Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Selection of an optimal feature set to predict heart transplantation outcomes

Medved, Dennis LU orcid ; Nugues, Pierre LU orcid and Nilsson, Johan LU orcid (2016) 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2016-October. p.3290-3293
Abstract

Heart transplantation (HT) is a life saving procedure, but a limited donor supply forces the surgeons to prioritize the recipients. The understanding of factors that predict mortality could help the doctors with this task. The objective of this study is to find locally optimal feature sets to predict survival of HT patients for different time periods. To this end, we applied logistic regression together with a greedy forward and backward search. As data source, we used the United Network for Organ Sharing (UNOS) registry, where we extracted adult patients (>17 years) from January 1997 to December 2008. As methods to predict survival, we used the Index for Mortality Prediction After Cardiac Transplantation (IMPACT) and the... (More)

Heart transplantation (HT) is a life saving procedure, but a limited donor supply forces the surgeons to prioritize the recipients. The understanding of factors that predict mortality could help the doctors with this task. The objective of this study is to find locally optimal feature sets to predict survival of HT patients for different time periods. To this end, we applied logistic regression together with a greedy forward and backward search. As data source, we used the United Network for Organ Sharing (UNOS) registry, where we extracted adult patients (>17 years) from January 1997 to December 2008. As methods to predict survival, we used the Index for Mortality Prediction After Cardiac Transplantation (IMPACT) and the International Heart Transplant Survival Algorithm (IHTSA). We used the LIBLINEAR library together with the Apache Spark cluster computing framework to carry out the computation and we found feature sets for 1, 5, and 10 year survival for which we obtained area under the ROC curves (AUROC) of 68%, 68%, and 76%, respectively.

(Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
series title
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
volume
2016-October
article number
7591431
pages
4 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
conference location
Orlando, United States
conference dates
2016-08-16 - 2016-08-20
external identifiers
  • scopus:85009067874
  • scopus:85009067874
  • pmid:28269008
ISSN
1557-170X
ISBN
978-1-4577-0220-4
DOI
10.1109/EMBC.2016.7591431
language
English
LU publication?
yes
additional info
Publisher Copyright: © 2016 IEEE.
id
a80e0e01-f16a-4795-9fc0-76d7d1ad443b
date added to LUP
2016-10-27 16:18:30
date last changed
2024-06-14 16:24:15
@inproceedings{a80e0e01-f16a-4795-9fc0-76d7d1ad443b,
  abstract     = {{<p>Heart transplantation (HT) is a life saving procedure, but a limited donor supply forces the surgeons to prioritize the recipients. The understanding of factors that predict mortality could help the doctors with this task. The objective of this study is to find locally optimal feature sets to predict survival of HT patients for different time periods. To this end, we applied logistic regression together with a greedy forward and backward search. As data source, we used the United Network for Organ Sharing (UNOS) registry, where we extracted adult patients (&gt;17 years) from January 1997 to December 2008. As methods to predict survival, we used the Index for Mortality Prediction After Cardiac Transplantation (IMPACT) and the International Heart Transplant Survival Algorithm (IHTSA). We used the LIBLINEAR library together with the Apache Spark cluster computing framework to carry out the computation and we found feature sets for 1, 5, and 10 year survival for which we obtained area under the ROC curves (AUROC) of 68%, 68%, and 76%, respectively.</p>}},
  author       = {{Medved, Dennis and Nugues, Pierre and Nilsson, Johan}},
  booktitle    = {{2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016}},
  isbn         = {{978-1-4577-0220-4}},
  issn         = {{1557-170X}},
  language     = {{eng}},
  month        = {{10}},
  pages        = {{3290--3293}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS}},
  title        = {{Selection of an optimal feature set to predict heart transplantation outcomes}},
  url          = {{http://dx.doi.org/10.1109/EMBC.2016.7591431}},
  doi          = {{10.1109/EMBC.2016.7591431}},
  volume       = {{2016-October}},
  year         = {{2016}},
}