Affordable Access

Access to the full text

OASIS +: leveraging machine learning to improve the prognostic accuracy of OASIS severity score for predicting in-hospital mortality

Authors
  • EL-Manzalawy, Yasser1
  • Abbas, Mostafa1
  • Hoaglund, Ian2
  • Cerna, Alvaro Ulloa1
  • Morland, Thomas B.1
  • Haggerty, Christopher M.1
  • Hall, Eric S.1
  • Fornwalt, Brandon K.1, 1
  • 1 Geisinger, Danville, PA, 17822, USA , Danville (United States)
  • 2 Pennsylvania State University, University Park, PA, 16802, USA , University Park (United States)
Type
Published Article
Journal
BMC Medical Informatics and Decision Making
Publisher
Springer (Biomed Central Ltd.)
Publication Date
May 13, 2021
Volume
21
Issue
1
Identifiers
DOI: 10.1186/s12911-021-01517-7
Source
Springer Nature
Keywords
License
Green

Abstract

BackgroundSeverity scores assess the acuity of critical illness by penalizing for the deviation of physiologic measurements from normal and aggregating these penalties (also called “weights” or “subscores”) into a final score (or probability) for quantifying the severity of critical illness (or the likelihood of in-hospital mortality). Although these simple additive models are human readable and interpretable, their predictive performance needs to be further improved.MethodsWe present OASIS +, a variant of the Oxford Acute Severity of Illness Score (OASIS) in which an ensemble of 200 decision trees is used to predict in-hospital mortality based on the 10 same clinical variables in OASIS.ResultsUsing a test set of 9566 admissions extracted from the MIMIC-III database, we show that OASIS + outperforms nine previously developed severity scoring methods (including OASIS) in predicting in-hospital mortality. Furthermore, our results show that the supervised learning algorithms considered in our experiments demonstrated higher predictive performance when trained using the observed clinical variables as opposed to OASIS subscores.ConclusionsOur results suggest that there is room for improving the prognostic accuracy of the OASIS severity scores by replacing the simple linear additive scoring function with more sophisticated non-linear machine learning models such as RF and XGB.

Report this publication

Statistics

Seen <100 times