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

Health care Medical research Prognosis

Journal

NPJ digital medicine
ISSN: 2398-6352
Titre abrégé: NPJ Digit Med
Pays: England
ID NLM: 101731738

Informations de publication

Date de publication:
2019
Historique:
received: 11 12 2018
accepted: 19 07 2019
entrez: 21 8 2019
pubmed: 21 8 2019
medline: 21 8 2019
Statut: epublish

Résumé

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

Identifiants

pubmed: 31428687
doi: 10.1038/s41746-019-0153-6
pii: 153
pmc: PMC6695410
doi:

Types de publication

Journal Article

Langues

eng

Pagination

76

Déclaration de conflit d'intérêts

Competing interestsO.B. is employed by Philips Healthcare. The other authors declare no competing interests.

Références

JAMA. 2018 Sep 18;320(11):1101-1102
pubmed: 30178065
Crit Care Med. 2018 Jul;46(7):1070-1077
pubmed: 29596073
Crit Care Med. 2014 Mar;42(3):544-53
pubmed: 24158174
J Clin Epidemiol. 2019 Jun;110:12-22
pubmed: 30763612
Sci Data. 2018 Sep 11;5:180178
pubmed: 30204154
Ann Am Thorac Soc. 2018 Jul;15(7):846-853
pubmed: 29787309
Med Decis Making. 2015 Feb;35(2):162-9
pubmed: 25155798
AMIA Annu Symp Proc. 2018 Apr 16;2017:625-634
pubmed: 29854127
BMJ. 1993 Oct 16;307(6910):977-81
pubmed: 8241909
Chest. 2012 Feb;141(2):518-527
pubmed: 22315120
Nat Biotechnol. 2018 Oct;36(9):829-838
pubmed: 30188539
AMIA Annu Symp Proc. 2018 Apr 16;2017:994-1003
pubmed: 29854167
Crit Care Med. 2006 May;34(5):1297-310
pubmed: 16540951
JAMA. 2018 Apr 3;319(13):1317-1318
pubmed: 29532063
Anaesthesia. 2002 Jan;57(1):21-6
pubmed: 11843737
Crit Care Med. 2006 Oct;34(10):2517-29
pubmed: 16932234
JAMA. 2017 Oct 10;318(14):1377-1384
pubmed: 29049590
JAMA. 2018 Sep 18;320(11):1099-1100
pubmed: 30178068
Chest. 1999 Mar;115(3):802-10
pubmed: 10084495
JAMA. 1993 Nov 24;270(20):2478-86
pubmed: 8230626
Crit Care Med. 2015 Feb;43(2):261-9
pubmed: 25365725
Intensive Care Med. 2005 Oct;31(10):1345-55
pubmed: 16132892
Ann Intern Med. 2015 Jan 6;162(1):55-63
pubmed: 25560714
NPJ Digit Med. 2019 Aug 15;2:76
pubmed: 31428687
Crit Care Med. 1994 Sep;22(9):1392-401
pubmed: 8062560
Intensive Care Med. 1996 Jul;22(7):707-10
pubmed: 8844239
Chest. 2012 Jan;141(1):245-252
pubmed: 22215834

Auteurs

Christopher V Cosgriff (CV)

1MIT Critical Data, Laboratory for Computational Physiology, Harvard-MIT Health Sciences & Technology, Massachusetts Institute of Technology, Cambridge, MA 02139 USA.
2Department of Medicine, Hospital of the University of Pennsylvania, Philadelphia, PA 19104 USA.

Leo Anthony Celi (LA)

1MIT Critical Data, Laboratory for Computational Physiology, Harvard-MIT Health Sciences & Technology, Massachusetts Institute of Technology, Cambridge, MA 02139 USA.
3Division of Pulmonary Critical Care and Sleep Medicine, Beth Israel Deaconess Medical Center, Boston, MA 02215 USA.

Stephanie Ko (S)

4Department of Medicine, National University Health Systems, Singapore, Singapore.

Tejas Sundaresan (T)

5Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139 USA.

Miguel Ángel Armengol de la Hoz (MÁ)

1MIT Critical Data, Laboratory for Computational Physiology, Harvard-MIT Health Sciences & Technology, Massachusetts Institute of Technology, Cambridge, MA 02139 USA.
6Division of Clinical Informatics, Department of Medicine, Beth Israel Deaconess Medical Center, Boston, MA 02215 USA.
7Harvard Medical School, Boston, MA 02115 USA.
8Biomedical Engineering and Telemedicine Group, Biomedical Technology Centre CTB, ETSI Telecomunicación, Universidad Politécnica de Madrid, Madrid, 28040 Spain.

Aaron Russell Kaufman (AR)

9Department of Government, Harvard University, Cambridge, MA 02138 USA.

David J Stone (DJ)

1MIT Critical Data, Laboratory for Computational Physiology, Harvard-MIT Health Sciences & Technology, Massachusetts Institute of Technology, Cambridge, MA 02139 USA.
10Departments of Anesthesiology and Neurosurgery, University of Virginia School of Medicine, Charlottesville, VA 22908 USA.

Omar Badawi (O)

Department of eICU Research and Development, Philips Healthcare, Baltimore, MD 21202 USA.

Rodrigo Octavio Deliberato (RO)

1MIT Critical Data, Laboratory for Computational Physiology, Harvard-MIT Health Sciences & Technology, Massachusetts Institute of Technology, Cambridge, MA 02139 USA.
12Big Data Department, Hospital Israelita Albert Einstein, São Paulo, Brazil.
13Critical Care Department, Hospital Israelita Albert Einstein, São Paulo, Brazil.

Classifications MeSH