School of Public Health Imperial College London, Medical School Building, St Mary's Hospital, Norfolk Place, London, UK.
Imperial Clinical Trials Unit, Imperial College London, Stadium House, 68 Wood Lane, London, UK.
BMC Med Res Methodol. 2021 Apr 15;21(1):72. doi: 10.1186/s12874-021-01261-6.
Missing data are common in randomised controlled trials (RCTs) and can bias results if not handled appropriately. A statistically valid analysis under the primary missing-data assumptions should be conducted, followed by sensitivity analysis under alternative justified assumptions to assess the robustness of results. Controlled Multiple Imputation (MI) procedures, including delta-based and reference-based approaches, have been developed for analysis under missing-not-at-random assumptions. However, it is unclear how often these methods are used, how they are reported, and what their impact is on trial results. This review evaluates the current use and reporting of MI and controlled MI in RCTs.
A targeted review of phase II-IV RCTs (non-cluster randomised) published in two leading general medical journals (The Lancet and New England Journal of Medicine) between January 2014 and December 2019 using MI. Data was extracted on imputation methods, analysis status, and reporting of results. Results of primary and sensitivity analyses for trials using controlled MI analyses were compared.
A total of 118 RCTs (9% of published RCTs) used some form of MI. MI under missing-at-random was used in 110 trials; this was for primary analysis in 43/118 (36%), and in sensitivity analysis for 70/118 (59%) (3 used in both). Sixteen studies performed controlled MI (1.3% of published RCTs), either with a delta-based (n = 9) or reference-based approach (n = 7). Controlled MI was mostly used in sensitivity analysis (n = 14/16). Two trials used controlled MI for primary analysis, including one reporting no sensitivity analysis whilst the other reported similar results without imputation. Of the 14 trials using controlled MI in sensitivity analysis, 12 yielded comparable results to the primary analysis whereas 2 demonstrated contradicting results. Only 5/110 (5%) trials using missing-at-random MI and 5/16 (31%) trials using controlled MI reported complete details on MI methods.
Controlled MI enabled the impact of accessible contextually relevant missing data assumptions to be examined on trial results. The use of controlled MI is increasing but is still infrequent and poorly reported where used. There is a need for improved reporting on the implementation of MI analyses and choice of controlled MI parameters.
随机对照试验（RCT）中常见数据缺失，如果处理不当，可能会导致结果产生偏倚。应根据主要缺失数据假设进行有效的统计分析，然后根据替代合理假设进行敏感性分析，以评估结果的稳健性。已经开发了基于受控多重插补（MI）的程序，包括基于差值和基于参考的方法，用于分析非随机缺失数据的情况。然而，目前尚不清楚这些方法的使用频率、报告方式以及它们对试验结果的影响。本综述评估了 MI 和受控 MI 在 RCT 中的当前使用和报告情况。
对 2014 年 1 月至 2019 年 12 月期间在两家领先的普通医学期刊（《柳叶刀》和《新英格兰医学杂志》）上发表的 II-IV 期 RCT（非整群随机）进行有针对性的综述，使用 MI 进行分析。提取关于插补方法、分析状态和结果报告的数据。比较使用受控 MI 分析的试验的主要和敏感性分析结果。
共有 118 项 RCT（已发表 RCT 的 9%）使用了某种形式的 MI。110 项试验中使用了随机缺失数据下的 MI，其中 43/118（36%）用于主要分析，70/118（59%）用于敏感性分析（3 项用于两者）。16 项研究进行了受控 MI（已发表 RCT 的 1.3%），其中 9 项采用基于差值的方法，7 项采用基于参考的方法。受控 MI 主要用于敏感性分析（n=14/16）。两项试验将受控 MI 用于主要分析，其中一项报告没有进行敏感性分析，另一项报告了没有插补的相似结果。在 14 项用于敏感性分析的受控 MI 试验中，12 项与主要分析结果相当，而 2 项结果则相反。在使用随机缺失 MI 的 110 项试验中，只有 5/110（5%）报告了 MI 方法的完整细节，而在使用受控 MI 的 16 项试验中，只有 5/16（31%）报告了 MI 方法的完整细节。
受控 MI 能够检查试验结果中可访问的上下文相关缺失数据假设的影响。受控 MI 的使用正在增加，但仍然很少见，且使用时报告也很差。需要改进 MI 分析的实施和受控 MI 参数选择的报告。
