A multibiomarker-based model for estimating the risk of septic acute kidney injury

Hector R. Wong, Natalie Z. Cvijanovich, Nick Anas, Geoffrey L. Allen, Neal J. Thomas, Michael T. Bigham, Scott L. Weiss, Julie Fitzgerald, Paul A. Checchia, Keith Meyer, Thomas P. Shanley, Michael Quasney, Mark Hall, Rainer Gedeit, Robert J. Freishtat, Jeffrey Nowak, Shekhar S. Raj, Shira Gertz, Emily Dawson, Kelli HowardKelli Harmon, Patrick Lahni, Erin Frank, Kimberly W. Hart, Christopher J. Lindsell

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Objective: The development of acute kidney injury in patients with sepsis is associated with worse outcomes. Identifying those at risk for septic acute kidney injury could help to inform clinical decision making. We derived and tested a multibiomarker-based model to estimate the risk of septic acute kidney injury in children with septic shock. Design: Candidate serum protein septic acute kidney injury biomarkers were identified from previous transcriptomic studies. Model derivation involved measuring these biomarkers in serum samples from 241 subjects with septic shock obtained during the first 24 hours of admission and then using a Classification and Regression Tree approach to estimate the probability of septic acute kidney injury 3 days after the onset of septic shock, defined as at least two-fold increase from baseline serum creatinine. The model was then tested in a separate cohort of 200 subjects. Setting: Multiple PICUs in the United States. Interventions: None other than standard care. Measurements and Main Results: The decision tree included a firstlevel decision node based on day 1 septic acute kidney injury status and five subsequent biomarker-based decision nodes. The area under the curve for the tree was 0.95 (CI95, 0.91-0.99), with a sensitivity of 93% and a specificity of 88%. The tree was superior to day 1 septic acute kidney injury status alone for estimating day 3 septic acute kidney injury risk. In the test cohort, the tree had an area under the curve of 0.83 (0.72-0.95), with a sensitivity of 85% and a specificity of 77% and was also superior to day 1 septic acute kidney injury status alone for estimating day 3 septic acute kidney injury risk. Conclusions: We have derived and tested a model to estimate the risk of septic acute kidney injury on day 3 of septic shock using a novel panel of biomarkers. The model had very good performance in a test cohort and has test characteristics supporting clinical utility and further prospective evaluation.

Original languageEnglish (US)
Pages (from-to)1646-1653
Number of pages8
JournalCritical care medicine
Volume43
Issue number8
DOIs
StatePublished - Jan 1 2015

Fingerprint

Acute Kidney Injury
Septic Shock
Biomarkers
Area Under Curve
Decision Trees
Serum
Blood Proteins
Creatinine
Sepsis

Keywords

  • Biomarkers
  • Decision tree
  • Inflammation
  • Kidney injury
  • Modeling
  • Sepsis

ASJC Scopus subject areas

  • Critical Care and Intensive Care Medicine

Cite this

Wong, H. R., Cvijanovich, N. Z., Anas, N., Allen, G. L., Thomas, N. J., Bigham, M. T., ... Lindsell, C. J. (2015). A multibiomarker-based model for estimating the risk of septic acute kidney injury. Critical care medicine, 43(8), 1646-1653. https://doi.org/10.1097/CCM.0000000000001079
Wong, Hector R. ; Cvijanovich, Natalie Z. ; Anas, Nick ; Allen, Geoffrey L. ; Thomas, Neal J. ; Bigham, Michael T. ; Weiss, Scott L. ; Fitzgerald, Julie ; Checchia, Paul A. ; Meyer, Keith ; Shanley, Thomas P. ; Quasney, Michael ; Hall, Mark ; Gedeit, Rainer ; Freishtat, Robert J. ; Nowak, Jeffrey ; Raj, Shekhar S. ; Gertz, Shira ; Dawson, Emily ; Howard, Kelli ; Harmon, Kelli ; Lahni, Patrick ; Frank, Erin ; Hart, Kimberly W. ; Lindsell, Christopher J. / A multibiomarker-based model for estimating the risk of septic acute kidney injury. In: Critical care medicine. 2015 ; Vol. 43, No. 8. pp. 1646-1653.
@article{508ae630195c4485957897e0dcbc355a,
title = "A multibiomarker-based model for estimating the risk of septic acute kidney injury",
abstract = "Objective: The development of acute kidney injury in patients with sepsis is associated with worse outcomes. Identifying those at risk for septic acute kidney injury could help to inform clinical decision making. We derived and tested a multibiomarker-based model to estimate the risk of septic acute kidney injury in children with septic shock. Design: Candidate serum protein septic acute kidney injury biomarkers were identified from previous transcriptomic studies. Model derivation involved measuring these biomarkers in serum samples from 241 subjects with septic shock obtained during the first 24 hours of admission and then using a Classification and Regression Tree approach to estimate the probability of septic acute kidney injury 3 days after the onset of septic shock, defined as at least two-fold increase from baseline serum creatinine. The model was then tested in a separate cohort of 200 subjects. Setting: Multiple PICUs in the United States. Interventions: None other than standard care. Measurements and Main Results: The decision tree included a firstlevel decision node based on day 1 septic acute kidney injury status and five subsequent biomarker-based decision nodes. The area under the curve for the tree was 0.95 (CI95, 0.91-0.99), with a sensitivity of 93{\%} and a specificity of 88{\%}. The tree was superior to day 1 septic acute kidney injury status alone for estimating day 3 septic acute kidney injury risk. In the test cohort, the tree had an area under the curve of 0.83 (0.72-0.95), with a sensitivity of 85{\%} and a specificity of 77{\%} and was also superior to day 1 septic acute kidney injury status alone for estimating day 3 septic acute kidney injury risk. Conclusions: We have derived and tested a model to estimate the risk of septic acute kidney injury on day 3 of septic shock using a novel panel of biomarkers. The model had very good performance in a test cohort and has test characteristics supporting clinical utility and further prospective evaluation.",
keywords = "Biomarkers, Decision tree, Inflammation, Kidney injury, Modeling, Sepsis",
author = "Wong, {Hector R.} and Cvijanovich, {Natalie Z.} and Nick Anas and Allen, {Geoffrey L.} and Thomas, {Neal J.} and Bigham, {Michael T.} and Weiss, {Scott L.} and Julie Fitzgerald and Checchia, {Paul A.} and Keith Meyer and Shanley, {Thomas P.} and Michael Quasney and Mark Hall and Rainer Gedeit and Freishtat, {Robert J.} and Jeffrey Nowak and Raj, {Shekhar S.} and Shira Gertz and Emily Dawson and Kelli Howard and Kelli Harmon and Patrick Lahni and Erin Frank and Hart, {Kimberly W.} and Lindsell, {Christopher J.}",
year = "2015",
month = "1",
day = "1",
doi = "10.1097/CCM.0000000000001079",
language = "English (US)",
volume = "43",
pages = "1646--1653",
journal = "Critical Care Medicine",
issn = "0090-3493",
publisher = "Lippincott Williams and Wilkins",
number = "8",

}

Wong, HR, Cvijanovich, NZ, Anas, N, Allen, GL, Thomas, NJ, Bigham, MT, Weiss, SL, Fitzgerald, J, Checchia, PA, Meyer, K, Shanley, TP, Quasney, M, Hall, M, Gedeit, R, Freishtat, RJ, Nowak, J, Raj, SS, Gertz, S, Dawson, E, Howard, K, Harmon, K, Lahni, P, Frank, E, Hart, KW & Lindsell, CJ 2015, 'A multibiomarker-based model for estimating the risk of septic acute kidney injury', Critical care medicine, vol. 43, no. 8, pp. 1646-1653. https://doi.org/10.1097/CCM.0000000000001079

A multibiomarker-based model for estimating the risk of septic acute kidney injury. / Wong, Hector R.; Cvijanovich, Natalie Z.; Anas, Nick; Allen, Geoffrey L.; Thomas, Neal J.; Bigham, Michael T.; Weiss, Scott L.; Fitzgerald, Julie; Checchia, Paul A.; Meyer, Keith; Shanley, Thomas P.; Quasney, Michael; Hall, Mark; Gedeit, Rainer; Freishtat, Robert J.; Nowak, Jeffrey; Raj, Shekhar S.; Gertz, Shira; Dawson, Emily; Howard, Kelli; Harmon, Kelli; Lahni, Patrick; Frank, Erin; Hart, Kimberly W.; Lindsell, Christopher J.

In: Critical care medicine, Vol. 43, No. 8, 01.01.2015, p. 1646-1653.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A multibiomarker-based model for estimating the risk of septic acute kidney injury

AU - Wong, Hector R.

AU - Cvijanovich, Natalie Z.

AU - Anas, Nick

AU - Allen, Geoffrey L.

AU - Thomas, Neal J.

AU - Bigham, Michael T.

AU - Weiss, Scott L.

AU - Fitzgerald, Julie

AU - Checchia, Paul A.

AU - Meyer, Keith

AU - Shanley, Thomas P.

AU - Quasney, Michael

AU - Hall, Mark

AU - Gedeit, Rainer

AU - Freishtat, Robert J.

AU - Nowak, Jeffrey

AU - Raj, Shekhar S.

AU - Gertz, Shira

AU - Dawson, Emily

AU - Howard, Kelli

AU - Harmon, Kelli

AU - Lahni, Patrick

AU - Frank, Erin

AU - Hart, Kimberly W.

AU - Lindsell, Christopher J.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Objective: The development of acute kidney injury in patients with sepsis is associated with worse outcomes. Identifying those at risk for septic acute kidney injury could help to inform clinical decision making. We derived and tested a multibiomarker-based model to estimate the risk of septic acute kidney injury in children with septic shock. Design: Candidate serum protein septic acute kidney injury biomarkers were identified from previous transcriptomic studies. Model derivation involved measuring these biomarkers in serum samples from 241 subjects with septic shock obtained during the first 24 hours of admission and then using a Classification and Regression Tree approach to estimate the probability of septic acute kidney injury 3 days after the onset of septic shock, defined as at least two-fold increase from baseline serum creatinine. The model was then tested in a separate cohort of 200 subjects. Setting: Multiple PICUs in the United States. Interventions: None other than standard care. Measurements and Main Results: The decision tree included a firstlevel decision node based on day 1 septic acute kidney injury status and five subsequent biomarker-based decision nodes. The area under the curve for the tree was 0.95 (CI95, 0.91-0.99), with a sensitivity of 93% and a specificity of 88%. The tree was superior to day 1 septic acute kidney injury status alone for estimating day 3 septic acute kidney injury risk. In the test cohort, the tree had an area under the curve of 0.83 (0.72-0.95), with a sensitivity of 85% and a specificity of 77% and was also superior to day 1 septic acute kidney injury status alone for estimating day 3 septic acute kidney injury risk. Conclusions: We have derived and tested a model to estimate the risk of septic acute kidney injury on day 3 of septic shock using a novel panel of biomarkers. The model had very good performance in a test cohort and has test characteristics supporting clinical utility and further prospective evaluation.

AB - Objective: The development of acute kidney injury in patients with sepsis is associated with worse outcomes. Identifying those at risk for septic acute kidney injury could help to inform clinical decision making. We derived and tested a multibiomarker-based model to estimate the risk of septic acute kidney injury in children with septic shock. Design: Candidate serum protein septic acute kidney injury biomarkers were identified from previous transcriptomic studies. Model derivation involved measuring these biomarkers in serum samples from 241 subjects with septic shock obtained during the first 24 hours of admission and then using a Classification and Regression Tree approach to estimate the probability of septic acute kidney injury 3 days after the onset of septic shock, defined as at least two-fold increase from baseline serum creatinine. The model was then tested in a separate cohort of 200 subjects. Setting: Multiple PICUs in the United States. Interventions: None other than standard care. Measurements and Main Results: The decision tree included a firstlevel decision node based on day 1 septic acute kidney injury status and five subsequent biomarker-based decision nodes. The area under the curve for the tree was 0.95 (CI95, 0.91-0.99), with a sensitivity of 93% and a specificity of 88%. The tree was superior to day 1 septic acute kidney injury status alone for estimating day 3 septic acute kidney injury risk. In the test cohort, the tree had an area under the curve of 0.83 (0.72-0.95), with a sensitivity of 85% and a specificity of 77% and was also superior to day 1 septic acute kidney injury status alone for estimating day 3 septic acute kidney injury risk. Conclusions: We have derived and tested a model to estimate the risk of septic acute kidney injury on day 3 of septic shock using a novel panel of biomarkers. The model had very good performance in a test cohort and has test characteristics supporting clinical utility and further prospective evaluation.

KW - Biomarkers

KW - Decision tree

KW - Inflammation

KW - Kidney injury

KW - Modeling

KW - Sepsis

UR - http://www.scopus.com/inward/record.url?scp=84942509173&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942509173&partnerID=8YFLogxK

U2 - 10.1097/CCM.0000000000001079

DO - 10.1097/CCM.0000000000001079

M3 - Article

C2 - 25962083

AN - SCOPUS:84942509173

VL - 43

SP - 1646

EP - 1653

JO - Critical Care Medicine

JF - Critical Care Medicine

SN - 0090-3493

IS - 8

ER -

Wong HR, Cvijanovich NZ, Anas N, Allen GL, Thomas NJ, Bigham MT et al. A multibiomarker-based model for estimating the risk of septic acute kidney injury. Critical care medicine. 2015 Jan 1;43(8):1646-1653. https://doi.org/10.1097/CCM.0000000000001079