Study Design

Study designs
are structured approaches to address specific research questions

Study designs provide general guidelines for thinking about specific aspects of study conduct. including:
– sampling populations
– how to systematically collect various measurements
– how to analyze the data sets

When selecting a study design you should start with a good study question like
– Is it relevant
– Is it novel
– is it feasible

Three main types of study designs
Descriptive, analytic, diagnostic

Descriptive study design consist of
survey and qualitative

Analytic study design consist of
experimental and observational

Analytic experimental study design consist of
Randomised (Parallel group)

Randomised (Crossover)

meta analysis

Observational experimental study design consist
cohort study, cross sectional, case-control study

Observational studies have zero
randomization associated with them

In observational studies, investigators do not
assign subjects to groups

In experimental studies, investigators
assign subjects to different groups

Power is less in what type of studies
observational which includes cohort, case control, cross sectional

What questions are asked when spotting the study design?
What is the aim of the study?

If it is analytic, was the intervention randomly allocated?

When were the outcomes determined?

If the aim of the study is to simply describe a population (PO questions) then it is a
descriptive study

If the aim of the study is to quantify the relationship between factors (PICO or PECO questions) then it is a
Analytic study

Which type of study would you expect residents to perform?
descriptive studies because of time constraints

If the study is analytic and the intervention is randomly allocated then it is a
randomized control trial

If the study is analytic and the intervention is not randomly allocated then it is a
observational study

If the outcomes were determined after the exposure or intervention then it is a
cohort study

If the outcomes were determined at the same time as the exposure or intervention then it is a
cross sectional study or survey

If the outcomes were determined before the exposure or intervention then it is a

Why are systemic reviews strong evidence
they look for published data and unpublished data which makes them strong evidence

What is the major issue with meta analysis?
the lack of negative publications

Why are opinions and reviews important?
because the opinions of experts matters and u will be asked about it during journal clubs

What are the differences between study designs?
– how participants are sampled
– when measurements are to be taken
– How outcome variables are measured
– Are there comparison groups involved

Case reports
an article that describes and interprets an individual case and often written in the form of a detailed story

Case reports often will describe
– unique cases that cannot be explained by known diseases or syndromes
– cases that show an important variation of a disease or condition
– cases that show unexpected events that may yield new or useful information
– cases in which one patient has two or more unexpected diseases or disorders

Case report advantages
-very good for rare cases
– dont require a lot of time
– can help in the identification of new trends or diseases
– can help detect new drug side effects and potential uses
– educational: a way of sharing lessons learned

Case reports help to
build hypotheses

With case reports there is no
control. since there is no control group there is no statistical validity

Case reports disadvantages
– cases may not be generalizable
– not based on systematic studies
– causes or associations may have other explanations
-can be seen as emphasizing the bizarre or focusing on misleading elements

Case control studies will often use an
odds ratio

Case control studies are generally designed to estimate
the odds of developing the studied condition or disease

With case control studies you can determine if there is
an associational relationship between the condition and risk factor

with case control studies u want the the sample to reflect the population so you want
there to be more controls than cases = cuts out confounding and bias

Biggest case control study that was disproved is what?
vaccines and autism

Case Control advantages
– good for rare diseases
– less time needed to conduct the study
– u can look at multiple risk factors
– useful as an initial study to establish an association

Case control disadvantages
– reliance on recall or records to determine exposure status
– cofounders
– selection of control groups
– potential bias: especially recall and selection

Cross sectional study
– examines relationship between diseases and other variables of interest as they exist in a defined population at a specific point in time
– section is independent of exposure or disease
– carried out for public health planning and for etiologic research

cross sectional studies are also known as
prevalence studies because they are good for prevalence

Cross sectional study advantage
– INEXPENSIVE and takes little time to conduct
– estimate prevalence because sample is usually taken from the whole population
– many outcomes and risk factors can be assessed
– useful for public health planning, disease etiology, generation of hypotheses

Cross sectional disadvantages
– difficult to make casual inference
– Prevalence and incidence bias (Neyman bias)
– it is only a snap shot, may get different results if another time frame had been chosen

Cohort study is associated with
relative risk

Odds ratio is associated with
case control

Prospective Cohort
exposure factors are identified at the BEGINNING of a study and a defined population is followed into the future

Retrospective cohort
past medical records for the defined population are used to identify exposure factors and compared with another group

You get answers faster with case control versus cohort but case control studies
are only valid in specific populations while cohort is valid in multiple populations

Population is more defined in case control but in cohort, the population
is much larger and varying

Cohort advantages
– subjects in cohorts can be matched, which limits the influence of confounding variables
– standardization of criteria/outcome is possible
– easier and cheaper than a randomized controlled trial

cohort disadvantages
– cohorts can be difficult to identify due to confounding variables
– no randomization so imbalance in patient characteristics could exist
– blinding/masking is difficult
– outcome of interest could take time to occur

Randomized controlled study does not eliminate confounding and bias but
it evenly distributes those between the groups

Randomized controlled study is a study in which
there are two or more groups, one of which is a control group

the treatment group receives the Tx under investigation and the control group receives either no treatment or standard of care treatment

subjects are randomly assigned to all groups

RCT – randomization helps avoid
selection bias

RCT- randomization increases the probability that
differences between groups can be attributed to the treatment under study

What is considered the gold standard for medical research

RCT advantages
– good randomization will “wash out” any population bias
– easier to blind/mask than observational studies
– results can be analyzed with well known statistical tools
– populations of participating individuals are clearly identified

RCT disadvantages
– EXPENSIVE in terms of time and money
– LOSS TO FOLLOW UP attributed to treatment
– Volunteer biases, the population that participates may not be representative of the whole
– does not reveal causation

Double blind study
RCT in which neither the medical personnel nor the patients know which treatment group they are allocated to

Double blind study advantages
less bias

Double blind study disadvantage
test subjects may not be receiving active drug or may be receiving an active drug that isnt comparable to what is out on the market

Crossover study advantages
– all subjects serve as own controls and error variance is reduced
– thus reduces sample size
– all subjects receive treatment at least at some point during the study
– blinding can still be maintained

Crossover study disadvantages
– all subjects receive placebo or alternative treatment at some point
– washout period can be lengthy or unknown
– cannot be used for treatments with permanent effects

Washout period
u have to make sure treatment A is out of their system until you can administer treatment B

If you see p values and confidence intervals then it is a
meta analysis

Meta analysis
a systematic objective way to combine data from many studies, usually from randomized controlled trials

arrive at a pooled estimate of treatment effectiveness and statistical significance

can also combine data from case control and cohort studies

Meta analysis advantage
– includes data from multiple randomized clinical trials
– greater statistical power
– confirmatory data analysis
– greater ability to extrapolate to general population affected
– considered an evidence based resource

Meta analysis disadvantage
– difficult and time consuming to identify appropriate studies
– not all studies provide adequate data for inclusion and analysis
– requires advanced statistical techniques
– heterogeneity of study populations

Systematic review
– uses a process to identify comprehensively all studies for a specific focused question, appraises the methods of the studies, summarizes the results, and presents key findings
– also identifies reasons for different results across studies
– cites limitations for current knowledge

Systematic review process uses what type of literature?
both published and unpublished

Systematic review process has a clearly formulated
research question

Key disadvantage with meta analysis is that
you can quantify the data but you cant qualify the data meaning u cant assess the quality

Final results of systematic review process are placed in context which addresses issues such as
quality of the study, impact bias, applicability of the findings

Systematic review advantages
– exhaustive review of the current literature and other sources
– Less costly to review prior studies than to create a new study
– less time required than conducting a new study
– results can be generalized and extrapolated into the general population more broadly than individual studies
-more reliable and accurate than individual studies
– considered to be evidence based

Which study design is considered to be evidence based?
Systematic review

Systematic review disadvantage
-time consuming
– may not be easy to combine studies
– studies included may be of varying study designs but they should be studying the same outcomes
-did each