STUDY

DESIGNS
DR. H A SFA PA RA C H A (PT)
Research Coordinator
DIPMR, DUHS

1
 OBJECTIVES:

At the end of the session, the participants will be able to know:

◾ What are Study Design?

◾ W hy we need research design?
◾ What are the Basic Study designs?
◾ What are types of Study Designs?
◾ Experimental Vs Observational Studies.

◾ Hierarchy of evidence
2
W H AT IS STUDY DESIGN??

“Research study design is a

framework, or the set of
methods and procedures
used to collect and analyze
data on variables specified in
a particular research
problem” [1]
3
 TYPES OF STUDY DESIGNS:

[Link]
 DIFFERENCE!!!

EXPERIMENTAL S T U DI ES OBSERVATIONAL S T U DI ES
◾ The investigators apply treatment to ◾ The investigators observe the subjects and
experimental Units and then proceeds to measures the variable of interest without
observe the effect of treatment on assigning any treatment.
experimental units. ◾ Easy to conduct
◾ N ot Easy to conduct ◾ Low Cost needed
◾ High cost N eeded ◾ Can be looking back to investigate
◾ Adopting and following the natural way from historical backgrounds
exposure to effect. ◾ Best when the exposure has negative
◾ Not good, when the exposure has adverse effect on
effect. subjects.
5
 C A S E REPORTS

◾ A case report is a descriptive study of a single individual[1]

◾ Case reports usually describe an unusual or novel occurrence and as such,
remain one of the
C O R N E R S T O N E S of medical progress and provide many new ideas in
medicine.[3]
◾ They potentially generate new research questions [4]

6
 C A S E REPORTS
STRENGTHS [ 5 ]
LIMITATIONS [5]
◾ Identification of new, abnormal, or
variant ◾ Lack of generalizability and
presentation of diseases. implications.
◾ Have significant educational ◾ Uncontrolled
value.
◾ Selection bias.
◾ Help in generating a hypothesis.
◾ Over-interpretation.
◾ Researching rare or uncommon
◾ Confidentiality.
disorders.
◾ Causes may have other
◾ In-depth narrative case studies
explanations.
7
◾ Flexible structure.
 C A S E –SERIES (CASE STUDY)
◾ Case studies involve multiple patients.[4]

◾ Case study research focuses on the contextual analysis of several events or

conditions and their
relationships.[4]

◾ Bias in a case series can be decreased through consecutive patient enrollment and
predefined
inclusion and exclusion criteria.[4]

8
 C A S E -SERIES

STRENGTHS [ 5 ] LIMITATIONS [ 5 ]
◾ Educational. ◾ Selection bias.
◾ It described the outcomes of novel
◾ Lack of control
treatments.
◾ The gained information can be used to ◾ D ifficult to compare different cases.
generate
hypotheses. ◾ Immediate follow-up.

◾ Provide strong evidence with multiple ◾ The result may not be generalized.
cases.
◾ Have a lower position on the hierarchy of
◾ Helpful in refining new techniques or
evidence
treatment
protocols.
◾ Identify the rare manifestations of a disease 9

or drug.
◾ Feasible study designs.
 C R O SS - S E C T I O N A L STUDY

◾ The cross-sectional study examines the association between exposures and outcomes on a
snap of time.
◾ This design can be
1. Descriptive (when dealing with prevalence or survey)
2. A nalytic (when comparing groups).
◾ The selection of participants in a cross-sectional study design depends on the predefined
inclusion and exclusion
criteria.
◾ Cross-sectional study design limits randomization.

10
 C R O SS - S E C T I O N A L STUDY
STRENGTHS [ 5 ]
LIMITATIONS [5]
◾ Fast and inexpensive.
◾ Difficult to derive causal
◾ Useful for planning monitoring and evaluation relationships.
of public health.
◾ Prone to certain types of biases.
◾ Efficient in studying rare diseases.
◾ The response rate is critical.
◾ It can assess multiple outcomes.
◾ The temporality of the design.
◾ Population-based surveys.
◾ There are seldom ethical
◾ Estimation of prevalence. difficulties.
◾ The baseline for a cohort study. ◾ No clear demarcation between
exposure
and effect 11
 C A S E - C O N T R O L STUDY D E S I G N

◾ Observational Analytical Retrospective Study design.[5]

◾ A case-control study is designed to help determine if an exposure is associated with an outcome
(i.e., disease or
condition of interest).[7]
◾ A case-control study is always retrospective because it starts with an outcome then traces back
to investigate
exposures.[7]
◾ They are comparatively quick, inexpensive, and easy.[7]
◾ They are particularly appropriate for (1) investigating outbreaks, and (2) studying rare diseases
or outcomes.[7]
12
 C A SES A N D C O N T RO LS

◾ Some participants have the outcome of interest (referred to as cases), whereas

others do
not have the outcome of interest (referred to as controls).[8]
◾ Example:
Smoking and lung cancer study
◾ Doll and Hill (1950) evaluated the association between smoking and lung
[Link] included 709 patients of lung carcinoma (defined as cases).They also included
709 controls from general medical and surgical [Link] selected controls were similar
to the cases with respect to age and [Link], they included 649 males and 60 females in
cases as well as controls.

◾ They found that only 0.3% of males were non-smokers among cases. However, the 13

proportion of non-
smokers among controls was 4.2%.
14
 C A S E - C O N T R O L STUDY D E S I G N
S T R E N GT H S [5] LIMITATIONS [5]

◾ Relatively fast in conduction in ◾ N ot useful for rare exposures.

comparison with prospective cohort
studies.. ◾ Cannot estimate the
◾ C omparatively, needs few participants incidence.
and fewer
resources. ◾ Affect by observation and
◾ Useful for testing hypotheses. recall bias.
◾ Useful in studying multiple exposures in
the same
outcome.
◾ C an study the association of risk factors and
outcomes in outbreak investigations.
◾ It can generate much information from 15
relatively few
participants with unusual cases.
 C O H O RT STUDY DESIGN:

◾ The cohort study design is classified as an observational analytic study design.

◾ This design compares two groups, with exposure of interest and control one.
◾ A cohort design can be either prospective or retrospective.
◾ In Prospective cohort studies, the investigator measures a variety of variables that might
be a risk factor or relevant to the development of the outcome of interest. Over time, the
participants are observed to detect whether they develop the outcome of interest or not.
◾ Retrospective cohort studies use data records that were documented for other
[Link] study duration may vary according to the commencement of data recording.
Completion of the study is limited to the analysis of the data.

16
17
 RANDOMIZED CONTROL TRIALS
RANDOMIZED CONTROL TRIALS
Randomized controlled trial or Randomized clinical trial (RCT) [2]

They can provide strong evidence for one particular research purpose: determining whether
clinical interventions work. [2]
RCTs are prospective and experimental, meaning:[2]

It includes a treatment group and some form of comparison, or control group. [2]
 The “randomized” component of the RCT refers to random allocation of participants to
treatment and
control groups. [2]
18
 NOTE!!!

RCTs may take many forms, but all contain the elements noted above. [2]

By definition then, all RCTs are experimental designs. However, not all experimental designs are
RCTs.

19
20
21
 REFERNCES:

1. [Link]
2. [Link]
3. [Link]
4. [Link]
5. [Link]
[Link]
6. Biostatistics and Research Methods by Muhammad Ibrahim
7. [Link]
8. [Link]
22