Carl van Walraven1, Finlay A McAlister2. 1. Faculty of Medicine, University of Ottawa; Epidemiology and Community Medicine, University of Ottawa; Ottawa Hospital Research Institute; ICES uOttawa. Electronic address: carlv@ohri.ca. 2. Medicine, University of Alberta, 8440 112 St NW, Edmonton, AB T6G 2P4, Canada; Alberta Innovates-Health Solutions.
Abstract
OBJECTIVE: Risk estimates from Kaplan-Meier curves are well known to medical researchers, reviewers, and editors. In this study, we determined the proportion of Kaplan-Meier analyses published in prominent medical journals that are potentially biased because of competing events ("competing risk bias"). STUDY DESIGN AND SETTING: We randomly selected 100 studies that had at least one Kaplan-Meier analysis and were recently published in prominent medical journals. Susceptibility to competing risk bias was determined by examining the outcome and potential competing events. In susceptible studies, bias was quantified using a previously validated prediction model when the number of outcomes and competing events were given. RESULTS: Forty-six studies (46%) contained Kaplan-Meier analyses susceptible to competing risk bias. Sixteen studies (34.8%) susceptible to competing risk cited the number of outcomes and competing events; in six of these studies (6/16, 37.5%), the outcome risk from the Kaplan-Meier estimate (relative to the true risk) was biased upward by 10% or more. CONCLUSION: Almost half of Kaplan-Meier analyses published in medical journals are susceptible to competing risk bias and may overestimate event risk. This bias was found to be quantitatively important in a third of such studies.
OBJECTIVE: Risk estimates from Kaplan-Meier curves are well known to medical researchers, reviewers, and editors. In this study, we determined the proportion of Kaplan-Meier analyses published in prominent medical journals that are potentially biased because of competing events ("competing risk bias"). STUDY DESIGN AND SETTING: We randomly selected 100 studies that had at least one Kaplan-Meier analysis and were recently published in prominent medical journals. Susceptibility to competing risk bias was determined by examining the outcome and potential competing events. In susceptible studies, bias was quantified using a previously validated prediction model when the number of outcomes and competing events were given. RESULTS: Forty-six studies (46%) contained Kaplan-Meier analyses susceptible to competing risk bias. Sixteen studies (34.8%) susceptible to competing risk cited the number of outcomes and competing events; in six of these studies (6/16, 37.5%), the outcome risk from the Kaplan-Meier estimate (relative to the true risk) was biased upward by 10% or more. CONCLUSION: Almost half of Kaplan-Meier analyses published in medical journals are susceptible to competing risk bias and may overestimate event risk. This bias was found to be quantitatively important in a third of such studies.
Authors: Victor D Dinglas; Caroline M Chessare; Wesley E Davis; Ann Parker; Lisa Aronson Friedman; Elizabeth Colantuoni; Clifton O Bingham; Alison E Turnbull; Dale M Needham Journal: Thorax Date: 2017-07-29 Impact factor: 9.139
Authors: Alison E Turnbull; Kristin A Sepulveda; Victor D Dinglas; Caroline M Chessare; Clifton O Bingham; Dale M Needham Journal: Crit Care Med Date: 2017-06 Impact factor: 7.598