Developing well-calibrated illness severity scores for decision support in the critically ill

Cosgriff, Christopher V. and Celi, Leo Anthony and Ko, Stephanie and Sundaresan, Tejas and Armengol de la Hoz, Miguel Ángel and Kaufman, Aaron Russell and Stone, David J. and Badawi, Omar and Deliberato, Rodrigo Octavio (2019). Developing well-calibrated illness severity scores for decision support in the critically ill. "npj Digital Medicine", v. 2 (n. 76); pp. 1-8. ISSN 2398-6352. https://doi.org/10.1038/s41746-019-0153-6.

Description

Title: Developing well-calibrated illness severity scores for decision support in the critically ill
Author/s:
  • Cosgriff, Christopher V.
  • Celi, Leo Anthony
  • Ko, Stephanie
  • Sundaresan, Tejas
  • Armengol de la Hoz, Miguel Ángel
  • Kaufman, Aaron Russell
  • Stone, David J.
  • Badawi, Omar
  • Deliberato, Rodrigo Octavio
Item Type: Article
Título de Revista/Publicación: npj Digital Medicine
Date: 15 August 2019
ISSN: 2398-6352
Volume: 2
Subjects:
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Tecnología Fotónica y Bioingeniería
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview

Abstract

Illness severity scores are regularly employed for quality improvement and benchmarking in the intensive care unit, but poor generalization performance, particularly with respect to probability calibration, has limited their use for decision support. These models tend to perform worse in patients at a high risk for mortality. We hypothesized that a sequential modeling approach wherein an initial regression model assigns risk and all patients deemed high risk then have their risk quantified by a second, highrisk- specific, regression model would result in a model with superior calibration across the risk spectrum. We compared this approach to a logistic regression model and a sophisticated machine learning approach, the gradient boosting machine. The sequential approach did not have an effect on the receiver operating characteristic curve or the precision-recall curve but resulted in improved reliability curves. The gradient boosting machine achieved a small improvement in discrimination performance and was similarly calibrated to the sequential models.

More information

Item ID: 63202
DC Identifier: http://oa.upm.es/63202/
OAI Identifier: oai:oa.upm.es:63202
DOI: 10.1038/s41746-019-0153-6
Official URL: https://www.nature.com/articles/s41746-019-0153-6
Deposited by: Memoria Investigacion
Deposited on: 26 Sep 2020 08:30
Last Modified: 26 Sep 2020 08:30
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM