Discussion on Randomisation and Blinding

Slides:



Advertisements
Similar presentations
Appraisal of an RCT using a critical appraisal checklist
Advertisements

Presentation of BE data in a product dossier Drs. Jan Welink Training workshop: Training of BE assessors, Kiev, October 2009.
The Bahrain Branch of the UK Cochrane Centre In Collaboration with Reyada Training & Management Consultancy, Dubai-UAE Cochrane Collaboration and Systematic.
Role of Pharmaceutical Statistician March 10, 2009 The Role of the Pharmaceutical Statistician What can be improved? Per Larsson Head of Biostatistics.
DESIGNING EXPERIMENTS
Designing Clinical Research Studies An overview S.F. O’Brien.
Study Designs in Epidemiologic
Experimental design ITS class December 2, 2004 ITS class December 2, 2004.
The Bahrain Branch of the UK Cochrane Centre In Collaboration with Reyada Training & Management Consultancy, Dubai-UAE Cochrane Collaboration and Systematic.
Why to Randomize a Randomized Controlled Trial? (and how to do it) John Matthews University of Newcastle upon Tyne.
天 津 医 科 大 学天 津 医 科 大 学 Clinical trail. 天 津 医 科 大 学天 津 医 科 大 学 1.Historical Background 1537: Treatment of battle wounds: 1741: Treatment of Scurvy 1948:
Copyright © 2010, 2007, 2004 Pearson Education, Inc. Chapter 13 Experiments and Observational Studies.
Conducting systematic reviews for development of clinical guidelines 8 August 2013 Professor Mike Clarke
Elements of a clinical trial research protocol
Clinical Trials Medical Interventions
Obtaining Informed Consent: 1. Elements Of Informed Consent 2. Essential Information For Prospective Participants 3. Obligation for investigators.
Subject Selection and Recruitment David Wendler Department of Clinical Bioethics NIH, USA.
Evaluating Whether Interventions on the Use of Antibiotics Work to Decrease Resistance Chris Ford Regina Joice 1/18/08.
1 A Bayesian Non-Inferiority Approach to Evaluation of Bridging Studies Chin-Fu Hsiao, Jen-Pei Liu Division of Biostatistics and Bioinformatics National.
Clinical Trials Hanyan Yang
Methods to Control Extraneous Variables
Experiments and Observational Studies.  A study at a high school in California compared academic performance of music students with that of non-music.
Study Designs By Az and Omar.
Accredited Member of the Association of Clinical Research Professionals, USA Tips on clinical trials Maha Al-Farhan B.Sc, M.Phil., M.B.A., D.I.C.
Developing Research Proposal Systematic Review Mohammed TA, Omar Ph.D. PT Rehabilitation Health Science.
Critical Reading. Critical Appraisal Definition: assessment of methodological quality If you are deciding whether a paper is worth reading – do so on.
Copyright © 2010 Pearson Education, Inc. Chapter 13 Experiments and Observational Studies.
Chapter 13 Notes Observational Studies and Experimental Design
What is a Clinical Trial (alpha version) John M. Harris Jr., MD President Medical Directions, Inc.
Study Design. Study Designs Descriptive Studies Record events, observations or activities,documentaries No comparison group or intervention Describe.
What is a research proposal? Plan to test hypothesis using research Write research Proposal (plan) Carry out research Apply for grant/ethics Clinical.
Types of clinical studies Thomas Abraham. Three broad types of studies: used for different purposes 1. Observational (observe groups of people, gather.
Systematic Reviews.
Research Study Design. Objective- To devise a study method that will clearly answer the study question with the least amount of time, energy, cost, and.
Slide 13-1 Copyright © 2004 Pearson Education, Inc.
Evidence Based Medicine Meta-analysis and systematic reviews Ross Lawrenson.
Evidence-Based Journal Article Presentation [Insert your name here] [Insert your designation here] [Insert your institutional affiliation here] Department.
1 Statistical Review Dr. Shan Sun-Mitchell. 2 ENT Primary endpoint: Time to treatment failure by day 50 Placebo BDP Patients randomized Number.
LT 4.2 Designing Experiments Thanks to James Jaszczak, American Nicaraguan School.
Basics of Randomization.
Evidence-Based Medicine Presentation [Insert your name here] [Insert your designation here] [Insert your institutional affiliation here] Department of.
1 Copyright © 2011 by Saunders, an imprint of Elsevier Inc. Chapter 8 Clarifying Quantitative Research Designs.
Adaptive randomization
RevMan for Registrars Paul Glue, Psychological Medicine What is EBM? What is EBM? Different approaches/tools Different approaches/tools Systematic reviews.
DSBS Discussion: Multiple Testing 28 May 2009 Discussion on Multiple Testing Prepared and presented by Lars Endahl.
C HAPTER 5: P RODUCING D ATA DESIGNING EXPERIMENTS.
بسم الله الرحمن الرحيم جامعة أم درمان الإسلامية كلية الطب و العلوم الصحية - قسم طب المجتمع مساق البحث العلمي / الدفعة 21 Basics of Clinical Trials.
Critical appraisal of randomized controlled trial
1 Updates on Regulatory Requirements for Missing Data Ferran Torres, MD, PhD Hospital Clinic Barcelona Universitat Autònoma de Barcelona.
Critical Reading. Critical Appraisal Definition: assessment of methodological quality If you are deciding whether a paper is worth reading – do so on.
Study designs. Kate O’Donnell General Practice & Primary Care.
Objectives  Identify the key elements of a good randomised controlled study  To clarify the process of meta analysis and developing a systematic review.
C82MST Statistical Methods 2 - Lecture 1 1 Overview of Course Lecturers Dr Peter Bibby Prof Eamonn Ferguson Course Part I - Anova and related methods (Semester.
Sifting through the evidence Sarah Fradsham. Types of Evidence Primary Literature Observational studies Case Report Case Series Case Control Study Cohort.
1 Health and Disease in Populations 2002 Session 8 – 21/03/02 Randomised controlled trials 1 Dr Jenny Kurinczuk.
Penn CTSI Research Seminar Clinical Trials November 10, 2015 Vernon M. Chinchilli, PhD Distinguished Professor and Chair Department of Public Health Sciences.
How Empty Are Empty Reviews? The first report on the Empty Reviews Project sponsored by the Cochrane Opportunities Fund and an invitation to participate.
Evidence Based Practice (EBP) Riphah College of Rehabilitation Sciences(RCRS) Riphah International University Islamabad.
A Pharmacokinetic Drug Interaction Study of Drug-72 and Drug-12 Department of Mathematic & Statistics York University Yufeng Lin Xiaofeng Zhou.
CONSORT 2010 Balakrishnan S, Pondicherry Institute of Medical Sciences.
Levels of Evidence Dr Chetan Khatri Steering Committee, STARSurg.
European Patients’ Academy on Therapeutic Innovation Clinical Trial Designs.
Biostatistics Case Studies 2006 Peter D. Christenson Biostatistician Session 1: Demonstrating Equivalence of Active Treatments:
Randomized Control Trials: What, Why, How, When, and Where Mark L. Davison MESI Conference March 11, 2016 Department of Educational Psychology.
An Introduction to Clinical Trials and Pharmaceutical Statistics Workshop Robbie Peck University of Bath Student-Led Symposia 16 th Feb 2016.
CLINICAL PROTOCOL DEVELOPMENT
Statistical Approaches to Support Device Innovation- FDA View
Randomized Trials: A Brief Overview
Chapter 4: Designing Studies
Appraisal of an RCT using a critical appraisal checklist
Presentation transcript:

Discussion on Randomisation and Blinding DSBS Discussion: Randomisation Statistics for non-statisticians: Multiple Testing 20 May 2010 10-11 December 2008 Discussion on Randomisation and Blinding Lars Endahl Biostatistics Novo Nordisk A/S

DSBS Discussion: Randomisation Statistics for non-statisticians: Multiple Testing 20 May 2010 10-11 December 2008 Disclaimer The views that may be expressed in this discussion talk do not necessarily represent those of the speaker nor his affiliation! In short: I’m all for randomisation and blinding even though it may not appear this way in the following…

DSBS Discussion: Randomisation Statistics for non-statisticians: Multiple Testing Statistics for Non-statisticians: Hypothesis Testing 3 20 May 2010 Slide no 3 10-11 December 2008 12-13 March 2008 Randomised clinical trial: one of the simplest, most powerful and revolutionary forms of research Alenjandro Jadad-Bechara (2007)

Outline Who is Jadad? Is randomisation any concern for statisticians? DSBS Discussion: Randomisation Statistics for non-statisticians: Multiple Testing 20 May 2010 10-11 December 2008 Outline Who is Jadad? Is randomisation any concern for statisticians? Is blinding mostly a pestilence? Discussion

Who is Jadad? Physician from Oxford DSBS Discussion: Randomisation Statistics for non-statisticians: Multiple Testing 20 May 2010 Who is Jadad? 10-11 December 2008 Physician from Oxford Given name to the most widely used assessment tool for evaluating the quality of an randomised clinical trial Jadad et al. (1996). ”Assessing the quality of reports of randomized clinical trials: Is blinding necessary?”. Controlled Clinical Trials 17 (1): 1–12.

Jadad Score Jadad score (0-5 points) +1 point if trial randomised? DSBS Discussion: Randomisation Statistics for non-statisticians: Multiple Testing 20 May 2010 Jadad Score 10-11 December 2008 Jadad score (0-5 points) +1 point if trial randomised? +1 point if appropriate e.g. table of random numbers, computer generated etc. -1 point if inappropriate e.g. birth date +1 point trial double-blinded? e.g. identical treatments, double-dummy etc. e.g. tablet vs. injection +1 point if adequate description of dropouts i.e. number of and reason for dropouts stated

DSBS Discussion: Randomisation Statistics for non-statisticians: Multiple Testing Statistics for Non-statisticians: Hypothesis Testing 7 20 May 2010 Slide no 7 10-11 December 2008 12-13 March 2008 Randomised clinical trial: a type of experiment that any damn fool can analyse - and frequently does Stephen Senn (2007)

Show of Hands How many of you DSBS Discussion: Randomisation Statistics for non-statisticians: Multiple Testing 20 May 2010 Show of Hands 10-11 December 2008 How many of you have analysed a randomised clinical trial (RCT)? feel that the evidence from a RCT stands and falls with the randomisation? regard the randomisation as being the most important feature of the trial design? e.g. more important that parallel-group / cross-over patient population comparator drug duration of trial

DSBS Discussion: Randomisation Statistics for non-statisticians: Multiple Testing 20 May 2010 A key design feature? 10-11 December 2008 If randomisation is really a key feature of a trial design, why do all block-randomised two-armed 1:1 trials have a block size of four? and why is that a big secret? do statisticians rarely engage themselves in discussions on how a trial should be randomised? forced randomisation? block-randomisation? do we not document the details of the randomisation procedure in the report or publications

DSBS Discussion: Randomisation Statistics for non-statisticians: Multiple Testing 20 May 2010 10-11 December 2008 Is “how” important? Does it really matter how a trial was randomised, as long as we know that some kind of randomisation took place?

Features of randomisation? DSBS Discussion: Randomisation Statistics for Non-statisticians: Hypothesis Testing Statistics for non-statisticians: Multiple Testing 11 20 May 2010 Slide no 11 12-13 March 2008 10-11 December 2008 Features of randomisation? What are the most important features of a randomisation procedure? Ensure similar group sizes Ensure comparable groups Unpredictable Well-documented Easy to administer Is fool-proof Optimise use of trial drug Electronically founded

Do you agree? Do you agree with this statement? DSBS Discussion: Randomisation Statistics for Non-statisticians: Hypothesis Testing Statistics for non-statisticians: Multiple Testing 12 20 May 2010 Slide no 12 12-13 March 2008 10-11 December 2008 Do you agree? In a randomised trial, the only difference between the two groups being compared is that of most interest: the intervention under investigation. Mike Clarke, UK Cochrane Centre Do you agree with this statement? randomisation ensures causality???? If comparable groups was the aim of randomisation, why not use minimisation or dynamic allocation procedures

Why randomise? What are the key arguments for randomisation? DSBS Discussion: Randomisation Statistics for Non-statisticians: Hypothesis Testing Statistics for non-statisticians: Multiple Testing 13 20 May 2010 Slide no 13 12-13 March 2008 10-11 December 2008 Why randomise? What are the key arguments for randomisation? Essential for providing evidence Guidelines requires it Randomisation cannot do any harm Easier to randomise than try to explain why it may not be necessary Seals a sort of contract with the outside community (regulatory authorities) that recruitment is not manipulated

ICH-E9 and Randomisation DSBS Discussion: Randomisation Statistics for Non-statisticians: Hypothesis Testing Statistics for non-statisticians: Multiple Testing 14 20 May 2010 Slide no 14 12-13 March 2008 10-11 December 2008 ICH-E9 and Randomisation Randomisation provides a sound statistical basis for the quantitative evaluation of the evidence relating to treatment effects. page 9 In combination with blinding, randomisation helps to avoid possible bias in the selection and allocation of subjects arising from the predictability of treatment assignments. Details of the randomisation that facilitate predictability (e.g. block length) should not be contained in the trial protocol. page 10

DSBS Discussion: Randomisation Statistics for Non-statisticians: Hypothesis Testing Statistics for non-statisticians: Multiple Testing 15 20 May 2010 Slide no 15 Blinding 10-11 December 2008 12-13 March 2008 Blinding is done to avoid potential influence on the trial results caused by subjective behaviour, reporting, evaluation, data processing, and analysis due to personal preference of treatment Also the placebo effect of a trial may differ depending on what treatment the patient think he/she is receiving

Who? Who is most crucial to blind? patients investigators sponsor DSBS Discussion: Randomisation Statistics for Non-statisticians: Hypothesis Testing Statistics for non-statisticians: Multiple Testing 16 20 May 2010 Slide no 16 Who? 10-11 December 2008 12-13 March 2008 Who is most crucial to blind? patients investigators sponsor all equally important? depends on the trial design and drug?

Blind Data Review? How do we make a blind data review of DSBS Discussion: Randomisation Statistics for Non-statisticians: Hypothesis Testing Statistics for non-statisticians: Multiple Testing 17 20 May 2010 Slide no 17 Blind Data Review? 10-11 December 2008 12-13 March 2008 How do we make a blind data review of young –elderly phase 1 trial? blind the age of the subjects? how do we check inclusion in right age groups? PK trial with different chemical entities? or where the concentration level would reveal the drug

Analyse All Data? Is a blind data review really necessary? DSBS Discussion: Randomisation Statistics for Non-statisticians: Hypothesis Testing Statistics for non-statisticians: Multiple Testing 18 20 May 2010 Slide no 18 Analyse All Data? 10-11 December 2008 12-13 March 2008 Is a blind data review really necessary? even when blinding hinders the data cleaning? Why not just analyse all data as they are collected? New EMEA guidance on bioequivalence: “… the decision to exclude a subject from the statistical analysis must be made before bioanalysis… Exclusion of data cannot be accepted on the basis of statistical analysis or for pharmacokinetic reasons alone, because it is impossible to distinguish the formulation effects from other effects influencing the pharmacokinetics."

DSBS Discussion: Randomisation Statistics for Non-statisticians: Hypothesis Testing Statistics for non-statisticians: Multiple Testing 19 20 May 2010 Slide no 19 Where? 10-11 December 2008 12-13 March 2008 Is blinding equally important in all trials? confirmatory vs. exploratory superiority vs. non-inferiority vs. equivalence trials (trials with the aim to show no difference) parallel-group vs. cross-over trials phase 1 vs. phase 3 trials what about phase 2 trials? Does blinding play the same role regardless of the trial design and objectives?

ICH-E9 Guidance on Blinding DSBS Discussion: Randomisation Statistics for Non-statisticians: Hypothesis Testing Statistics for non-statisticians: Multiple Testing 20 20 May 2010 Slide no 20 12-13 March 2008 10-11 December 2008 ICH-E9 Guidance on Blinding If a double-blind trial is not feasible, then the single-blind option should be considered. page 9 In single-blind or open-label trials every effort should be made to minimise the various known sources of bias and primary variables should be as objective as possible. The sponsor should have adequate standard operating procedures to ensure that access to the treatment code is appropriately restricted during the process of cleaning the database prior to its release for analysis.

Blinding vs. Randomisation DSBS Discussion: Randomisation Statistics for Non-statisticians: Hypothesis Testing Statistics for non-statisticians: Multiple Testing 21 20 May 2010 Slide no 21 12-13 March 2008 10-11 December 2008 Blinding vs. Randomisation Is double-blinding and randomisation equally important for the quality of a clinical trial? 2 Jadad points each And are these the most important features determining the quality of a clinical trial? 4 out of 5 Jadad points

Statistics for non-statisticians: Multiple Testing DSBS Discussion: Randomisation Statistics for non-statisticians: Multiple Testing 20 May 2010 10-11 December 2008