MRC CTU at UCL, Institute of Clinical Trials and Methodology, University College London, 90 High Holborn, 2nd Floor, London, WC1V 6LJ, UK.
MGH Biostatistics, Massachusetts General Hospital and Harvard Medical School, 55 Fruit Street, Boston, MA, 02114, USA.
Trials. 2021 Mar 1;22(1):173. doi: 10.1186/s13063-021-05125-8.
During trials that span decades, new evidence including progress in statistical methodology, may require revision of original assumptions. An example is the continued use of a constant-effect approach to analyse the mortality reduction which is often delayed in cancer-screening trials. The latter led us to re-examine our approach for the upcoming primary mortality analysis (2020) of long-term follow-up of the United Kingdom Collaborative Trial of Ovarian Cancer Screening (LTFU UKCTOCS), having initially (2014) used the proportional hazards (PH) Cox model.
We wrote to 12 experts in statistics/epidemiology/screening trials, setting out current evidence, the importance of pre-specification, our previous mortality analysis (2014) and three possible choices for the follow-up analysis (2020) of the mortality outcome: (A) all data (2001-2020) using the Cox model (2014), (B) new data (2015-2020) only and (C) all data (2001-2020) using a test that allows for delayed effects.
Of 11 respondents, eight supported changing the 2014 approach to allow for a potential delayed effect (option C), suggesting various tests while three favoured retaining the Cox model (option A). Consequently, we opted for the Versatile test introduced in 2016 which maintains good power for early, constant or delayed effects. We retained the Royston-Parmar model to estimate absolute differences in disease-specific mortality at 5, 10, 15 and 18 years.
The decision to alter the follow-up analysis for the primary outcome on the basis of new evidence and using new statistical methodology for long-term follow-up is novel and has implications beyond UKCTOCS. There is an urgent need for consensus building on how best to design, test, estimate and report mortality outcomes from long-term randomised cancer screening trials.
ISRCTN22488978 . Registered on 6 April 2000.
在跨越数十年的试验中，新证据（包括统计方法学的进展）可能需要修订原始假设。一个例子是，在癌症筛查试验中，经常会延迟分析死亡率降低的效果，因此需要继续使用固定效应方法来分析。这导致我们重新审视我们在即将进行的英国卵巢癌筛查合作试验（LTFU UKCTOCS）长期随访的主要死亡率分析（2020 年）的方法，我们最初（2014 年）使用了比例风险（PH）Cox 模型。
我们致函 12 位统计学/流行病学/筛查试验方面的专家，阐述了当前的证据、预先指定的重要性、我们之前的死亡率分析（2014 年）以及对死亡率结果进行后续分析（2020 年）的三种可能选择：（A）使用 Cox 模型（2014 年）分析所有数据（2001-2020 年），（B）仅使用新数据（2015-2020 年），（C）使用允许延迟效果的检验方法分析所有数据（2001-2020 年）。
在 11 位回复者中，有 8 位支持改变 2014 年的方法以允许潜在的延迟效果（选项 C），并建议使用各种检验方法，而 3 位赞成保留 Cox 模型（选项 A）。因此，我们选择了 2016 年引入的 Versatile 检验方法，该方法对于早期、固定或延迟效果具有良好的功效。我们保留了 Royston-Parmar 模型来估计 5、10、15 和 18 年时疾病特异性死亡率的绝对差异。
基于新证据和使用新的统计方法对长期随访进行主要结局的后续分析的决定是新颖的，并且超出了 UKCTOCS 的范围。目前迫切需要就如何最好地设计、检验、估计和报告长期随机癌症筛查试验的死亡率结果达成共识。
ISRCTN22488978。于 2000 年 4 月 6 日注册。
