Advanced

Selection of an Optimal Feature Set to Predict Heart Transplantation Outcomes

Medved, Dennis LU ; Nugues, Pierre LU and Nilsson, Johan LU (2016) In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 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 International... (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
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
pages
3290 - 3293
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
external identifiers
  • scopus:85009067874
ISBN
978-1-4577-0220-4
DOI
10.1109/EMBC.2016.7591431
language
English
LU publication?
yes
id
a80e0e01-f16a-4795-9fc0-76d7d1ad443b
date added to LUP
2016-10-27 16:18:30
date last changed
2017-11-05 05:08:38
@inproceedings{a80e0e01-f16a-4795-9fc0-76d7d1ad443b,
  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 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.},
  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)},
  isbn         = {978-1-4577-0220-4},
  language     = {eng},
  month        = {10},
  pages        = {3290--3293},
  publisher    = {IEEE--Institute of Electrical and Electronics Engineers Inc.},
  title        = {Selection of an Optimal Feature Set to Predict Heart Transplantation Outcomes},
  url          = {http://dx.doi.org/10.1109/EMBC.2016.7591431},
  year         = {2016},
}