1. Study Designs
Part One
High Score Centre
Khadiga Mohammed, BCPS 2015, MSc
Clinical Pharmacy 2016
By: khadiga Mohammed
BCPS 2015, MSc Clinical Pharmacy 2016
August 2016
2. August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
If Valproic acid cause alopecia or not?
3. August 2016
Khadiga Mohammed, BCPS 2015, MSc
Clinical Pharmacy 2016
Past Present Future
NSAIDs and AKI
ProspectiveRetrospective
Prospective Vs Retrospective Studies
4. August 2016
Khadiga Mohammed, BCPS 2015, MSc
Clinical Pharmacy 2016
NSAIDs and AKI
Present Future
Experimental
Observational
Experimental Vs Observational studies
Study Vs Control group
Study
group
Control
group
5. August 2016
Khadiga Mohammed, BCPS 2015, MSc
Clinical Pharmacy 2016
Bias Confounder
Bias Vs Confounder
1. Selection bias
3. Observational or information bias
2. Recall bias
4. Interviewer bias
5. Misclassification bias:
6. Bias in Study Design
Definition: Systematic, nonrandom variation in study methodology
and conductance, ultimately introducing error in outcome
interpretation. Bias can occur in all aspects of the study design.
Examples of bias
Selection bias: An error in the selection of or sampling of individuals for
a clinical study.
Observational or information bias: An error in the recording of
individual factors of a study.
Recall bias: Classic example: Studies of birth defects secondary to
medications.
Interviewer bias: Classic example: Interviews are not conducted in a
uniform manner (or by the same person) for all study participants.
Misclassification bias:
i. Differential
ii. Non-differential
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
7. Controlling for bias
1. Design: For example, selection of study
population.
2. Means of collecting data.
3. Sources of information (regarding disease
and exposure).
Analysis: May be difficult to interpret ×
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
8. Confounding in Study Design
A variable that affects the independent or dependent
variable, altering the ability to determine the true effect
on the measured outcome These factors may hide or
exaggerate a true association.
Controlling for confounding:
1. During the design of a study
i. Randomization
ii. Restriction
iii. Matching
2. Analysis
i. Stratification
ii. Multivariate analysis
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
9. Validity in Study Design
Internal validity
Validity within the confines of the study methods
Does the study design adequately and appropriately
test/measure what it purports?
Does the study adequately and appropriately address bias,
confounding.
External validity
Validity related to generalizing the study results outside the
study setting
Can the results be applied to other groups, patients, or
systems?
Addresses issues of generalizability and representativeness.
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
11. Question 1
A recently released statin is associated with less myopathy than other
currently available statins. After 2 years of use, a retrospective case-
control study was undertaken by the manufacturer after 20 different
reports of severe myopathy were sent to the U.S. Food and Drug
Administration’s (FDA’s) MedWatch program. Risk factors for statin-
induced myopathy were not assessed; however, both the cases and the
controls of this study had identical diagnostic evaluations and were
stratified according to the duration of statin use before the onset of
myopathy.
(1st part)
Which type of bias is this study design most susceptible to?
A. Confounding by indication.
B. Recall bias.
C. Diagnostic bias.
D. Misclassification.
August 2016
Khadiga Mohammed, BCPS 2015, MSc
Clinical Pharmacy 2016
12. Answer 1
Answer: B
Recall bias is always a potential concern for case-
control studies because of the amount of time that
passes between the study and the drug
“ingestion.” Because risk factors were not included
in the study design, this is of concern (Answer B is
correct). Although a study may be susceptible to
many types of bias, the other choices would not
pose as much risk (if any) compared with recall
bias (Answers A, C, and D are incorrect).
August 2016
Khadiga Mohammed, BCPS 2015, MSc
Clinical Pharmacy 2016
13. Question 2
(2nd part)
Which factor will be most affected by the type of
bias likely to occur in this study?
A. External validity.
B. Internal validity.
C. Assessment of exposure.
D. Number of patients needed for the study.
August 2016
Khadiga Mohammed, BCPS 2015, MSc
Clinical Pharmacy 2016
14. Answer 2
Answer: B
Internal validity is greatly jeopardized because the
study is not designed to protect against this
possible bias. In a sense, this design flaw
jeopardizes external validity (how well does a
study apply to other patients with this
condition/disease?), but a lack of internal validity is
most affected (Answer B is correct). The other
answers can be adequately controlled for in the
design and conduct of the study (Answers A, C,
and D are incorrect).
August 2016
Khadiga Mohammed, BCPS 2015, MSc
Clinical Pharmacy 2016
16. August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
Study designs
Descriptive
CASE REPORTS
CASE SERIES
Observational
Studies
Retrospective
Case control
Retrospective
Cohort
Prospective
Prospective
Cohort
Cross
sectional
Experimental
Studies
RCT
17. August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
1.Exposure:
2.Outcome:
3. Type:
4. How to start (grouping)
?
18. 1. Descriptive
CASE REPORTS/CASE SERIES
Document and Describe Experiences,
Novel Treatments, and Unusual Events.
Allows hypothesis generation that can be
tested with other study designs.
Note that the title does not state “study.”
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
19. • Hypotheses formed
the first step in
describing an important
clinical problem.
• Easy to perform.
• Inexpensive.
Advantages
• Does not establish
causality or association.
• Does not provide
explanation other than
conjecture.
Disadvantages
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
20. 2. OBSERVATIONAL STUDY DESIGNS
Design Does Not Involve Investigator
Intervention, only Observation.
It is essential to remember that
observational study designs investigate
associations—not, in most cases, causes.
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
21. August 2016
Khadiga Mohammed, BCPS 2015, MSc
Clinical Pharmacy 2016
Thalidomide &
Phocomelia
Past Present
Exposure
(Thalidomide)
Outcome
(Phocomelia)
Case-Control Study
Without Outcome
(Normal Babies)
Exposure
(Thalidomide)
Study group
Control group
22. A/ Case-Control Study
Retrospective studies
Study Exposure in Those with and without
the Outcome of Interest
Determine the association between
exposures/risk factors and
disease/condition.
Useful method (and perhaps the only
practical way) to study exposures in rare
diseases or diseases that take long periods
to develop
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
23. •can be conducted
quickly
•Inexpensive
•Allows investigation
of several exposures
Advantages
•Observational and
recall bias
•Confounding must be
controlled for.
•Selection bias
Disadvantages
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
24. August 2016
Khadiga Mohammed, BCPS 2015, MSc
Clinical Pharmacy 2016
Past Present Future
Prospective Cohort
Exposure Outcome
Isotretinoin & Depression
Without Exposure Outcome
26. B/ Cohort Study
Determines the association between
exposures/factors and disease/condition
development.
Study outcome of interest in those with and
without the exposure of interest.
Describes the incidence or natural history of a
disease/condition and measures it in time sequence
1. Retrospective (historical): Begins and ends in the
present but involves a major backward look to
collect information about events that occurred in
the past.
2. Prospective or longitudinal: Begin in the present
and progress forward, collecting data from
subjects whose outcomes lie in the future.
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
27. Retrospective Cohort
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
• can be conducted
quickly
•Inexpensive.
•no loss to follow-
up
Advantages
•Recall bias
•Confounding must
be controlled for.
•Only as good as the
data available.
Disadvantages
28. Prospective Cohort
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
• Control confounder.
• Easier to plan for data
collection
Advantages
• More expensive
• time-intensive
• loss of subject follow-
up
• Difficult to study rare
diseases
Disadvantages
29. August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
Cohort ( both type) you will
group the patients according to the
Exposure (Exposed & No exposed)
Case Control You will group your
patients according to the outcome (
group with outcome & group
without outcome)
30. C. Cross-sectional (prevalence study)
Identify the prevalence or characteristics
of a condition in a group of individuals.
Example: Prevalence of serious eye
disease and visual impairment in a north
London population.
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
31. August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
• Easy design
• snapshot in time
• Data collected by
questionnaire, or
available information.
Advantages
• Don’t study individual
subjects over time
• Difficult-to-study rare
condition
Disadvantages
32. August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
Experimental Studies causation
Observational Studies association
33. REMEMBER: In general, we do not prove or
show causality with observational studies,
but there is some general “guidance” to
consider when evaluating them. It is
important to recognize that, in many
situations, the conduct of studies to
establish causality is not possible, practical,
or ethical.
* That depend on the strength of the
association
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
34. 3. Experimental or interventional Studies
RANDOMIZED CONTROLLED TRIAL DESIGN
Experimental or interventional, investigator makes
intervention and evaluates cause and effect.
Examine etiology, cause, efficacy, using
comparative groups.
Some previous background information or studies
should exist to suggest that the intervention used
will likely be beneficial.
Design allows assessment of causality:
a. Sufficient cause
b. Necessary cause
c. Risk factor
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
35. •X , Z and M Y
Sufficient
cause
•X Y ( Y will not occur
if no X)
Necessary
cause
•X can cause Y or not.
•Smoking lung cancer
Risk factor
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
36. Minimizes bias through randomization
a. Randomization
b. Block randomization
c. Stratification
d. Cluster randomization
Treatment controls
a. Placebo controlled
b. Active controlled
c. Historical control
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
38. Blinding methods
a. Single-blind: Either subjects or investigators are
unaware of subject assignment to active/control.
b. Double-blind: Both subjects and investigators are
unaware of subject assignment to active/control.
c. Triple-blind: Both subjects and investigators are
unaware of subject assignment to active/control;in
addition, an analysis group is unaware.
d. Open-label: Everyone is aware of subject assignment
to active/control.
e. Double-dummy: Two placebos necessary to match
active and control therapies
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
39. August 2016
Khadiga Mohammed, BCPS 2015, MSc
Clinical Pharmacy 2016
A
B
Present Future
Outcome
Outcome
Parallel design
41. May use parallel or crossover design
a. Crossover provides practical and statistical
efficiency.
b. Crossover is not appropriate for certain types
of treatment questions (e.g., effect of
treatment on a disease that worsens quickly
over time or worsens during the study period).
Factorial design: Designed to answer two
separate research questions in a single group
of subjects
Examples: Comparison of two drugs.
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
43. OTHER ISSUES TO CONSIDER IN
CONTROLLED TRIALS
1. Subgroup Analysis
Important part of controlled clinical trials (if
set a priori)
Many times, they are overused and over
interpreted, leading to unnecessary research,
misinterpretation of results, and/or suboptimal
patient care.
Many potential pitfalls in identifying and
Problems with sample size (power),
classification.
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
44. August 2016
Khadiga Mohammed, BCPS 2015, MSc
Clinical Pharmacy 2016
1.BP
2.Death
3.MI
4.stroke
5. cardiac arrest
6. heart failure
There is 70% reduction
in composite end point
Composite End Points
45. 2. Composite End Points:
Often, the impression is that this practice is not a
good practice.
The primary end point is one of the most
important decisions to make in the design of a
clinical study.
A composite end point combines several end
points.
Advantage:
a. No single primary outcome
b. To alleviate problems of multiple testing
c. To increase number of events, which decreases
sample size and cost to the investigator
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
46. What are the problems?
• Difficulties in interpreting.
• Dilution of effects
• “Averaging” of overall effect
• Should all end points be weighed the
same, or should death “weigh” more?
The results for each individual end point
should be reported together with the results
for the composite.
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
47. August 2016
Khadiga Mohammed, BCPS 2015, MSc
Clinical Pharmacy 2016
Surrogate End Points
BP Stroke
Primary end point Secondary end point
LDL Stroke
Primary end point Secondary end point
48. 3. Surrogate End Points
Parameters thought to be associated with
clinical outcomes
LDL-C reduction and cardiovascular death
reduction:
i. Statins: Yes
ii. Hormone replacement therapy: No
Surrogate outcomes do not always
predict clinical outcomes.
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
49. Superiority Versus Equivalence Versus Non
inferiority
1. A superiority trial is designed to detect a difference
between experimental treatments. This is the typical
design in a clinical trial.
2. An equivalence trial is designed to confirm the
absence of a meaningful difference(s) between
treatments, neither better nor worse (both directions).
One example is a bioequivalence trial.
3. A non inferiority trial is designed to investigate
whether a treatment is not clinically worse (not less
effective than stated margin, or inferior) than an existing
treatment.
a. It may be the most effective, or it may have a similar
effect.
b. Useful when placebo administration is not possible for
ethical reasons.
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
50. August 2016
Khadiga Mohammed, BCPS 2015, MSc
Clinical Pharmacy 2016
literature review SYSTEMATIC REVIEW META-ANALYSIS
NSAIDs and AKI
51. SYSTEMATIC REVIEW/META-
ANALYSIS
Systematic Review:
Summary that uses explicit methods to
perform a comprehensive literature search,
critically appraise it, and synthesize the
world literature on a specific topic.
Differs from a standard literature review:
The study results are more comprehensively
synthesized and reviewed.
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
52. Meta-analysis
Systematic review that uses mathematical/
statistical techniques to summarize the results
of the evaluated studies
2. These techniques may improve on the
following:
a. Calculation of effect size
b. Increase in statistical power
c. Interpretation of disparate results
d. Reduction in bias
e. Answers to questions that may not be
addressable with individual studies
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
53. Elements of trial methodology
a. Research question
b. Identification of available studies
c. Criteria for trial inclusion/exclusion
d. Data collection and presentation of findings
e. Calculation of summary estimate: Ideally
with Forest plot.
f. Assessment of heterogeneity
i. Statistical heterogeneity
ii. chi-squared and Cochran are common tests
for heterogeneity.
g. Assessment of publication bias: Funnel plot
August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
56. August 2016 Khadiga Mohammed, BCPS 2015, MSc Clinical Pharmacy 2016
Publication bias occurs when
results of published studies
are systematically different
from results of unpublished
studies. ( All published will
be in when direction)