STROBE FOR

U N D E R G R A D UAT E S

Emad Magdy Shawky

 AGENDA

Types of studies we will be confronted with

Important terminologies in the result section

Items of STROBE

Example to follow
WHY WE ARE DOING THIS ACTIVITY

All the physicians should

know how to explore the
power of evidence
Gregory E. Tasian et al. JASN doi:10.1681/ASN.2017111213
Observational studies
Many types of studies - right research design
depends on the question we ask

Observational studies
• Large proportion of research
• Can be valuable (e.g. AE) but also many
disadvantages (confounding, bias)

Without comparison group – descriptive:

(do not try to qualify the relationships but give us a
perspective of what is happening in the population,
prevalence or experience of a group)
• Case reports, case series, qualitative
studies, some cross-sectional studies
(surveys)

With comparison group - analytical

(attempts to qualify relationship between two factors
– effect of an intervention / exposure on an outcome)
• Cohort studies, case-control studies, some
cross-sectional studies

6
 Difference in analytical designs

Experimental studies:

• Researcher
manipulates exposure
by allocating Observational studies with
a comparison group:
participants to
Intervention (Exposure)
• Researcher simply
group
measures the exposure or
treatments of the groups

• These studies all include

matched groups of
participants

• They assess associations

between exposures and
outcomes

7
 Cohort studies

• Cohort = group of Roman soldiers

• Start with exposure (variable) then follow for
outcome

• Data are obtained from groups who have been

exposed or not exposed to the factor of
interest

• Best for study the effect of predictive risk

factors on an outcome

8
 Case-control studies

• Patients with a certain outcome or disease and an appropriate

group of controls without the outcome or disease are selected
(usually with careful consideration of choice of
controls, matching)

• Information is obtained on whether the participants have been

exposed to the factor under investigation

9
 Cross-sectional studies
• Examine the relationship between diseases
(or other health-related characteristics) and
other variable of interest as they exist in a
defined population at one particular time
(outcomes and exposures are both
measured at the same time)

• Best for quantifying the prevalence of a

disease or risk factor, and for quantifying the
accuracy of a diagnostic test

10
 STROBE

Grimes, DA, Schulz KF. An overview of clinical research: 11

the lay of the land. Lancet 2002; 359; 57-61.
 The Problem
Most studies in medicine exhibit serious weaknesses due to issues of
reporting. Inadequate and poor reporting practices restrict
generalizability and implementation of results and subsequently the
clinical and scientific utility of such studies is lost . To aid reporting in
epidemiology, the STROBE (Strengthening the Reporting of Observational
Studies in Epidemiology) guidelines was developed to guide researchers
working on observational studies.
 Risk
Can this be isolated from
the other RFs or personal
characteristics?

Are they representative?

Outcome
Is it measurable?
 Risk
Confounding Be
factor prospective
Disease Adjust the
modifying statistics
factor

Sample
size
calculation Outcome
Control
group Relative Risk Absolute
Odds
Risk
Confounders are factors that distort the association between a predictor (independent
variable) and outcome (dependent variable).
For example, a study may find that drinking coffee have a higher chance of getting lung cancer. Hence,
does this mean that we should not drink coffee so that we reduce our chance of getting lung cancer?
If you take a closer look at what is being done in the study, perhaps you may have realized coffee drinkers
tend to be smokers as well. It is well known and established that smoking increases the chance of having
lung cancer (Do read Doll’s paper, which establishes that smoking is a predictor of lung cancer).
In this case, smoking is a confounder that causes coffee drinking to be associated with lung cancer. If we
remove this confounder, coffee drinking may no longer associated with lung cancer (and we can drink
coffee in peace again). These relationship is explained in the diagram below
Disease modification Using the same example If the study found that the relation of
coffee drinking to lung cancer is different from male to female his means that gender is a diseased
modifying factor not a confounding factor
RISK MEASUREMENT

• Relative Risk vs Odds ratio

• Absolute risk
R E L AT I V E R I S K V S O D D S R AT I O

• If we have an idea to test relationship between

smoking and development of ischemic heart
disease in a group of population
• We have some statistical methods to measure
 R E L AT I V E R I S K

• If we divide the group into smokers and nonsmokers, then get confirmed
that they are free from HT disease. Then followed them for 10 years, then
will report the percentage of occurrence of HT disease in each group

• 2 groups (400 each)

• Smokers: 40 of them developed (so the percentage 10%)

• Smokers: 20 of them developed (so the percentage 5%)

• So, the relative risk of developing disease is 10/5= 2

The risk of having heart diseases among smokers is 2

times the risk of having heart diseases among non-
smokers.
 O D D S R AT I O

• If we consider he same example

• Someone else have the same Q but do not have time to follow

• He explored the group for those who already HT diseased, he found

100 and start to search for another 100 matches who do not have
HT disease
• He asked them who is the smoker and who is not

• Found that 40 of the diseased are smokers, and 20 of the non-

diseased are smokers
 O D D S R AT I O

• Odds of being a smoker among patients with heart attack/ odds of being a smoker among
healthy people
• (40/60)/(20/80)= 2.67
Odds of being a smoker among patients with heart attack is 2.67 times the odds of
being a smoker among healthy people
Odds of having a heart attack among smokers / odds of having a heart attack among
nonsmokers
(40/20)/(60/80)=2.67
Odds of having a heart attack among smokers is 2.67 times the odds of having a heart
attack among nonsmokers
T E ST YO U U N D E R STA N D I N G ( M AT C H )

RR Case
control

Odds
Ratio
Cohort
OR

25
RR, AR

26
 STROBE Statement
• Guidance on how to report observational studies well
(which is rare!)
– Focus on 3 main study designs: cohort, case-control,
cross-sectional studies
• Published in Oct 2007: short paper and E&E
• Adopted by many journals

Find it on:
www.equator-network.org
www.strobe-statement.org

28
 STROBE
• Checklist with 22 items
– Heading (where in paper), item No
– Recommendation, divided into:
cohort, case-control, cross-sectional study - where different

29
Title and abstract:
1.a) Indicate the study’s design with a commonly used term
in the title or the abstract

b) Provide in the abstract an informative and balanced

summary of what was done and what was found

Introduction
Background/Rationale
2.Explain the scientific background and rationale for the
investigation being reported

Objectives
3. State specific objectives, including any prespecified
hypothesis

30
??
32
Methods:
Study Design
4. Present key elements of study design early in the
paper
(what design, what was compared, which controls and
why...etc)

Setting
5. Describe the setting, locations, and relevant dates,
including periods of recruitment, exposure, follow-up,
and data collection

33
Methods - continued
Participants
6.a) Cohort study:
• eligibility criteria
• sources and methods of participant selection
• follow-up methods

Case-control study:
• eligibility criteria
• sources and methods of case ascertainment and control
selection
• rationale for the choices of cases and controls

Cross-sectional study:
• eligibility criteria
• sources and methods of participant selection

34
Methods - continued
Participants
6.b) Cohort study:
For matched studies, give matching criteria and number of
exposed and unexposed

Case-control:
For matched studies, give matching criteria and the number of
controls per case

Variables
7. Clearly define all outcomes, exposures, predictors,
potential confounders, and effect modifiers. Give
diagnostic criteria, if applicable

35
Methods - continued
Data sources/measurement
8. For each variable of interest, give sources of data and
details of methods of assessment (measurement)
Describe comparability of assessment methods if
there is more than one group

* Give information separately for cases and controls in

case-control studies and, if applicable, for exposed
and unexposed in cohort and cross-sectional studies

36
Methods - continued
Bias
9. Describe any efforts to address potential sources of
bias

(ie systematic deviation of a result from the true value)

e.g.: recall bias, detection bias,
interviewer bias, selection bias

Very important
in observational
studies!

37
Methods - continued
Study size
10. Explain how the study size was arrived at

(should be large enough to arrive at a point estimate

with a reasonably narrow confidence interval)

Quantitative variables
11. Explain how quantitative variables were handled in the
analyses. If applicable, describe which groupings
were chosen and why

38
Methods - continued
Statistical methods
12.a) Describe all statistical methods, including those
used to control confounding

(≠bias, confounding: association true but caused

by something else)

b) Describe any methods used to examine subgroups

and interactions

c) Explain how missing data were addressed

39
Methods - continued
Statistical methods - continued
12.d) Cohort study:
If applicable, explain how loss to follow-up was addressed

Case-control:
If applicable, explain how matching of cases and controls
was addressed

Cross-sectional:
If applicable, describe analytical methods including
sampling strategy

e) Describe any sensitivity analyses

40
Thanks For Today

41
Results
Participants
13. a) Report numbers of individuals at each stage of study
- e.g., numbers potentially eligible, examined for
eligibility, confirmed eligible, included in the study,
completing follow-up, and analysed

b) Give reasons for non-participation at each stage

c) Consider use of a flow diagram

* Give information separately for cases and controls in case-control

studies and, if applicable, for exposed and unexposed in cohort
and cross-sectional studies

42
43
Results - continued
Descriptive data
14. a) Give characteristics of study participants
(e.g. demographic, clinical, social) and information on
exposures and potential confounders

b) Indicate number of participants with missing data for

each variable of interest

c) Cohort study:
Summarise follow up time (e.g. average and total
amount)

* Give information separately for cases and controls in case-control

studies and, if applicable, for exposed and unexposed in cohort and
cross-sectional studies

44
45
Results - continued
Outcome data
15. Cohort study:
Report numbers of outcome events or
summary measures over time

Case-control:
Report numbers in each exposure category, or summary
measures of exposure

Cross-sectional:
Report number of outcome events or summary
measures

* Give information separately for cases and controls in case-control

studies and, if applicable, for exposed and unexposed in cohort and
cross-sectional studies

46
Results - continued
Main results
16 a) Give unadjusted estimates and, if applicable,
confounder-adjusted estimates and their precision
(e.g. 95%CI). Make clear which confounders were
adjusted for and why they were included

b) Report category boundaries when continuous

variables were categorised

c) If relevant, consider translating estimates of

relative risk into absolute risk for a meaningful time
period

47
Report
category
boundaries
when
continuous
variables
were
categorised

48
CI

49
CI

50
RR, AR

51
AR vs RR
Results - continued
Other analyses
17. Report other analyses done, e.g. analyses of subgroups
and interactions, and sensitivity analyses

Discussion
Key results
18. Summarize key results with reference to study objectives

Limitations
19. Discuss limitations of the study, taking into account
sources of potential bias or imprecision. Discuss both
direction and magnitude of any potential bias

53
 Sensitivity analysis

Sensitivity analysis is useful in assessing how robust

an association is to potential unmeasured or
uncontrolled confounding.
The problem in observational studies
is the causality confirmation

54
Discussion - continued
Interpretation
20. Give a cautious overall interpretation of
results considering objectives, limitations,
multiplicity of analyses, results from similar
studies, and other relevant evidence

Generalisability
21. Discuss the generalisability (external validity) of the
study results

55
 Comparison with other studies
and explanation

Strength points and

Conclusion generalisability
56
Other information
Funding
22. Give the source of funding and the role of the
funders for the present study and, if applicable, for
the original study on which the present article is
based

More detailed explanation:

Vandenbroucke JP, von Elm E, Altman DA, et al. Strengthening the Reporting of
Observational Studies in Epidemiology (STROBE): Explanation and
Elaboration. PLoS Med 4(10): e297.doi:10.1371/journal.pmed.0040297

57