File(s) under permanent embargo
Multi-task transfer learning for in hospital-death prediction of ICU patients
conference contribution
posted on 2016-08-18, 00:00 authored by Chandan KarmakarChandan Karmakar, Budhaditya Saha, M Palaniswami, Svetha VenkateshSvetha VenkateshMulti-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 hypothesize
that 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.
that 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.
History
Event
Engineering in Medicine and Biology Society. Annual International Conference (38th : 2016 : Orlando, Florida)Series
Annual International Conference of the IEEE Engineering in Medicine and Biology SocietyPagination
3321 - 3324Publisher
IEEELocation
Orlando, FloridaPlace of publication
Piscataway, N.J.Publisher DOI
Start date
2016-08-16End date
2016-08-20Language
engPublication classification
E Conference publication; E1 Full written paper - refereedCopyright notice
2016, IEEETitle of proceedings
EMBC 2016: Proceedings of the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology SocietyUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC