Display options
Share it on

JAMIA Open. 2021 Aug 02;4(3):ooab062. doi: 10.1093/jamiaopen/ooab062. eCollection 2021 Jul.

Comparison of early warning scores for sepsis early identification and prediction in the general ward setting.

JAMIA open

Sean C Yu, Nirmala Shivakumar, Kevin Betthauser, Aditi Gupta, Albert M Lai, Marin H Kollef, Philip R O Payne, Andrew P Michelson

Affiliations

  1. Institute for Informatics, Department of Medicine, Washington University School of Medicine in St. Louis, St. Louis, Missouri, USA.
  2. Department of Biomedical Engineering, Washington University School in St. Louis, St. Louis, Missouri, USA.
  3. Department of Medicine, Washington University School of Medicine in St. Louis, St. Louis, Missouri, USA.
  4. Department of Pharmacy, Barnes-Jewish Hospital, St. Louis, Missouri, USA.
  5. Division of Pulmonary and Critical Care, Department of Medicine, Washington University School of Medicine in St. Louis, St. Louis, MO, USA.

PMID: 34820600 PMCID: PMC8607822 DOI: 10.1093/jamiaopen/ooab062

Abstract

The objective of this study was to directly compare the ability of commonly used early warning scores (EWS) for early identification and prediction of sepsis in the general ward setting. For general ward patients at a large, academic medical center between early-2012 and mid-2018, common EWS and patient acuity scoring systems were calculated from electronic health records (EHR) data for patients that both met and did not meet Sepsis-3 criteria. For identification of sepsis at index time, National Early Warning Score 2 (NEWS 2) had the highest performance (area under the receiver operating characteristic curve: 0.803 [95% confidence interval [CI]: 0.795-0.811], area under the precision recall curves: 0.130 [95% CI: 0.121-0.140]) followed NEWS, Modified Early Warning Score, and quick Sequential Organ Failure Assessment (qSOFA). Using validated thresholds, NEWS 2 also had the highest recall (0.758 [95% CI: 0.736-0.778]) but qSOFA had the highest specificity (0.950 [95% CI: 0.948-0.952]), positive predictive value (0.184 [95% CI: 0.169-0.198]), and F1 score (0.236 [95% CI: 0.220-0.253]). While NEWS 2 outperformed all other compared EWS and patient acuity scores, due to the low prevalence of sepsis, all scoring systems were prone to false positives (low positive predictive value without drastic sacrifices in sensitivity), thus leaving room for more computationally advanced approaches.

© The Author(s) 2021. Published by Oxford University Press on behalf of the American Medical Informatics Association.

Keywords: early warning score; predictive analytics; sepsis

References

  1. JAMA. 2016 Feb 23;315(8):801-10 - PubMed
  2. Ann R Coll Surg Engl. 2006 Oct;88(6):571-5 - PubMed
  3. Crit Care Med. 1985 Oct;13(10):818-29 - PubMed
  4. JAMA Netw Open. 2020 May 1;3(5):e205191 - PubMed
  5. Chest. 1992 Jun;101(6):1644-55 - PubMed
  6. Clin Infect Dis. 2021 Feb 16;72(4):541-552 - PubMed
  7. Emerg Med J. 2016 Jan;33(1):37-41 - PubMed
  8. JAMA. 2016 Feb 23;315(8):762-74 - PubMed
  9. Arch Surg. 2001 Jan;136(1):55-9 - PubMed
  10. QJM. 2001 Oct;94(10):521-6 - PubMed
  11. Crit Care Med. 2021 Apr 1;49(4):e433-e443 - PubMed
  12. N Engl J Med. 2017 Jun 8;376(23):2235-2244 - PubMed
  13. Crit Care Med. 2011 Mar;39(3):469-73 - PubMed
  14. Am J Respir Crit Care Med. 2015 Oct 15;192(8):958-64 - PubMed
  15. JAMA. 2014 Jul 2;312(1):90-2 - PubMed
  16. Crit Care Med. 2014 Apr;42(4):841-8 - PubMed
  17. PLoS One. 2019 Jan 25;14(1):e0211133 - PubMed
  18. Heart Lung. 2019 May - Jun;48(3):240-244 - PubMed

Publication Types