Advanced

Streamlining a Transplantation Survival Prediction Program with a RDF Triplestore

Medved, Dennis LU ; Nilsson, Johan LU and Nugues, Pierre LU (2013) 9th International Conference on Data Integration in the Life Sciences
Abstract
In this paper, we describe the conversion of a heart trans-

plantation dataset in the RDF format and its application in a survival

prediction program. The International Society for Heart & Lung Trans-

plantation (ISHLT) maintains a registry of heart transplantations that

it gathers from operations performed worldwide. The US United Net-

work for Organ Sharing (UNOS) and the Scandinavian Scandiatrans-

plant are contributors of this registry although they use different data

models. We designed a unified graph representation covering the three

data models and we converted the ISHLT tables into RDF triples. We

used the resulting triplestore as input to a... (More)
In this paper, we describe the conversion of a heart trans-

plantation dataset in the RDF format and its application in a survival

prediction program. The International Society for Heart & Lung Trans-

plantation (ISHLT) maintains a registry of heart transplantations that

it gathers from operations performed worldwide. The US United Net-

work for Organ Sharing (UNOS) and the Scandinavian Scandiatrans-

plant are contributors of this registry although they use different data

models. We designed a unified graph representation covering the three

data models and we converted the ISHLT tables into RDF triples. We

used the resulting triplestore as input to a survival prediction program

for transplanted patients [3, 2]. Recipient and donor properties are essen-

tial to predict the mortality or survival of the patients. In contrast with

the manual techniques we used to extract data from the tabulated files,

the RDF triplestore enables us to experiment quickly and automatically

with combinations of features that influence most the survival that we

will demonstrate at the conference. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to conference
publication status
published
subject
keywords
RDF triplestore, transplantation data set, feature sets
pages
4 pages
conference name
9th International Conference on Data Integration in the Life Sciences
language
English
LU publication?
yes
id
286311d6-77a7-4853-8cba-1f34006b3305 (old id 4173432)
date added to LUP
2014-01-03 13:12:35
date last changed
2016-04-16 12:02:38
@misc{286311d6-77a7-4853-8cba-1f34006b3305,
  abstract     = {In this paper, we describe the conversion of a heart trans-<br/><br>
plantation dataset in the RDF format and its application in a survival<br/><br>
prediction program. The International Society for Heart &amp; Lung Trans-<br/><br>
plantation (ISHLT) maintains a registry of heart transplantations that<br/><br>
it gathers from operations performed worldwide. The US United Net-<br/><br>
work for Organ Sharing (UNOS) and the Scandinavian Scandiatrans-<br/><br>
plant are contributors of this registry although they use different data<br/><br>
models. We designed a unified graph representation covering the three<br/><br>
data models and we converted the ISHLT tables into RDF triples. We<br/><br>
used the resulting triplestore as input to a survival prediction program<br/><br>
for transplanted patients [3, 2]. Recipient and donor properties are essen-<br/><br>
tial to predict the mortality or survival of the patients. In contrast with<br/><br>
the manual techniques we used to extract data from the tabulated files,<br/><br>
the RDF triplestore enables us to experiment quickly and automatically<br/><br>
with combinations of features that influence most the survival that we<br/><br>
will demonstrate at the conference.},
  author       = {Medved, Dennis and Nilsson, Johan and Nugues, Pierre},
  keyword      = {RDF triplestore,transplantation data set,feature sets},
  language     = {eng},
  pages        = {4},
  title        = {Streamlining a Transplantation Survival Prediction Program with a RDF Triplestore},
  year         = {2013},
}