-survivor’ class. The findings of the study may be useful for quantifying the quality of ICU care, managing ICU resources and selecting appropriate interventions.
Language eng
DOI 10.1109/EMBC.2016.7591438
Field of Research 080109 Pattern Recognition and Data Mining
Socio Economic Objective 920203 Diagnostic Methods
HERDC Research category E1 Full written paper - refereed
ERA Research output type E Conference publication
Copyright notice ©2016, IEEE
Free to Read? Yes
Persistent URL http://hdl.handle.net/10536/DRO/DU:30083419

Document type: Conference Paper
Collections: Centre for Pattern Recognition and Data Analytics
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: 112 Abstract Views, 34 File Downloads  -  Detailed Statistics
Created: Tue, 18 Oct 2016, 08:22:41 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.