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, Chandan orcid.org/0000-0003-1814-0856 Saha, Budhaditya orcid.org/0000-0001-8011-6801 Palaniswami, Marimuthu 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 Related Links Link Description Connect to published version Go to link with your DU access privileges   Connect to Elements publication management system Go to link with your DU access privileges     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 Thu, 12 May 2016, 14:07:39 EST Thu, 12 May 2016, 14:34:40 EST Thu, 12 May 2016, 14:43:24 EST Tue, 18 Oct 2016, 08:03:01 EST Tue, 18 Oct 2016, 08:22:41 EST Wed, 19 Oct 2016, 05:10:50 EST Mon, 24 Oct 2016, 09:11:56 EST Mon, 24 Oct 2016, 09:19:49 EST Mon, 24 Oct 2016, 09:55:45 EST Sat, 04 Feb 2017, 01:31:12 EST Sat, 17 Jun 2017, 02:30:32 EST Filtered Full Citation counts:   Cited 0 times in TR Web of Science Cited 0 times in Scopus 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.