2. Objectives
What are randomized controlled trials (RCTs)?
Why we do randomized trials?
How to randomize?
Types of studies
Evidence hierarchy
RCT: Definition
Steps in conducting RCT
Trial monitoring
Ethical considerations
Conclusions
Outline
3. Types of studies
1. Observational studies
a. Descriptive studies
b. Analytical studies
(i) Ecological
(ii) Cross-sectional
(iii) Case-control
(iv) Cohort
2. Experimental/Intervention
studies
a. Randomized controlled
trials*
b. Field trials
c. Community trials
*RCTs are a subset of possible experimental designs
4.
5. " An epidemiological experiment in which subjects in
a population are randomly allocated into groups,
usually called study and control groups to receive and
not receive an experimental preventive or therapeutic
procedure, maneuver or intervention"
-John M Last,2001
Definition
6. Designing a protocol
Selecting reference and experimental population
Randomization
Intervention
Follow up
Outcome analysis
Publishing
Steps in RCT
7. Purpose of randomization is to make the treatment groups
comparable
Ensures that only difference in groups is due to trial
treatments
Why Randomization?
8. The process by which each subject has the same chance of
being assigned to either intervention or control.
Must be purely by chance
Each group is a random sample of eligible patients, so both
are representative of that same population
What is random allocation?
9. Inclusion and exclusion criteria are the conditions that must
be met in order to participate in a clinical trial
Age
Gender
The type and stage of a disease
Treatment history
Any other medical conditions
Inclusion and exclusion criteria
10. Need to separate the person who generates allocation from
those who assess eligibility
Third party schemes
Telephone randomization service
Pharmacy randomization
Web-based service?
Envelopes
Serially numbered, sealed and opaque
Who should randomize?
12. Simple Randomization
Participants have an equal chance of being allocated to
different treatment groups
This method increases statistical power and meets the
assumption of equipoise in the randomly allocated groups
13. Unequal allocation randomization means randomly
assigning participants into disproportionately sized groups
The acceptable ratios for unequal allocation are 2:1, 3:1, and
4:1 controls to cases
This method is useful for studying rare outcomes, adverse
events, or emerging therapies
However equipoise is not possible
Unequal Allocation
Randomization
14. Randomly assigning participants to treatment groups based
on predefined and objective characteristics (strata e.g. age
gender)
Each stratum is randomly allocated to treatment groups.
Stratified Randomization
15. For smaller studies
Participant are randomly assigned to treatment groups in
small "blocks" of four or six participants
Ensures that there are equally sized groups
Groups meets the assumption of equipoise
Blocked Randomization
16. Essentially the right thing to do
Try not to do it in front of the patient
OK for big trials
For small trials, such ‘simple randomization’ can lead to
imbalance in group sizes
Toss a coin
17. If 30 patients are in a trial randomized using coin tossing
there is a 14% chance of 15:15 split
For 16:14 chance is 27%
‘Worse’ than 20:10 is 10%
Example: trial with 30 patients
18. Table of Random numbers
Computer generated list
According to date of birth (odd or even years)
The number of their hospital records
The date at which they are invited to participate in the study
(odd or even days)
Alternatively into the different study groups
19. Blinding requires placebo or use of alternate treatment that
cannot be distinguished from treatment
Blinding is done to minimize participant or observer bias
Unblinded (cannot conceal randomization, e.g., surgical
interventions)
Single blinding (observer but not participant knows the arm of
randomization, e.g., cluster-level trials)
Double blinding (neither observer or participant know the arm of
randomization)
Complete blinding: Everyone involved in the study blinded to
treatment
Blinding
21. Trial Monitoring
Trials must be approved by and monitored by Institutional
Review Boards (IRBs) for ethics and safety
Trials should have an independent monitoring system to
periodically review data and ensure participant safety
Data monitoring committee (DMC) or Data Safety and
Monitoring Board (DSMB) should have the authority to
terminate or change the trial procedures
Trials should report all adverse events, especially serious
adverse events, and unexpected events
22. It can be unethical to deny a new treatment to the
placebo group
“Equipoise” a genuine uncertainty or doubt about
whether one intervention or treatment is superior to
another
Protection of the study participants (including physical,
mental and social well being) is the most important
responsibility of the researcher
The protection of the vulnerable population (whose
decision–making capacity is impaired or diminished)
Informed consent
Ethical issues in randomized
trials
23. RCTs
Unbiased distribution of
confounders
Blinding more likely
Randomisation facilitates
statistical analysis
Expensive: time and
money
Volunteer bias
Ethically problematic at
times
Advantages Disadvantages
24. The trial should ideally reflect real-world conditions
Two groups that are comparable and free from bias
RCT is gold-standard in terms of identifying causality
Need to weigh theoretical advantages against practicalities
Randomization method
Unpredictable
Balanced
Simple
Summary
Editor's Notes
Study designs
Centre for Evidence Based Medicine, Oxford
http://www.cebm.net/index.aspx?o=1039