Study design

Dr. Mehrnaz NikouyehEmergency physician

The study of the distribution and determinants of health-related states or events in specified populations and the application of this study to the control of health problems

Definitions of Research

To describe the frequency and extent of health

conditions and disease. To determine the burden of disease in a community,

including socioeconomic impact of disease occurrence in specific populations.

To identify the causes and risk factors of specific diseases. This is the basis of disease prevention.

To evaluate medical interventions, including both preventive and therapeutic measures, and evaluate the delivery of these measures in health care settings.

To study the natural history and prognosis of disease. To provide the foundation for developing public policy

and regulatory decisions relating to health.

PURPOSE OF EPIDEMIOLOGY

A good clinical study starts with a good question based on good

hypothesis that is based on good and comprehensive review of the available evidence from pre-clinical and clinical data

Type of design depends on the question to be answered

Where to Start?

Focused and specific Supported by available data Not a replication of already

established evidence Ethical Answerable Methods, resources ….etc.

Formulating a Research Question

Specific aims

Clear and detailed End point(s)

Primary The main answer to the research question

Secondary Answer other related questions

Objectives

• Describe• Analyze

Your question

• Retrospective• Prospective

Your resources

• Acceptance of research• Observational• Interventional

Community

Study Design

Descriptiv

e

Case repot

Case series Survey

Analytic

Observational

Cross sectinal

Case control

Cohort

Experimental

RCT

Clinical Study Types

Types of primary studies

Descriptive studies describe occurrence of

outcome

Analytic studies describe association between

exposure and outcome

10

Observational study Clinical trial

exposed

non exposedoutcome

ClinicalTrial

observationalstudydescribe as

occurring in nature

allocaterandomly

Ethics!

Hierarchy of Epidemiologic Study Design

Validity: Truth

External Validity: Can the study be generalized to the

population Internal Validity:

Results will not be due to chance, bias or confounding factors

Symmetry Principle: Groups are similar

Important issues in Study Design

13

Confounding: distortion of the effect of one risk

factor by the presence of another Bias: Any effect from design, execution, &

interpretation that shifts or influences results Confounding bias: failure to account for the

effect of one or more variables that are not distributed equally

Measurement bias: measurement methods differ between groups

Sampling (selection) bias: design and execution errors in sampling

Important issues in Study Design

Descriptive studies

Cannot establish causal relationships Still play an important role in

describing trends and generating hypotheses about novel association

Describing a novel phenomena

Attempt to establish a causal link between

a predictor/risk factor and an outcome.

You are doing an analytic study if you have any of the following words in your research question: greater than, less than, causes, leads to,

compared with, more likely than, associated with, related to, similar to, correlated with

Analytic Studies

Timeframe of Studies

Prospective Study - looks forward, looks to the future, examines future events, follows a condition, concern or disease into the future

time

Study begins here

Timeframe of Studies

Retrospective Study - “to look back”, looks back in time to study events that have already occurred

time

Study begins here

Descriptive Studies

Case Reports

Detailed presentation of a single case or handful of cases

Generally report a new or unique finding

e.g. previous undescribed disease e.g. unexpected link between diseases e.g. unexpected new therapeutic effect e .g. adverse events

Case Series

Experience of a group of patients with a similar diagnosis

Assesses prevalent disease Cases may be identified from a single or

multiple sources Generally report on new/unique condition May be only realistic design for rare

disorders

Case Series

Advantages Useful for hypothesis generation Informative for very rare disease with few

established risk factors Characterizes averages for disorder

Disadvantages Cannot study cause and effect relationships Cannot assess disease frequency

Case Report

Case Series

DescriptiveEpidemiology Study

One case of unusualfindings

Multiple cases of findings

Population-based cases with denominator

Analytical Studies

Observational Studies

non-experimental observational because there is no individual intervention treatment and exposures occur in a “non-controlled”

environment individuals can be observed prospectively, retrospectively,

or currently Possibility of confounding No control over study units

need to clearly describe study individuals Can study risk factors that have serious consequences Study individuals in their natural environment (>>

extrapolation)

cohort

Case control

Cross sectional

Types of observational studies

Evaluate the effect of a suspected risk

factor (exposure) on an outcome (e.g. disease) define “exposure” and “disease”

Describe the impact of the risk factor on the frequency of disease in a population

Aims of observational studies

Temporal relations of observational studies

Cross - Sectional Study

Cross-sectional studies

An “observational” design that surveys exposures and disease status at a single point in time (a cross-section of the population)

time

Study only exists at this point in time

Cross-sectional Design

time

Study only exists at this point in time

Studypopulation

No Disease

Disease

factor present

factor absent

factor present

factor absent

Cross-sectional Studies

Often used to study conditions that are relatively frequent with long duration of expression (nonfatal, chronic conditions)

It measures prevalence, not incidence of disease. Comparison of prevalence among exposed and non-exposed.

Not suitable for studying rare or highly fatal diseases or a disease with short duration of expression

Cross - Sectional Study

Random sample from population i.e. results reflect reference population

Estimates the frequencies of both exposure and outcome in the population

Measuring both exposure and outcome at one point in time

Typically a survey

Cross - Sectional Study advantages

Can study several exposure factors and outcomes simultaneously

Determines disease prevalence Helpful in public health administration & planning Quick Low cost (e.g. mail survey) Very useful for public health planning Disease etiology. Conduct this by obtaining data on

risk factors for a disease. Hypothesis generating

Cross-sectional studies disadvantages

Weakest observational design, (it measures prevalence, not incidence of disease). Prevalent cases are survivors

The temporal sequence of exposure and effect may be difficult or impossible to determine

Usually don’t know when disease occurred Rare events a problem. Quickly emerging

diseases a problem Does not determine causal relationship

Cross-Sectional: Pediatrician-to-Child Ratio

Greg et al. (2001) Pediatrics.107(2):e18

0

5

10

15

20

25

30

35

40

Ped

iatr

icia

ns p

er

1000

Chi

ldre

n

Rural Urban

1981198619911996

Case-Control Studies

Case-Control Study Design

Cases

Controls

Exposed

Unexposed

Exposed

Unexposed

TimeData

collectionDirection of inquiry

Q: What happened?

Case control studies

Determines the strength of the association between each predictor variable and the presence or absence of disease

Cannot yield estimates of incidence or prevalence of disease in the population (why?)

Odds Ratio is statistics

Case-Control Study

Retrospective Can use hospital or health register data

First identify cases Then identify suitable controls

Hardest part: who is suitable ?? Critical that the exposure in the controls is representative

of the exposure in the population Ideal controls would have same/similar characteristics as

the cases Matching cases to controls

Then inquire or retrieve previous exposure By interview By databases (e.g. hospital, health insurance)

Case-Control Study

Strengths Less expensive and time consuming

Efficient for studying rare diseases Can study many risk factors at the same time Smaller sample Multiple etiologic factors evaluated for single disease Good for diseases with long latency

Limitations

Inappropriate when disease outcome for a specific exposure is not known at start of study

Exposure measurements taken after disease occurrence

Disease status can influence selection of subjects Confounding likely difficulties in selection of controls ascertainment of disease & exposure status inefficient for rare exposures unless attributable risk is

high

Case-Control Study

Case-control study-minuses

- Causality still difficult to establish

- Selection bias (appropriate controls)- Caffeine and Pancreatic cancer in the GI

clinic

- Recall bias: sampling (retrospective)- Abortion and risk of breast cancer in

Sweden

Case Selection

• Define source population• Cases

– incident/prevalent– diagnostic criteria (sensitivity + specificity)

• Controls– selected from same population as cases– select independent of exposure status

Control Selection

• Random selection from source population• Hospital based controls:

– convenient selection– controls from variety of diagnostic groups other

than case diagnosis– avoid selection of diagnoses related to

particular risk factors– limit number of diagnoses in individuals

Case-Crossover Studies

Study of “triggers” within an individual ”Case" and "control" component, but

information of both components will come from the same individual

”Case component" = hazard period which is the time period right before the disease or event onset

”Control component" = control period which is a specified time interval other than the hazard period

Cohort Studies

Prospective Cohort Study

without outcome

Cohort

with outcome

with outcome

withoutoutcome

Exposed

Unexposed

TimeOnsetof study Direction of inquiry

Q: What will happen?

Prospective Cohort study

Measure exposureand confounder

variables

Exposed

Non-exposed

Outcome

OutcomeBaseline

time

Study begins here

Retrospective Cohort

study

Measure exposureand confounder

variables

Exposed

Non-exposed

Outcome

OutcomeBaseline

time

Study begins here

Cohort studies

Follow-up studies; subjects selected on presence or absence of exposure & absence of disease at one point in time. Disease is then assessed for all subjects at another point in time.

Typically prospective but can be retrospective, depending on temporal relationship between study initiation & occurrence of disease.

Cohort studies

1. Prospective cohort study – outcome event of interest occur after the study is initiated

2. Retrospective cohort study – outcome events of interest have already occurred at study initiation Can be regarded as a reconstruction of a cohort

study which has already taken place Generally cheaper and faster than a prospective

study Requires good historical exposure data on subjects

Cohort studies

More clearly established temporal sequence between exposure & disease

Can establish population-based incidence Accurate relative risk (risk ratio) estimation Can examine rare exposures (asbestos > lung

cancer) Can be used where randomization is not possible Allows direct measurement of incidence Examines multiple effects of a single exposure - Magnitude of a risk factor’s effect can be quantified Selection and information biases are decreased

Cohort Study

Strengths Exposure status determined before disease detection Subjects selected before disease detection Can study several outcomes for each exposure Directly measure incidence of a disease outcome

Limitations Expensive and time-consuming Inefficient for rare diseases or diseases with long latency Loss to follow-up and unavailability of data potential confounding factors Unexpected environmental changes may influence the association

Basic Question in Analytic Epidemiology

Are exposure and disease linked?

Exposure Disease

Experimental Studies

In an experiment, we are interested in the consequences of some treatment on some outcome.

The subjects in the study who actually receive the treatment of interest are called the treatment group.

The subjects in the study who receive no treatment or a different treatment are called the comparison group.

Epidemiologic Study Designs

Randomized Controlled Trials (RCTs) a design with subjects randomly assigned to

“treatment” and “comparison” groups

provides most convincing evidence of relationship between exposure and effect

not possible to use RCTs to test effects of exposures that are expected to be harmful, for ethical reasons

Clinical Trials

Uncontrolled Controlled

Before/after (cross-over) Historical Concurrent, not randomized Randomized

Clinical Trial: Study Design

May Be AppropriateEarly studies of new and untried therapies

Uncontrolled early phase studies where the standard is relatively ineffective

Investigations which cannot be done within the current climate of controversy

Truly dramatic response

Non-randomized Trials

Randomized controled trial

timeStudy begins here (baseline point)

Studypopulation

Intervention

Control

outcome

no outcome

outcome

no outcome

baseline future

RANDOMIZATION

Epidemiologic Study

Designs

Randomized Controlled Trials (RCTs) the “gold standard” of research designs provides most convincing evidence of

relationship between exposure and effect

trials of hormone replacement therapy in menopausal women found no protection for heart disease, contradicting findings of prior observational studies

62

Advantages of Randomized Control Clinical Trial

advantages Randomization tends to produce

comparable groups Assure causal relationship Randomization produces valid statistical

tests

63

Disadvantages of Randomized Control Clinical Trial

1. Generalizable Results? Participants studied may not represent

general study population.

2. Recruitment Hard

3. Acceptability of Randomization Process Some physicians will refuse Some participants will refuse

4. Administrative Complexity5. Very expensive

64

Clinical Trials-Phases

Phase I - Does it hurt the Patient? Usually in normal volunteers, small groups for

safety testing

Phase II - Does it help the Patient? On patients to confirm the effectiveness of the

drug

Phase III - Is it any better? Large groups of patients for statistical confirmation of effect

and incidence of side-effects

Phase IV - Does it work in the community? Post marketing studies. Fine tuning and new

rare findings from a very large population