更改

An RCT may be [[Blind experiment|blinded]], (also called "masked") by "procedures that prevent study participants, caregivers, or outcome assessors from knowing which intervention was received."<ref name="Wood-2008">{{Cite journal |vauthors=Wood L, Egger M, Gluud LL, Schulz KF, Jüni P, Altman DG, Gluud C, Martin RM, Wood AJ, Sterne JA | title = Empirical evidence of bias in treatment effect estimates in controlled trials with different interventions and outcomes: meta-epidemiological study | journal = BMJ | volume = 336 | issue = 7644 | pages = 601–5 | year = 2008 | doi = 10.1136/bmj.39465.451748.AD | pmid = 18316340 | pmc = 2267990 }}</ref> Unlike allocation concealment, blinding is sometimes inappropriate or impossible to perform in an RCT; for example, if an RCT involves a treatment in which active participation of the patient is necessary (e.g., [[physical therapy]]), participants cannot be blinded to the intervention.

An RCT may be [[Blind experiment|blinded]], (also called "masked") by "procedures that prevent study participants, caregivers, or outcome assessors from knowing which intervention was received."<ref name="Wood-2008">{{Cite journal |vauthors=Wood L, Egger M, Gluud LL, Schulz KF, Jüni P, Altman DG, Gluud C, Martin RM, Wood AJ, Sterne JA | title = Empirical evidence of bias in treatment effect estimates in controlled trials with different interventions and outcomes: meta-epidemiological study | journal = BMJ | volume = 336 | issue = 7644 | pages = 601–5 | year = 2008 | doi = 10.1136/bmj.39465.451748.AD | pmid = 18316340 | pmc = 2267990 }}</ref> Unlike allocation concealment, blinding is sometimes inappropriate or impossible to perform in an RCT; for example, if an RCT involves a treatment in which active participation of the patient is necessary (e.g., [[physical therapy]]), participants cannot be blinded to the intervention.

If a disruptive innovation in medical technology is developed, it may be difficult to test this ethically in an RCT if it becomes "obvious" that the control subjects have poorer outcomes—either due to other foregoing testing, or within the initial phase of the RCT itself.  Ethically it may be necessary to abort the RCT prematurely, and getting ethics approval (and patient agreement) to withhold the innovation from the control group in future RCT's may not be feasible.

一项RCT的盲法是指阻止研究参与者、照顾者或结果评估者知道哪些干预措施，这一程序也称“蒙面”。与分配隐藏不同，在RCT，致盲有时是不合适的或不可能的；例如，如果RCT涉及需要患者积极参与的治疗(例如物理治疗)，参与者不能对干预视而不见。

 

 

 

Traditionally, blinded RCTs have been classified as "single-blind", "double-blind", or "triple-blind"; however, in 2001 and 2006 two studies showed that these terms have different meanings for different people.<ref name="Devereaux-2001">{{Cite journal |vauthors=Devereaux PJ, Manns BJ, Ghali WA, Quan H, Lacchetti C, Montori VM, Bhandari M, Guyatt GH | title = Physician interpretations and textbook definitions of blinding terminology in randomized controlled trials | journal = [[J Am Med Assoc]] | volume = 285 | issue = 15 | pages = 2000–3 | year = 2001 | doi =  10.1001/jama.285.15.2000| pmid = 11308438 | doi-access = free }}</ref><ref name="Haahr-2006">{{Cite journal |vauthors=Haahr MT, Hróbjartsson A | title = Who is blinded in randomized clinical trials? A study of 200 trials and a survey of authors | journal = Clin Trials | volume = 3 | issue = 4 | pages = 360–5 | year = 2006 | doi = 10.1177/1740774506069153 | pmid = 17060210 | s2cid = 23818514 }}</ref>  The 2010 [[Consolidated Standards of Reporting Trials|CONSORT Statement]] specifies that authors and editors should not use the terms "single-blind", "double-blind", and "triple-blind"; instead, reports of blinded RCT should discuss "If done, who was blinded after assignment to interventions (for example, participants, care providers, those assessing outcomes) and how."<ref name="Moher-2010"/>

Traditionally, blinded RCTs have been classified as "single-blind", "double-blind", or "triple-blind"; however, in 2001 and 2006 two studies showed that these terms have different meanings for different people.<ref name="Devereaux-2001">{{Cite journal |vauthors=Devereaux PJ, Manns BJ, Ghali WA, Quan H, Lacchetti C, Montori VM, Bhandari M, Guyatt GH | title = Physician interpretations and textbook definitions of blinding terminology in randomized controlled trials | journal = [[J Am Med Assoc]] | volume = 285 | issue = 15 | pages = 2000–3 | year = 2001 | doi =  10.1001/jama.285.15.2000| pmid = 11308438 | doi-access = free }}</ref><ref name="Haahr-2006">{{Cite journal |vauthors=Haahr MT, Hróbjartsson A | title = Who is blinded in randomized clinical trials? A study of 200 trials and a survey of authors | journal = Clin Trials | volume = 3 | issue = 4 | pages = 360–5 | year = 2006 | doi = 10.1177/1740774506069153 | pmid = 17060210 | s2cid = 23818514 }}</ref>  The 2010 [[Consolidated Standards of Reporting Trials|CONSORT Statement]] specifies that authors and editors should not use the terms "single-blind", "double-blind", and "triple-blind"; instead, reports of blinded RCT should discuss "If done, who was blinded after assignment to interventions (for example, participants, care providers, those assessing outcomes) and how."<ref name="Moher-2010"/>

Historical control trials (HCT) exploit the data of previous RCTs to reduce the sample size; however, these approaches are controversial in the scientific community and must be handled with care.

传统上，盲法随机对照试验分为“单盲”、“双盲”或“三盲”；然而，2001年和2006年的两项研究表明，这些术语对不同的人有不同的含义。2010年CONSORT 声明明确指出，作者和编辑不应使用”单盲”、”双盲”和”三盲”等术语；相反，关于盲法 RCT 的报告应讨论”如果完成，干预分配后谁被“蒙面”了(例如，参与者、护理提供者、评估结果的人员)以及其原因”。

 

 

RCTs without blinding are referred to as "unblinded",<ref name="Marson-2007">{{Cite journal  |vauthors=Marson AG, Al-Kharusi AM, Alwaidh M, Appleton R, Baker GA, Chadwick DW, etal | title = The SANAD study of effectiveness of valproate, lamotrigine, or topiramate for generalised and unclassifiable epilepsy: an unblinded randomised controlled trial | journal = [[The Lancet|Lancet]] | volume = 369 | issue = 9566 | pages = 1016–26 | year = 2007 | doi = 10.1016/S0140-6736(07)60461-9 | pmid = 17382828 | pmc = 2039891 }}</ref> "open",<ref name="Chan-1995">{{Cite journal |vauthors=Chan R, Hemeryck L, O'Regan M, Clancy L, Feely J | title = Oral versus intravenous antibiotics for community acquired lower respiratory tract infection in a general hospital: open, randomised controlled trial | journal = [[BMJ]] | volume = 310 | issue = 6991 | pages = 1360–2 | year = 1995 | pmid = 7787537 | pmc = 2549744 | doi=10.1136/bmj.310.6991.1360}}</ref> or (if the intervention is a medication) "[[Open-label trial|open-label]]".<ref name="Fukase-2008">{{Cite journal | author = Fukase K, Kato M, Kikuchi S, Inoue K, Uemura N, Okamoto S, Terao S, Amagai K, Hayashi S, Asaka M; Japan Gast Study Group | title = Effect of eradication of Helicobacter pylori on incidence of metachronous gastric carcinoma after endoscopic resection of early gastric cancer: an open-label, randomised controlled trial | journal = Lancet | volume = 372 | issue = 9636 | pages = 392–7 | year = 2008 | doi = 10.1016/S0140-6736(08)61159-9 | pmid = 18675689 | hdl = 2115/34681 | s2cid = 13741892 | url = https://eprints.lib.hokudai.ac.jp/dspace/bitstream/2115/34681/1/asaka.pdf | hdl-access = free }}</ref> In 2008 a study concluded that the results of unblinded RCTs tended to be biased toward beneficial effects only if the RCTs' outcomes were subjective as opposed to objective;<ref name="Wood-2008"/> for example, in an RCT of treatments for [[multiple sclerosis]], unblinded neurologists (but not the blinded neurologists) felt that the treatments were beneficial.<ref name="Noseworthy-1994">{{Cite journal |vauthors=Noseworthy JH, Ebers GC, Vandervoort MK, Farquhar RE, Yetisir E, Roberts R | author-link1=John H. Noseworthy|title = The impact of blinding on the results of a randomized, placebo-controlled multiple sclerosis clinical trial | journal = Neurology | volume = 44 | issue = 1 | pages = 16–20 | year = 1994 | url = http://www.neurology.org/cgi/content/abstract/44/1/16 | pmid = 8290055 | doi=10.1212/wnl.44.1.16| s2cid=2663997}}</ref> In pragmatic RCTs, although the participants and providers are often unblinded, it is "still desirable and often possible to blind the assessor or obtain an objective source of data for evaluation of outcomes."<ref name="Zwarenstein-2008"/>

没有盲法的随机对照试验被称为“未盲法”，也称“开放”，或者(如果干预是一种药物)“开放标签”。2008年的一项研究得出结论，只有当随机对照试验的结果是主观的而不是客观的时候，非盲法随机对照试验的结果往往偏向于有益的结果；例如，在RCT多发性硬化症的治疗中，未盲的神经学家认为治疗是有益的。在实用的随机对照试验中，尽管参与者和提供者往往是非盲的，但是”仍然需要并且往往可能使评估者“蒙面”，以获得评估结果的客观数据来源”。

== Analysis of data ==

== Analysis of data ==

* For time-to-event outcome data that may be [[Censoring (statistics)|censored]], [[survival analysis]] (e.g., [[Kaplan–Meier estimator]]s and [[Cox proportional hazards model]]s for time to [[coronary heart disease]] after receipt of [[Hormone replacement therapy (menopause)|hormone replacement therapy in menopause]]<ref name="Rossouw-2002">{{Cite journal | author = Rossouw JE, Anderson GL, [[Ross Prentice|Prentice RL]], LaCroix AZ, Kooperberg C, Stefanick ML, Jackson RD, Beresford SA, Howard BV, Johnson KC, Kotchen JM, Ockene J; Writing Group for the Women's Health Initiative Investigators | title = Risks and benefits of estrogen plus progestin in healthy postmenopausal women: principal results from the Women's Health Initiative randomized controlled trial | journal = [[J Am Med Assoc]] | volume = 288 | issue = 3 | pages = 321–33 | year = 2002 | pmid = 12117397 | doi = 10.1001/jama.288.3.321 | s2cid = 20149703 | url = https://escholarship.org/content/qt3mr6f93p/qt3mr6f93p.pdf?t=prll4c | doi-access = free }}</ref>) is appropriate.

* For time-to-event outcome data that may be [[Censoring (statistics)|censored]], [[survival analysis]] (e.g., [[Kaplan–Meier estimator]]s and [[Cox proportional hazards model]]s for time to [[coronary heart disease]] after receipt of [[Hormone replacement therapy (menopause)|hormone replacement therapy in menopause]]<ref name="Rossouw-2002">{{Cite journal | author = Rossouw JE, Anderson GL, [[Ross Prentice|Prentice RL]], LaCroix AZ, Kooperberg C, Stefanick ML, Jackson RD, Beresford SA, Howard BV, Johnson KC, Kotchen JM, Ockene J; Writing Group for the Women's Health Initiative Investigators | title = Risks and benefits of estrogen plus progestin in healthy postmenopausal women: principal results from the Women's Health Initiative randomized controlled trial | journal = [[J Am Med Assoc]] | volume = 288 | issue = 3 | pages = 321–33 | year = 2002 | pmid = 12117397 | doi = 10.1001/jama.288.3.321 | s2cid = 20149703 | url = https://escholarship.org/content/qt3mr6f93p/qt3mr6f93p.pdf?t=prll4c | doi-access = free }}</ref>) is appropriate.

 

 

 

 

Regardless of the statistical methods used, important considerations in the analysis of RCT data include:

Regardless of the statistical methods used, important considerations in the analysis of RCT data include:

* Whether an RCT should be stopped early due to interim results.  For example, RCTs may be stopped early if an intervention produces "larger than expected benefit or harm", or if "investigators find evidence of no important difference between experimental and control interventions."<ref name="Moher-2010"/>

* Whether an RCT should be stopped early due to interim results.  For example, RCTs may be stopped early if an intervention produces "larger than expected benefit or harm", or if "investigators find evidence of no important difference between experimental and control interventions."<ref name="Moher-2010"/>

* The extent to which the groups can be analyzed exactly as they existed upon randomization (i.e., whether a so-called "[[intention-to-treat analysis]]" is used). A "pure" intention-to-treat analysis is "possible only when complete outcome data are available" for all randomized subjects;<ref name="Hollis-1999">{{Cite journal |vauthors=Hollis S, Campbell F | title = What is meant by intention to treat analysis? Survey of published randomised controlled trials | journal = [[Br Med J]] | volume = 319 | issue = 7211 | pages = 670–4 | year = 1999 | pmid = 10480822 | pmc = 28218 | doi=10.1136/bmj.319.7211.670}}</ref> when some outcome data are missing, options include analyzing only cases with known outcomes and using [[Imputation (statistics)|imputed]] data.<ref name="Moher-2010"/> Nevertheless, the more that analyses can include all participants in the groups to which they were randomized, the less bias that an RCT will be subject to.<ref name="Moher-2010"/>

* The extent to which the groups can be analyzed exactly as they existed upon randomization (i.e., whether a so-called "[[intention-to-treat analysis]]" is used). A "pure" intention-to-treat analysis is "possible only when complete outcome data are available" for all randomized subjects;<ref name="Hollis-1999">{{Cite journal |vauthors=Hollis S, Campbell F | title = What is meant by intention to treat analysis? Survey of published randomised controlled trials | journal = [[Br Med J]] | volume = 319 | issue = 7211 | pages = 670–4 | year = 1999 | pmid = 10480822 | pmc = 28218 | doi=10.1136/bmj.319.7211.670}}</ref> when some outcome data are missing, options include analyzing only cases with known outcomes and using [[Imputation (statistics)|imputed]] data.<ref name="Moher-2010"/> Nevertheless, the more that analyses can include all participants in the groups to which they were randomized, the less bias that an RCT will be subject to.<ref name="Moher-2010"/>

* Whether [[subgroup analysis]] should be performed.  These are "often discouraged" because [[multiple comparisons]] may produce false positive findings that cannot be confirmed by other studies.<ref name="Moher-2010"/>

* Whether [[subgroup analysis]] should be performed.  These are "often discouraged" because [[multiple comparisons]] may produce false positive findings that cannot be confirmed by other studies.<ref name="Moher-2010"/>

Has not been applied to all members of a unique group of people (e.g. the population of a whole country, all employees of a unique organisation etc.)

* 这些组在多大程度上可以完全按照随机化时的状态进行分析(即，是否使用了所谓的“意向治疗分析”)。一项“纯”意向治疗分析“只有在获得所有随机受试者的完整结果数据时才有可能”；当一些结果数据缺失时，选项包括仅分析具有已知结果的病例和使用估算数据。然而，分析越能包括他们被随机分组的所有参与者，RCT受到的偏见就越少。

 

并不适用于一个特殊群体的所有成员(例如:。整个国家的人口，一个独特组织的所有雇员等)

== Reporting of results ==

== Reporting of results ==