Advertisement

Time-dependent effect, immortal bias, and competing risk: 3 components that should be handled to assess the impact of covariates on occurrence of acute kidney injury

  • Matthieu Jamme
    Correspondence
    Correspondence: Matthieu Jamme, Service de Réanimation polyvalente, Centre hospitalier intercommunal de Poissy Saint Germain en Laye, 10 rue du champ Gaillard, 78300, Poissy, France.
    Affiliations
    Service de Réanimation polyvalente, Centre hospitalier intercommunal de Poissy Saint Germain en Laye (CHIPS), Poissy, France

    INSERM U1018, Centre de recherche en épidémiologie et santé des populations (CESP), Equipe “Rein et Cœur,” Université Paris Saclay, Villejuif, France
    Search for articles by this author
  • Guillaume Geri
    Affiliations
    INSERM U1018, Centre de recherche en épidémiologie et santé des populations (CESP), Equipe “Rein et Cœur,” Université Paris Saclay, Villejuif, France

    Service de Médecine intensive Réanimation, Hôpital Ambroise Paré, Assistance Publique Hôpitaux de Paris (APHP), Boulogne Billancourt, France
    Search for articles by this author
      We read with great interest the study from Hirsch et al. in the July 2020 issue of Kidney International.
      • Hirsch J.S.
      • Ng J.H.
      • Ross D.W.
      • et al.
      Acute kidney injury in patients hospitalized with COVID-19.
      In that study, the authors aimed to identify risk factors of acute kidney injury (AKI) in patients admitted for coronavirus disease 2019. They compared characteristics of 5449 patients according to AKI occurrence and performed multivariable logistic regression to adjust for covariates. The authors have identified 2 risk factors occurring during the hospital stay: the need for mechanical ventilation (odds ratio = 31.6 [25.8–38.6] in univariate analysis and odds ratio = 10.7 [6.81–16.7] in multivariable analysis) and vasopressor medication (odds ratio = 31.4 [25.6–38.4] in univariate analysis and odds ratio = 4.5 [2.9–7.1] in multivariable analysis).
      To read this article in full you will need to make a payment
      ISN Member Login
      Login with your ISN username and password.
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Purchase one-time access:

      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Hirsch J.S.
        • Ng J.H.
        • Ross D.W.
        • et al.
        Acute kidney injury in patients hospitalized with COVID-19.
        Kidney Int. 2020; 98: 209-218
        • Latouche A.
        • Porcher R.
        • Chevret S.
        A note on including time-dependent covariate in regression model for competing risks data.
        Biom J Biom Z. 2005; 47: 807-814
        • Beyersmann J.
        • Gastmeier P.
        • Wolkewitz M.
        • Schumacher M.
        An easy mathematical proof showed that time-dependent bias inevitably leads to biased effect estimation.
        J Clin Epidemiol. 2008; 61: 1216-1221
        • Rizopoulos D.
        Dynamic predictions and prospective accuracy in joint models for longitudinal and time-to-event data.
        Biometrics. 2011; 67: 819-829

      Linked Article

      • Acute kidney injury in patients hospitalized with COVID-19
        Kidney InternationalVol. 98Issue 1
        • Preview
          The rate of acute kidney injury (AKI) associated with patients hospitalized with Covid-19, and associated outcomes are not well understood. This study describes the presentation, risk factors and outcomes of AKI in patients hospitalized with Covid-19. We reviewed the health records for all patients hospitalized with Covid-19 between March 1, and April 5, 2020, at 13 academic and community hospitals in metropolitan New York. Patients younger than 18 years of age, with end stage kidney disease or with a kidney transplant were excluded.
        • Full-Text
        • PDF
      • The authors reply
        Kidney InternationalVol. 98Issue 5
        • Preview
          We thank Jamme and Geri for their comments.1 When we first embarked on this study in mid-April 2020, the data on acute kidney injury (AKI) among patients hospitalized with coronavirus disease 2019 in the United States were sparse.2 Thus, our primary research question was to (i) determine the rates of AKI among these patients, and (ii) investigate the effects of potential explanatory variables on the occurrence of AKI.2 The goal was not to determine time-to-AKI, nor to make causal inferences about how mechanical ventilation causes AKI.
        • Full-Text
        • PDF