Development of biomarker combinations for postoperative acute kidney injury via Bayesian model selection in a multicenter cohort study

Allison Meisner, Kathleen F. Kerr, Heather Thiessen Philbrook, Francis Perry Wilson, Amit X. Garg, Michael G. Shlipak, Peter Kavsak, Richard P. Whitlock, Steven G. Coca, Chirag Parikh

Research output: Contribution to journalArticle

Abstract

Background: Acute kidney injury (AKI) is a frequent complication of cardiac surgery. We sought prognostic combinations of postoperative biomarkers measured within 6 h of surgery, potentially in combination with cardiopulmonary bypass time (to account for the degree of insult to the kidney). We used data from a large cohort of patients and adapted methods for developing biomarker combinations to account for the multicenter design of the study. Methods: The primary endpoint was sustained mild AKI, defined as an increase of 50% or more in serum creatinine over preoperative levels lasting at least 2 days during the hospital stay. Severe AKI (secondary endpoint) was defined as a serum creatinine increase of 100% or more or dialysis during hospitalization. Data were from a cohort of 1219 adults undergoing cardiac surgery at 6 medical centers; among these, 117 developed sustained mild AKI and 60 developed severe AKI. We considered cardiopulmonary bypass time and 22 biomarkers as candidate predictors. We adapted Bayesian model averaging methods to develop center-adjusted combinations for sustained mild AKI by (1) maximizing the posterior model probability and (2) retaining predictors with posterior variable probabilities above 0.5. We used resampling-based methods to avoid optimistic bias in evaluating the biomarker combinations. Results: The maximum posterior model probability combination included plasma N-terminal-pro-B-type natriuretic peptide, plasma heart-type fatty acid binding protein, and change in serum creatinine from before to 0-6 h after surgery; the median probability combination additionally included plasma interleukin-6. The center-adjusted, optimism-corrected AUCs for these combinations were 0.80 (95% CI: 0.78, 0.87) and 0.81 (0.78, 0.87), respectively, for predicting sustained mild AKI, and 0.81 (0.76, 0.90) and 0.83 (0.76, 0.90), respectively, for predicting severe AKI. For these data, the Bayesian model averaging methods yielded combinations with prognostic capacity comparable to that achieved by standard frequentist methods but with more parsimonious models. Conclusions: Pending external validation, the identified combinations could be used to identify individuals at high risk of AKI immediately after cardiac surgery and could facilitate clinical trials of renoprotective agents.

Original languageEnglish (US)
Article number3
JournalBiomarker Research
Volume6
Issue number1
DOIs
StatePublished - Jan 12 2018
Externally publishedYes

Fingerprint

Biomarkers
Acute Kidney Injury
Surgery
Multicenter Studies
Cohort Studies
Creatinine
Plasmas
Thoracic Surgery
Fatty Acid-Binding Proteins
Dialysis
Brain Natriuretic Peptide
Cardiopulmonary Bypass
Interleukin-6
Serum
Area Under Curve
Length of Stay
Hospitalization
Clinical Trials
Kidney

Keywords

  • Acute kidney injury
  • Biomarkers combinations
  • Cardiac surgery
  • Prognostic

ASJC Scopus subject areas

  • Molecular Medicine
  • Clinical Biochemistry
  • Biochemistry, medical

Cite this

Development of biomarker combinations for postoperative acute kidney injury via Bayesian model selection in a multicenter cohort study. / Meisner, Allison; Kerr, Kathleen F.; Thiessen Philbrook, Heather; Wilson, Francis Perry; Garg, Amit X.; Shlipak, Michael G.; Kavsak, Peter; Whitlock, Richard P.; Coca, Steven G.; Parikh, Chirag.

In: Biomarker Research, Vol. 6, No. 1, 3, 12.01.2018.

Research output: Contribution to journalArticle

Meisner, Allison ; Kerr, Kathleen F. ; Thiessen Philbrook, Heather ; Wilson, Francis Perry ; Garg, Amit X. ; Shlipak, Michael G. ; Kavsak, Peter ; Whitlock, Richard P. ; Coca, Steven G. ; Parikh, Chirag. / Development of biomarker combinations for postoperative acute kidney injury via Bayesian model selection in a multicenter cohort study. In: Biomarker Research. 2018 ; Vol. 6, No. 1.
@article{8e7f6bdf690144999c8c0fc0a2c8ffb8,
title = "Development of biomarker combinations for postoperative acute kidney injury via Bayesian model selection in a multicenter cohort study",
abstract = "Background: Acute kidney injury (AKI) is a frequent complication of cardiac surgery. We sought prognostic combinations of postoperative biomarkers measured within 6 h of surgery, potentially in combination with cardiopulmonary bypass time (to account for the degree of insult to the kidney). We used data from a large cohort of patients and adapted methods for developing biomarker combinations to account for the multicenter design of the study. Methods: The primary endpoint was sustained mild AKI, defined as an increase of 50{\%} or more in serum creatinine over preoperative levels lasting at least 2 days during the hospital stay. Severe AKI (secondary endpoint) was defined as a serum creatinine increase of 100{\%} or more or dialysis during hospitalization. Data were from a cohort of 1219 adults undergoing cardiac surgery at 6 medical centers; among these, 117 developed sustained mild AKI and 60 developed severe AKI. We considered cardiopulmonary bypass time and 22 biomarkers as candidate predictors. We adapted Bayesian model averaging methods to develop center-adjusted combinations for sustained mild AKI by (1) maximizing the posterior model probability and (2) retaining predictors with posterior variable probabilities above 0.5. We used resampling-based methods to avoid optimistic bias in evaluating the biomarker combinations. Results: The maximum posterior model probability combination included plasma N-terminal-pro-B-type natriuretic peptide, plasma heart-type fatty acid binding protein, and change in serum creatinine from before to 0-6 h after surgery; the median probability combination additionally included plasma interleukin-6. The center-adjusted, optimism-corrected AUCs for these combinations were 0.80 (95{\%} CI: 0.78, 0.87) and 0.81 (0.78, 0.87), respectively, for predicting sustained mild AKI, and 0.81 (0.76, 0.90) and 0.83 (0.76, 0.90), respectively, for predicting severe AKI. For these data, the Bayesian model averaging methods yielded combinations with prognostic capacity comparable to that achieved by standard frequentist methods but with more parsimonious models. Conclusions: Pending external validation, the identified combinations could be used to identify individuals at high risk of AKI immediately after cardiac surgery and could facilitate clinical trials of renoprotective agents.",
keywords = "Acute kidney injury, Biomarkers combinations, Cardiac surgery, Prognostic",
author = "Allison Meisner and Kerr, {Kathleen F.} and {Thiessen Philbrook}, Heather and Wilson, {Francis Perry} and Garg, {Amit X.} and Shlipak, {Michael G.} and Peter Kavsak and Whitlock, {Richard P.} and Coca, {Steven G.} and Chirag Parikh",
year = "2018",
month = "1",
day = "12",
doi = "10.1186/s40364-018-0117-z",
language = "English (US)",
volume = "6",
journal = "Biomarker Research",
issn = "2050-7771",
publisher = "BioMed Central Ltd.",
number = "1",

}

TY - JOUR

T1 - Development of biomarker combinations for postoperative acute kidney injury via Bayesian model selection in a multicenter cohort study

AU - Meisner, Allison

AU - Kerr, Kathleen F.

AU - Thiessen Philbrook, Heather

AU - Wilson, Francis Perry

AU - Garg, Amit X.

AU - Shlipak, Michael G.

AU - Kavsak, Peter

AU - Whitlock, Richard P.

AU - Coca, Steven G.

AU - Parikh, Chirag

PY - 2018/1/12

Y1 - 2018/1/12

N2 - Background: Acute kidney injury (AKI) is a frequent complication of cardiac surgery. We sought prognostic combinations of postoperative biomarkers measured within 6 h of surgery, potentially in combination with cardiopulmonary bypass time (to account for the degree of insult to the kidney). We used data from a large cohort of patients and adapted methods for developing biomarker combinations to account for the multicenter design of the study. Methods: The primary endpoint was sustained mild AKI, defined as an increase of 50% or more in serum creatinine over preoperative levels lasting at least 2 days during the hospital stay. Severe AKI (secondary endpoint) was defined as a serum creatinine increase of 100% or more or dialysis during hospitalization. Data were from a cohort of 1219 adults undergoing cardiac surgery at 6 medical centers; among these, 117 developed sustained mild AKI and 60 developed severe AKI. We considered cardiopulmonary bypass time and 22 biomarkers as candidate predictors. We adapted Bayesian model averaging methods to develop center-adjusted combinations for sustained mild AKI by (1) maximizing the posterior model probability and (2) retaining predictors with posterior variable probabilities above 0.5. We used resampling-based methods to avoid optimistic bias in evaluating the biomarker combinations. Results: The maximum posterior model probability combination included plasma N-terminal-pro-B-type natriuretic peptide, plasma heart-type fatty acid binding protein, and change in serum creatinine from before to 0-6 h after surgery; the median probability combination additionally included plasma interleukin-6. The center-adjusted, optimism-corrected AUCs for these combinations were 0.80 (95% CI: 0.78, 0.87) and 0.81 (0.78, 0.87), respectively, for predicting sustained mild AKI, and 0.81 (0.76, 0.90) and 0.83 (0.76, 0.90), respectively, for predicting severe AKI. For these data, the Bayesian model averaging methods yielded combinations with prognostic capacity comparable to that achieved by standard frequentist methods but with more parsimonious models. Conclusions: Pending external validation, the identified combinations could be used to identify individuals at high risk of AKI immediately after cardiac surgery and could facilitate clinical trials of renoprotective agents.

AB - Background: Acute kidney injury (AKI) is a frequent complication of cardiac surgery. We sought prognostic combinations of postoperative biomarkers measured within 6 h of surgery, potentially in combination with cardiopulmonary bypass time (to account for the degree of insult to the kidney). We used data from a large cohort of patients and adapted methods for developing biomarker combinations to account for the multicenter design of the study. Methods: The primary endpoint was sustained mild AKI, defined as an increase of 50% or more in serum creatinine over preoperative levels lasting at least 2 days during the hospital stay. Severe AKI (secondary endpoint) was defined as a serum creatinine increase of 100% or more or dialysis during hospitalization. Data were from a cohort of 1219 adults undergoing cardiac surgery at 6 medical centers; among these, 117 developed sustained mild AKI and 60 developed severe AKI. We considered cardiopulmonary bypass time and 22 biomarkers as candidate predictors. We adapted Bayesian model averaging methods to develop center-adjusted combinations for sustained mild AKI by (1) maximizing the posterior model probability and (2) retaining predictors with posterior variable probabilities above 0.5. We used resampling-based methods to avoid optimistic bias in evaluating the biomarker combinations. Results: The maximum posterior model probability combination included plasma N-terminal-pro-B-type natriuretic peptide, plasma heart-type fatty acid binding protein, and change in serum creatinine from before to 0-6 h after surgery; the median probability combination additionally included plasma interleukin-6. The center-adjusted, optimism-corrected AUCs for these combinations were 0.80 (95% CI: 0.78, 0.87) and 0.81 (0.78, 0.87), respectively, for predicting sustained mild AKI, and 0.81 (0.76, 0.90) and 0.83 (0.76, 0.90), respectively, for predicting severe AKI. For these data, the Bayesian model averaging methods yielded combinations with prognostic capacity comparable to that achieved by standard frequentist methods but with more parsimonious models. Conclusions: Pending external validation, the identified combinations could be used to identify individuals at high risk of AKI immediately after cardiac surgery and could facilitate clinical trials of renoprotective agents.

KW - Acute kidney injury

KW - Biomarkers combinations

KW - Cardiac surgery

KW - Prognostic

UR - http://www.scopus.com/inward/record.url?scp=85049632878&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049632878&partnerID=8YFLogxK

U2 - 10.1186/s40364-018-0117-z

DO - 10.1186/s40364-018-0117-z

M3 - Article

VL - 6

JO - Biomarker Research

JF - Biomarker Research

SN - 2050-7771

IS - 1

M1 - 3

ER -