Serum creatinine back-estimation in cardiac surgery patients: Misclassification of AKI using existing formulae and a data-driven model

Martin Hermann Bernardi, Daniel Schmidlin, Robin Ristl, Clemens Heitzinger, Arno Schiferer, Thomas Neugebauer, Thomas Wrba, Michael Hiesmayr, Wilfred Druml, Andrea Lassnigg

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Background and objectives A knowledge of baseline serum creatinine (bSCr) is mandatory for diagnosing and staging AKI.With often missing values, bSCr is estimated by back-calculation using several equations designed for the estimation of GFR, assuming a “true” GFR of 75 ml/min per 1.73 m2.Using a data set from a large cardiac surgery cohort,we tested the appropriateness of such an approach and compared estimated andmeasured bSCr. Moreover, we designed a novel data-driven model (estimated serum creatinine [eSCr]) for estimating bSCr. Finally, we analyzed the extent of AKI and mortality rate misclassifications. Design, setting, participants, & measurements Data for 8024 patients (2833 women) in our cardiac surgery center were included from 1997 to 2008. Measured and estimated bSCr were plotted against age for men and women. Patients were classified to AKI stages defined by the Kidney Disease Improving Global Outcomes (KDIGO) group. Results were compared with data from another cardiac surgery center in Zurich, Switzerland. Results The Modification of Diet in Renal Disease and the Chronic Kidney Disease Epidemiology Collaboration formulae describe higher estimated bSCr values in younger patients, but lower values in older patients compared with themeasured bSCr values in both centers. The Pittsburgh Linear ThreeVariables formula correctly describes the increasing bSCr with age, however, it underestimates the overall bSCr level, being in the range of the 25% quantile of themeasured values. Our eSCrmodel estimatedmeasured bSCr best. AKI stage 1 classification using all formulae, including our eSCr model, was incorrect in 53%–80% of patients in Vienna and in 74%–91% in Zurich; AKI severity (according to KDIGO stages) and also mortality were overestimated. Mortality rate was higher among patients falsely classified into higher KDIGO stages by estimated bSCr. Conclusions bSCr values back-estimated using currently available eGFR formulae are inaccurate and cannot correctly classify AKI stages. Our model eSCr improves the prediction of AKI but to a still inadequate extent.

Original languageEnglish (US)
Pages (from-to)395-404
Number of pages10
JournalClinical Journal of the American Society of Nephrology
Volume11
Issue number3
DOIs
StatePublished - Mar 7 2016
Externally publishedYes

Fingerprint

Thoracic Surgery
Creatinine
Serum
Kidney Diseases
Mortality
Diet Therapy
Switzerland
Chronic Renal Insufficiency
Epidemiology

ASJC Scopus subject areas

  • Nephrology
  • Transplantation
  • Epidemiology
  • Critical Care and Intensive Care Medicine

Cite this

Serum creatinine back-estimation in cardiac surgery patients : Misclassification of AKI using existing formulae and a data-driven model. / Bernardi, Martin Hermann; Schmidlin, Daniel; Ristl, Robin; Heitzinger, Clemens; Schiferer, Arno; Neugebauer, Thomas; Wrba, Thomas; Hiesmayr, Michael; Druml, Wilfred; Lassnigg, Andrea.

In: Clinical Journal of the American Society of Nephrology, Vol. 11, No. 3, 07.03.2016, p. 395-404.

Research output: Contribution to journalArticle

Bernardi, MH, Schmidlin, D, Ristl, R, Heitzinger, C, Schiferer, A, Neugebauer, T, Wrba, T, Hiesmayr, M, Druml, W & Lassnigg, A 2016, 'Serum creatinine back-estimation in cardiac surgery patients: Misclassification of AKI using existing formulae and a data-driven model', Clinical Journal of the American Society of Nephrology, vol. 11, no. 3, pp. 395-404. https://doi.org/10.2215/CJN.03560315
Bernardi, Martin Hermann ; Schmidlin, Daniel ; Ristl, Robin ; Heitzinger, Clemens ; Schiferer, Arno ; Neugebauer, Thomas ; Wrba, Thomas ; Hiesmayr, Michael ; Druml, Wilfred ; Lassnigg, Andrea. / Serum creatinine back-estimation in cardiac surgery patients : Misclassification of AKI using existing formulae and a data-driven model. In: Clinical Journal of the American Society of Nephrology. 2016 ; Vol. 11, No. 3. pp. 395-404.
@article{a0041a144d064dcfbde253e7d4cfb00a,
title = "Serum creatinine back-estimation in cardiac surgery patients: Misclassification of AKI using existing formulae and a data-driven model",
abstract = "Background and objectives A knowledge of baseline serum creatinine (bSCr) is mandatory for diagnosing and staging AKI.With often missing values, bSCr is estimated by back-calculation using several equations designed for the estimation of GFR, assuming a “true” GFR of 75 ml/min per 1.73 m2.Using a data set from a large cardiac surgery cohort,we tested the appropriateness of such an approach and compared estimated andmeasured bSCr. Moreover, we designed a novel data-driven model (estimated serum creatinine [eSCr]) for estimating bSCr. Finally, we analyzed the extent of AKI and mortality rate misclassifications. Design, setting, participants, & measurements Data for 8024 patients (2833 women) in our cardiac surgery center were included from 1997 to 2008. Measured and estimated bSCr were plotted against age for men and women. Patients were classified to AKI stages defined by the Kidney Disease Improving Global Outcomes (KDIGO) group. Results were compared with data from another cardiac surgery center in Zurich, Switzerland. Results The Modification of Diet in Renal Disease and the Chronic Kidney Disease Epidemiology Collaboration formulae describe higher estimated bSCr values in younger patients, but lower values in older patients compared with themeasured bSCr values in both centers. The Pittsburgh Linear ThreeVariables formula correctly describes the increasing bSCr with age, however, it underestimates the overall bSCr level, being in the range of the 25{\%} quantile of themeasured values. Our eSCrmodel estimatedmeasured bSCr best. AKI stage 1 classification using all formulae, including our eSCr model, was incorrect in 53{\%}–80{\%} of patients in Vienna and in 74{\%}–91{\%} in Zurich; AKI severity (according to KDIGO stages) and also mortality were overestimated. Mortality rate was higher among patients falsely classified into higher KDIGO stages by estimated bSCr. Conclusions bSCr values back-estimated using currently available eGFR formulae are inaccurate and cannot correctly classify AKI stages. Our model eSCr improves the prediction of AKI but to a still inadequate extent.",
author = "Bernardi, {Martin Hermann} and Daniel Schmidlin and Robin Ristl and Clemens Heitzinger and Arno Schiferer and Thomas Neugebauer and Thomas Wrba and Michael Hiesmayr and Wilfred Druml and Andrea Lassnigg",
year = "2016",
month = "3",
day = "7",
doi = "10.2215/CJN.03560315",
language = "English (US)",
volume = "11",
pages = "395--404",
journal = "Clinical journal of the American Society of Nephrology : CJASN",
issn = "1555-9041",
publisher = "American Society of Nephrology",
number = "3",

}

TY - JOUR

T1 - Serum creatinine back-estimation in cardiac surgery patients

T2 - Misclassification of AKI using existing formulae and a data-driven model

AU - Bernardi, Martin Hermann

AU - Schmidlin, Daniel

AU - Ristl, Robin

AU - Heitzinger, Clemens

AU - Schiferer, Arno

AU - Neugebauer, Thomas

AU - Wrba, Thomas

AU - Hiesmayr, Michael

AU - Druml, Wilfred

AU - Lassnigg, Andrea

PY - 2016/3/7

Y1 - 2016/3/7

N2 - Background and objectives A knowledge of baseline serum creatinine (bSCr) is mandatory for diagnosing and staging AKI.With often missing values, bSCr is estimated by back-calculation using several equations designed for the estimation of GFR, assuming a “true” GFR of 75 ml/min per 1.73 m2.Using a data set from a large cardiac surgery cohort,we tested the appropriateness of such an approach and compared estimated andmeasured bSCr. Moreover, we designed a novel data-driven model (estimated serum creatinine [eSCr]) for estimating bSCr. Finally, we analyzed the extent of AKI and mortality rate misclassifications. Design, setting, participants, & measurements Data for 8024 patients (2833 women) in our cardiac surgery center were included from 1997 to 2008. Measured and estimated bSCr were plotted against age for men and women. Patients were classified to AKI stages defined by the Kidney Disease Improving Global Outcomes (KDIGO) group. Results were compared with data from another cardiac surgery center in Zurich, Switzerland. Results The Modification of Diet in Renal Disease and the Chronic Kidney Disease Epidemiology Collaboration formulae describe higher estimated bSCr values in younger patients, but lower values in older patients compared with themeasured bSCr values in both centers. The Pittsburgh Linear ThreeVariables formula correctly describes the increasing bSCr with age, however, it underestimates the overall bSCr level, being in the range of the 25% quantile of themeasured values. Our eSCrmodel estimatedmeasured bSCr best. AKI stage 1 classification using all formulae, including our eSCr model, was incorrect in 53%–80% of patients in Vienna and in 74%–91% in Zurich; AKI severity (according to KDIGO stages) and also mortality were overestimated. Mortality rate was higher among patients falsely classified into higher KDIGO stages by estimated bSCr. Conclusions bSCr values back-estimated using currently available eGFR formulae are inaccurate and cannot correctly classify AKI stages. Our model eSCr improves the prediction of AKI but to a still inadequate extent.

AB - Background and objectives A knowledge of baseline serum creatinine (bSCr) is mandatory for diagnosing and staging AKI.With often missing values, bSCr is estimated by back-calculation using several equations designed for the estimation of GFR, assuming a “true” GFR of 75 ml/min per 1.73 m2.Using a data set from a large cardiac surgery cohort,we tested the appropriateness of such an approach and compared estimated andmeasured bSCr. Moreover, we designed a novel data-driven model (estimated serum creatinine [eSCr]) for estimating bSCr. Finally, we analyzed the extent of AKI and mortality rate misclassifications. Design, setting, participants, & measurements Data for 8024 patients (2833 women) in our cardiac surgery center were included from 1997 to 2008. Measured and estimated bSCr were plotted against age for men and women. Patients were classified to AKI stages defined by the Kidney Disease Improving Global Outcomes (KDIGO) group. Results were compared with data from another cardiac surgery center in Zurich, Switzerland. Results The Modification of Diet in Renal Disease and the Chronic Kidney Disease Epidemiology Collaboration formulae describe higher estimated bSCr values in younger patients, but lower values in older patients compared with themeasured bSCr values in both centers. The Pittsburgh Linear ThreeVariables formula correctly describes the increasing bSCr with age, however, it underestimates the overall bSCr level, being in the range of the 25% quantile of themeasured values. Our eSCrmodel estimatedmeasured bSCr best. AKI stage 1 classification using all formulae, including our eSCr model, was incorrect in 53%–80% of patients in Vienna and in 74%–91% in Zurich; AKI severity (according to KDIGO stages) and also mortality were overestimated. Mortality rate was higher among patients falsely classified into higher KDIGO stages by estimated bSCr. Conclusions bSCr values back-estimated using currently available eGFR formulae are inaccurate and cannot correctly classify AKI stages. Our model eSCr improves the prediction of AKI but to a still inadequate extent.

UR - http://www.scopus.com/inward/record.url?scp=84960105445&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960105445&partnerID=8YFLogxK

U2 - 10.2215/CJN.03560315

DO - 10.2215/CJN.03560315

M3 - Article

AN - SCOPUS:84960105445

VL - 11

SP - 395

EP - 404

JO - Clinical journal of the American Society of Nephrology : CJASN

JF - Clinical journal of the American Society of Nephrology : CJASN

SN - 1555-9041

IS - 3

ER -