Towards an Evolutionary Open Pediatric Intensive Care Dataset in the ELISE Project.
Data Science
Dataset
Intensive Care Units
Pediatric
Journal
Studies in health technology and informatics
ISSN: 1879-8365
Titre abrégé: Stud Health Technol Inform
Pays: Netherlands
ID NLM: 9214582
Informations de publication
Date de publication:
29 Jun 2022
29 Jun 2022
Historique:
entrez:
1
7
2022
pubmed:
2
7
2022
medline:
6
7
2022
Statut:
ppublish
Résumé
To embrace the need for freely accessible training data sets originating from the real world, in the ELISE project, we integrate source data from a pediatric intensive care unit and provide it to researchers. We present our vision, initial results and steps on a trail towards an evolutionary open pediatric intensive care data set. Our evolution plan for the data set comprises three steps. The final data set will include raw clinical data and labels on critical outcomes such as organ dysfunction and sepsis, generated automatically by computerized and well-evaluated methods. First step resulted in an initial version data set available in a central repository. Our approach has great potential to provide a comprehensive open intensive care data set labeled for critical pediatric outcomes and, thus, contributing to overcome the current lack of real-world pediatric intensive care data usable for training data-driven algorithms.
Sections du résumé
BACKGROUND
BACKGROUND
To embrace the need for freely accessible training data sets originating from the real world, in the ELISE project, we integrate source data from a pediatric intensive care unit and provide it to researchers.
OBJECTIVE
OBJECTIVE
We present our vision, initial results and steps on a trail towards an evolutionary open pediatric intensive care data set.
METHODS
METHODS
Our evolution plan for the data set comprises three steps. The final data set will include raw clinical data and labels on critical outcomes such as organ dysfunction and sepsis, generated automatically by computerized and well-evaluated methods.
RESULTS
RESULTS
First step resulted in an initial version data set available in a central repository.
CONCLUSIONS
CONCLUSIONS
Our approach has great potential to provide a comprehensive open intensive care data set labeled for critical pediatric outcomes and, thus, contributing to overcome the current lack of real-world pediatric intensive care data usable for training data-driven algorithms.
Identifiants
pubmed: 35773816
pii: SHTI220670
doi: 10.3233/SHTI220670
doi:
Types de publication
Journal Article
Langues
eng
Pagination
100-103Investigateurs
Louisa Bode
(L)
Marcel Mast
(M)
Antje Wulff
(A)
Michael Marschollek
(M)
Sven Schamer
(S)
Henning Rathert
(H)
Thomas Jack
(T)
Philipp Beerbaum
(P)
Nicole Rübsamen
(N)
Julia Böhnke
(J)
André Karch
(A)
Pronaya Prosun Das
(PP)
Lena Wiese
(L)
Christian Groszewski-Anders
(C)
Andreas Haller
(A)
Torsten Frank
(T)