STUDY DESIGNS

By : Tahani Alghamdi
CLINICAL RESEARCH
 ASSOCIATION & CAUSATION

qASSOCIATION:
-When two variables are related, we say that there is association between them.

qCAUSATION:
-One variable has a direct influence on the other, this is called a causal relationship.

-If two variables are causally related, it is possible to conclude that changes to the
explanatory variable X, will have a direct impact on Y.
 VALIDITY

q VALIDITY:
A. Internal Validity:To what degree does a study appropriately test and answer the
questions being asked and measure what is claimed to be measured?
“addresses issues of bias, confounding, and measurement of endpoints.”
It directly affects external validity.
B. External Validity: Presuming internal validity, this assesses whether the results
can be extrapolated to the general population, to other groups, patients, or
systems.

-Validity is most often affected by introduction of some sort of systemic error or

bias.
 ERRORS VERSUS BIAS

qErrors are mistakes that do not systematically under- or overestimate effect

Size.

qBiases are systematic errors/flaws in study design that lead to incorrect results.

üThe best way to minimize bias is through proper study design (e.g., randomization
, inclusion/exclusion criteria, blinding, using controls and objective outcome
measures)
 Tyaps of BIAS

Selection bias: the study in cleveland is not representative of the US

‫ اﻟدراﺳﺔ ﻓﻲ ﻛﻠﯾﻔﻼﻧد ﻟﯾﺳت ﻣﻣﺛﻠﺔ ﻟﻠوﻻﯾﺎت اﻟﻣﺗﺣدة‬: ‫اﻧﺣﯾﺎز اﻻﺧﺗﯾﺎر‬

Measurment bias: the research design does not match the reaserch
question
‫ ﺗﺻﻣﯾم اﻟﺑﺣث ﻻ ﯾﺗطﺎﺑق ﻣﻊ ﺳؤال اﻟﺑﺣث‬:‫اﻧﺣﯾﺎز اﻟﻘﯾﺎس‬

Expectancy bias - experimenter -expectancy effect , observ bias

the researcher's expectations effect the outcome of study
‫ ﺗؤﺛر ﺗوﻗﻌﺎت اﻟﺑﺎﺣث ﻋﻠﻰ ﻧﺗﺎﺋﺞ اﻟدراﺳﺔ‬- (‫ ﺗﺣﯾز اﻟﻣراﻗب‬- ‫ ﺗوﻗﻊ‬- ‫اﻟﺗﺣﯾز اﻟﻣﺗوﻗﻊ )ﺗﺄﺛﯾر اﻟﻣﺟرب‬
 Tyaps of BIAS

Social desirability bias : the tendency of respondents to answer question in

a manner that will be viewed favorably by others
‫ ﻣﯾل اﻟﻣﺟﯾﺑﯾن إﻟﻰ اﻹﺟﺎﺑﺔ ﻋﻠﻰ اﻟﺳؤال ﺑطرﯾﻘﺔ ﯾﻧظر إﻟﯾﮭﺎ اﻵﺧرون ﺑﺷﻛل إﯾﺟﺎﺑﻲ‬:‫ﺗﺣﯾز اﻟرﻏﺑﺔ اﻻﺟﺗﻣﺎﻋﯾﺔ‬

Observation bias : memory recall and information interviewer and misclassification

‫ اﺳﺗدﻋﺎء اﻟذاﻛرة وﻣﻘﺎﺑﻠﺔ اﻟﻣﻌﻠوﻣﺎت وﺗﺻﻧﯾﻔﮭﺎ اﻟﺧﺎطﺊ‬:‫ﻣﻼﺣظﺔ اﻟﺗﺣﯾز‬

Losses to follow up bias :if the researcher lost many subject in follow up the
subject who are in analysis are special subject
‫ إذا ﺧﺳر اﻟﺑﺎﺣث اﻟﻌدﯾد ﻣن اﻟﻣوﺿوﻋﺎت ﻓﻲ ﻣﺗﺎﺑﻌﺔ اﻟﻣوﺿوع اﻟذي ﯾﺧﺿﻊ ﻟﻠﺗﺣﻠﯾل ﻓﮭو ﻣوﺿو‬:‫ﺧﺳﺎﺋر ﻣﺗﺎﺑﻌﺔ اﻟﺗﺣﯾز‬
‫ع ﺧﺎص‬
 Tyaps of BIAS
Response and non response bias : subject answer what they wanted to say
subject not answer what they did not want to say
‫ ﻣوﺿوع اﻹﺟﺎﺑﺔ ﻣﺎ أرادوا ﻗوﻟﮫ اﻟﻣوﺿوع ﻻ ﯾﺟﯾب ﻋﻠﻰ ﻣﺎ ﻻ ﯾرﯾدون أن ﯾﻘوﻟوا‬:‫رد وﻋدم ﺗﺣﯾز اﺳﺗﺟﺎﺑﺔ‬

Reporting bias : if researchers find their hypothesis was wrong they don't
publish it
‫ ﻓﻠن ﯾﻧﺷروھﺎ‬، ‫ إذا وﺟد اﻟﺑﺎﺣﺛون أن ﻓرﺿﯾﺗﮭم ﻛﺎﻧت ﺧﺎطﺋﺔ‬:‫اﻹﺑﻼغ ﻋن اﻟﺗﺣﯾز‬

Recall bias : is a systematic error that occurs when participants do not remember
previous events or experiences accurately or omit details
‫ ھو ﺧطﺄ ﻣﻧﮭﺟﻲ ﯾﺣدث ﻋﻧدﻣﺎ ﻻ ﯾﺗذﻛر اﻟﻣﺷﺎرﻛون اﻷﺣداث أو اﻟﺗﺟﺎرب اﻟﺳﺎﺑﻘﺔ ﺑدﻗﺔ أو ﯾﺗﺟﺎھﻠون‬:‫ﺗذّﻛر اﻟﺗﺣﯾز‬
‫اﻟﺗﻔﺎﺻﯾل‬
 CONFOUNDING
üConfounders are “causes, other than the one studied, which may be linked to the
studied outcomes and/or the hypothesized cause.”

For example, coffee drinking causes pancreatic cancer. There is an association between
coffee drinking and smoking.
-The proposed cause is coffee drinking.
-The potential confounder is smoking, so investigators need to account for any
significant smoking differences among studied groups.
 BLINDING
qBLINDING: It helps minimize clinicians’ treating/assessing one group differently from another,
helps control for a placebo effect, and helps maximize equal patient compliance.

üCommon types of blinding are listed in the following:

A. Nonblinded trial: The investigator and subject know what treatment or intervention the
subject is receiving. This is commonly referred to as an open or open-label trial.

B. Single-blind trial: Someone (usually the patient) is unaware of what treatment or

intervention the subject is receiving.

C. Double-blind trial: Neither the investigator nor the subject is aware of what treatment or
intervention the subject is receiving
 BLINDING
D. Double-dummy trials: are used if one is comparing two different dosage forms
and doesn’t want the patient or investigator to know in which arm the patient is
participating.

üFor example, if one is comparing intranasal sumatriptan (Imitrex) to injectable

sumatriptan, one group would receive intranasal sumatriptan and a placebo
injection, while the other group would receive intranasal placebo and a
sumatriptan injection
TRIAL DESIGN
 TRIAL DESIGN
qProspective versus retrospective:

1. Prospective study: Subjects are followed forward in time from a specified time
point. Data are collected and outcomes or variables are measured and analyzed.

2. Retrospective study: Always begins and sometimes ends in the past (case report,
case series, case control, retrospective cohort) but may end in the present or
future (prospective cohort). The investigator(s) look(s) back in time to collect and
analyze data.
TRIAL DESIGN
 TRIAL DESIGN

1. Case report: (weakest) (not analytical or interventional)

2. Case series: (simply more patients than case reports) (not analytical or
interventional)

3. Cross-sectional studies: “survey characteristics of a population at a given time

and are particularly useful for measuring the prevalence of a disease or event.”

4. Case-control study: ( epidemiological or observational trial designs)(analytical)

Case control == recall bias
 TRIAL DESIGN
5. Cohort study: ( epidemiological or observational trial designs, outcomes or
follow-up studies) (analytical)
a. Retrospective cohort (exposure and end point occurred in the past)
b. Prospective cohort (exposure occurred in the past, end point in the future)
c. True prospective cohort (exposure in the present or future, end point in the
future)
Cohort == selection bias
6. Meta-analysis: is a statistical procedure for combining numerical data from
multiple separate studies

7. RCT Strongest for establishing causality (interventional)

How to recognize type of study from the question

1-How patient identified ? 2-Outcome of the study ? 3-Time period ?

cross sectional : cross sectional : cross sectional :

By location (Jeddah). Prevalence -‫اﻧﺗﺷﺎر‬ Not follow up

Case control : Case control : Prospective :

By disease(Lung cancer). OR - ‫ﻧﺳﺑﺔ اﻻﺣﺗﻣﺎﻻت‬ Look forward

Cohort : Cohort : Retrospective :

By Risk factor (Smoking) RR - ‫ﻧﺳﺑﺔ اﻟﺧطر‬ Look backward
The relative risk
(also known as risk ratio [RR]) is the ratio of risk of an event in one group
(e.g., exposed group) versus the risk of the event in the other group
(e.g., nonexposed group).

The odds ratio (OR)

is the ratio of odds of an event in one group versus the odds of the event in the
other group
TRIAL DESIGN
 TRIAL DESIGN
qSTUDY TYPE EXAMPLE:
üPredictors of surgical site infection after open lower extremity bypass (LEB)
revascularization
- Methods
Data was pulled from 35 hospitals for all patients who had LEB during a 3-year period. Cases of surgical
site infection (SSI) were identified and compared to those who did not develop a SSI (controls). An odds
ratio (OR) was calculated for various risk factors that might increase SSI risk.
- Statistical Data
Renal failure OR, 4.35; 95% Cl (3.45-5.47); P < .001
Hypertension OR, 4.29; 95% Cl (2.74-6.72); P < .001
BMI > 25 kg/m2 OR, 1.78; 95% Cl (1.23-2.57); P = .002
- Conclusion
Renal failure, hypertension, and BMI > 25 kg/m2 were all associated with an increased risk of SSI
TRIAL DESIGN
COHORT STUDY
 TRIAL DESIGN
qSTUDY TYPE EXAMPLE:
üStatin use and cognitive function in adults with type 1 diabetes.
- Methods
Patients with type 1 diabetes who were taking statins (exposed) were compared to those not
taking statins (not exposed) and followed for 7 - 12 years to see if statin use was associated
With cognitive impairment (outcome).
- Statistical Data
Statin use and odds of cognitive impairment OR 4.84; 95% Cl (1.63-14.44); P = 0.005
- Conclusion
In type 1 diabetes, patients on statins were more likely to develop cognitive impairment
compared to those who did not take statins.
 TRIAL DESIGN

qCROSS-SECTIONAL SURVEY
Estimates the relationship between variables and outcomes (prevalence)
at one particular Time (cross-section) in a defined population.
 TRIAL DESIGN

qCASE REPORT AND CASE SERIES

Describes an adverse reaction or a unique condition that appears in a
single patient (case report) or few patients (case series).
 TRIAL DESIGN
RANDOMIZED CONTROLLED TRIAL
üCompares an experimental treatment to a control (placebo or existing treatment) to
determine which is better; subjects with the desired characteristics are carefully selected to
exclude patients with characteristics that may also influence outcome(exclusion criteria) and
then are randomized and sometimes blinded

üRCT is considered to be the gold standard in evaluating the safety and efficacy of an
intervention.

üRCTs are required by FDA as part of new drug application

üRCTs are always prospective , patient in the study group are followed after the intervention
to evaluate changes in the clinical outcomes
 TRIAL DESIGN
TYPES OF RCT:
1- Parallel:
Subjects are randomized to the treatment or control arm for the entire study

qEXAMPLE: Angiotensin-neprilysin inhibition versus enalapril in heart failure

-Methods
Patients with heart failure were randomized in a double-blind manner to receive a new drug (angiotensin-
neprilysin inhibitor) or the current standard of care (enalapril). The effectiveness of the treatments was m
easured as a combination (composite) of death from cardiovascular causes or hospitalization for heart
failure.

-Conclusion
The new drug demonstrated a statistically significant benefit in reducing death and hospitalizations due to
heart failure. The null hypothesis (that there was no difference between the two arms) was rejected.
TRIAL DESIGN
 TRIAL DESIGN
TYPES OF RCT:
2- Crossover:
üPatients are randomized to one of two sequential treatments:
-Group 1 - Receive treatment A first, then crossover (change) to treatment B.
-Group 2 - Receive treatment B first, then crossover (change) to treatment A.

üUsed when there is wide, interpatient variability. “Since each patient serves as his or her
own control, variation between treatment groups is minimized.”

üTo prevent carryover effect, “atypical washout period should last at least 5 half-lives of the
study drug or its active metabolite.”
 TRIAL DESIGN
qEXAMPLE: Crossover Comparison of Timolol and Latanoprost in Chronic Primary
Angle-closure Glaucoma.
-Methods
Patients with chronic primary angle-closure glaucoma were randomized after surgery to
latanoprost or timolol. Three months after treatment with the first drug, the second drug was
substituted.Intraocular pressure (IOP) was recorded before starting and at 3 and7 months in
both groups.
-Statistical Data
Decrease IOP from baseline was 8.2 ± 2 mm Hg with latanoprost
(P<0.001) and 6.1 ±1.7 mmHg with timolol (P = 0.01).
-Conclusion
Latanoprost was associated with a greater decrease in IOP from baseline than timolol.
TRIAL DESIGN
 TRIAL DESIGN

qMETA-ANALYSIS:
Combines results from multiple studies in order to develop a conclusion that has greater
Statistical power than is possible from the individual smaller studies.
 TRIAL DESIGN

qSYSTEMATIC REVIEW ARTICLE

Summary of the clinical literature that focuses on a specific topic or question (e.g., treatment
options for a condition); begins with a question followed by literature search, then the
Information is summarized and sometimes includes a meta-analysis to synthesize results
CLINICAL TRIAL PHASES
CLINICAL TRIAL PHASES
 QUESTIONS
Question1:
A researcher was interested in examining the association between postmenopausal hormone
replacement therapy (HRT) and development of heart disease. All women who were
characterized as postmenopausal were approached regarding their interest in participating in
the study by answering a questionnaire annually regarding their medication use and medical
conditions. Of the 16,168 women who provided consent, the average length of follow-up was
12.5 years (range, 6 to 16 years). Which of the following best describes the study design?
(A) Case-control study
(B) Prospective cohort study
(C) Randomized controlled trial
(D) Meta-analysis
 ANSWER
Answer B (Prospective cohort study) is correct because postmenopausal women were
identified based on exposure (medications they were taking, i.e., whether or not they were
taking HRT) as is done in cohort studies.

Answer A is incorrect because,for case-control studies, subjects are identified based on

disease (heart disease in this case) rather than exposure (HRT), which was not the setup for
This study.

Answer C is incorrect because patients were not randomized to an intervention.

Answer D is incorrect because meta-analyses include multiple studies, which is not the case in
this example.
 QUESTIONS
Question 2:
Which of the following would be appropriate for a crossover design study?

(A) Effects of Drug A versus Drug B on hypertension in 100 patients

(B) Effects of varenicline (Chantix) compared to placebo on smoking cessation
(C) Effects of fl uticasone/salmeterol (Advair) and budesonide/formoterol (Symbicort) on
asthma exacerbations
(D) Effects of hydralazine and hydrochlorothiazide (Microzide) on all-cause mortality
 ANSWER
Answer A is correct (Effects of Drug A versus Drug B on hypertension in 100 patients).

Answer B is incorrect because it would be unethical to ask those who had stopped smoking in
the first part of the trial to restart smoking in order to obtain data for the second part of the
study.

Answer C is incorrect because crossovers are not good for treatment evaluation in unstable
diseases. Asthma severity may vary depending on seasons.

Answer D is incorrect because those who died in the fi rst part of the crossover trial could
not be evaluated during thesecond part of the trial
Thank you