Department of Biostatistics, Hôpital Saint Louis, Université Paris 7 Diderot, Paris, France.
J Clin Epidemiol. 2011 Dec;64(12):1373-82. doi: 10.1016/j.jclinepi.2011.02.009. Epub 2011 Jun 11.
When analyzing observational databases, marginal structural models (MSMs) may offer an appealing approach to estimate causal effects. We aimed at evaluating MSMs, in accounting for confounding when assessing the benefit of intensive care unit (ICU) admission and on its interaction with patient age, as compared with propensity score (PS) matching.
PS and inverse-probability-of-treatment weights for MSMs were derived from an observational study designed to evaluate the benefit of ICU admission on in-hospital mortality. Only first ICU triages (time-fixed weights) or whole triage history (time-dependent weights) were considered. Weights were stabilized by either the prevalence of the actual treatment or the probability of the actual treatment given baseline covariates. Risk difference (RD) was the main outcome measure.
MSMs with time-dependent weights offered the best reduction in the baseline imbalances as compared with PS matching. No effect of ICU admission on in-hospital mortality was found (RD=0.010; 95% confidence interval=-0.038, 0.052) with no interaction between age and treatment.
MSMs appear interesting to handle selection bias in observational studies. When confounding evolves over time, the use of time-dependent weights should be stressed out.
在分析观察性数据库时，边缘结构模型（MSM）可能是一种很有吸引力的方法，可以用来估计因果效应。我们旨在评估 MSM，在评估重症监护病房（ICU）入院的益处并评估其与患者年龄的相互作用时，与倾向评分（PS）匹配相比，MSM 可以控制混杂因素。
PS 和 MSM 的逆处理概率权重是从一项旨在评估 ICU 入院对住院死亡率益处的观察性研究中得出的。仅考虑第一次 ICU 分诊（时间固定权重）或整个分诊历史（时间相关权重）。通过实际治疗的流行率或基线协变量给定的实际治疗的概率来稳定权重。风险差异（RD）是主要的结果衡量指标。
与 PS 匹配相比，具有时间相关权重的 MSM 提供了对基线不平衡的最佳减少。没有发现 ICU 入院对住院死亡率有影响（RD=0.010；95%置信区间=-0.038，0.052），且年龄和治疗之间没有相互作用。
MSM 似乎是处理观察性研究中选择偏差的有趣方法。当混杂因素随时间演变时，应强调使用时间相关权重。
