Immortal Time Bias in the Analysis of Time-to-Event Data in Orthopedics.
Immortal Time Bias in the Analysis of Time-to-Event Data in Orthopedics.
复制标题
DOI:
10.1016/j.arth.2021.06.012
复制
发表时间:
2021-10
期刊:
影响因子:
--
通讯作者:
Maradit Kremers H
中科院分区:
文献类型:
--
作者:
Larson DR;Crowson CS;Devick KL;Lewallen DG;Berry DJ;Maradit Kremers H
Many outcomes in arthroplasty research are analyzed as time-to-event outcomes using survival analysis methods. When comparison groups are defined after a time-delayed exposure or intervention, a period of immortal time arises and can lead to biased results. In orthopaedics research, immortal time bias often arises when a minimum amount of follow-up is required for study inclusion or when comparing outcomes in staged bilateral versus unilateral arthroplasty patients. We present an explanation of immortal time and the associated bias, describe how to correctly account for it using proper data preparation and statistical techniques, and provide an illustrative example using real-world arthroplasty data. We offer practical guidelines for identifying and properly handling immortal time to avoid bias.
登录
查看更多内容
影响因子:
5.8
作者:
Dekkers, Olaf M.;Groenwold, Rolf H. H.
通讯作者:
Groenwold, Rolf H. H.
影响因子:
13.3
作者:
Prieto-Alhambra, Daniel;Lalmohamed, Arief;de Vries, Frank
通讯作者:
de Vries, Frank
影响因子:
2.6
作者:
Agarwal, Parul;Moshier, Erin;Mazumdar, Madhu
通讯作者:
Mazumdar, Madhu
影响因子:
3.4
作者:
Hugar, Lee A.;Borza, Tudor;Jacobs, Bruce L.
通讯作者:
Jacobs, Bruce L.
影响因子:
5
作者:
Lalmohamed, Arief;van Staa, Tjeerd P.;de Vries, Frank
通讯作者:
de Vries, Frank