Introduction to study Designs
Dr Ajithkumar KDean (Research)
KUHS
23/01/2015---Cochin--Ay
23/01/2015---Cochin--Ay
Pigment reduction in nevus of Ota following leech therapy Sanjeev Rastogi1, Priyanka Chaudhari2
• Nevus of Ota is a congenital blue-gray color nevus afflicting unilaterally, the area near the eyes. It poses a huge cosmetic concern besides being a potential threat for developing melanoma sometime in the course of the disease. The treatment options are neither many nor promising besides they are too expensive. We have treated a case of nevus of Ota with leech therapy where leech was applied upon the lesion for five times spanned in a period of 2 months. The results in terms of change in the color of lesion were evaluated with the help of serial photographs following every treatment session to mark the level of color changes in the lesion. A substantial reduction in color of the nevus was reported following the completion of the therapy. The results were demonstrated with the photographs. Although, recommended as the classical Ayurvedic management for skin diseases, leech therapy is not reported earlier in such conditions. It proposes a novel approach to deal with such congenital pigment lesions where other options are not promising.
23/01/2015---Cochin--Ay
23/01/2015---Cochin--Ay
23/01/2015---Cochin--Ay
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
23/01/2015---Cochin--Ay
Case Reports/ Case Series
• The most basic descriptive study• Link between clinical medicine and
epidemiology• Hypothesis generating• feasible study designs, are easy to conduct
and require less time and financial resources than randomised-controlled trials, case-control, or cohort studies
23/01/2015---Cochin--Ay
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
23/01/2015---Cochin--Ay
Case Report
Case Series
DescriptiveEpidemiology Study
One case of unusualfindings
Multiple cases of findings
Population-based cases with denominator
23/01/2015---Cochin--Ay
• Case series represents an observational study that reports on data from a subject group without a comparison population.
23/01/2015---Cochin--Ay
Case series also need methodology
• Clear study objective/question• Well-defined study protocol• Explicit inclusion and exclusion criteria for study
participants• Specified time interval for patient recruitment• Consecutive patient enrollment• Clinically relevant outcomes• Prospective outcome data collection• High follow-up rate23/01/2015---Cochin--Ay
• Selection bias• Placebo effect, • Hawthorne effect: tendency of some people to work
harder and perform better when they are participants in an experiment
• Rosenthal effect: the greater the expectation placed upon people,
the better they perform. • Natural history effect
23/01/2015---Cochin--Ay
23/01/2015---Cochin--Ay
23/01/2015---Cochin--Ay
Cross-Sectional Study
23/01/2015---Cochin--Ay
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 time23/01/2015---Cochin--Ay
Cross-sectional Design
time
Study only exists at this point in time
Studypopulation
No Disease
Disease
factor present
factor absent
factor present
factor absent
23/01/2015---Cochin--Ay
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• Example: community surveys• Not suitable for studying rare or highly fatal diseases
or a disease with short duration of expression
23/01/2015---Cochin--Ay
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
23/01/2015---Cochin--Ay
SURVEYS
• Prevalence and incidence are obtained from surveys
• The denominator i.e. the population at risk should be clearly defined.Cross sectional survey• a one time measurement conducted on a sample derived from a
populationPrevalence = No. of persons with disease
Population at riskLongitudinal Survey
A group of subjects under surveillance over a period of time.
Incidence rate = Number of new cases occurring over the period Population at risk X time of observation
23/01/2015---Cochin--Ay
The exposure and disease status are examined for a sample from a defined population at the same time point. The prevalence as well as the OR can be determined.OR= No of diseased exposed/no of diseased non exposed -------------------------------------------------------------------- No exp.control /non exposed control
cross-sectional studies
23/01/2015---Cochin--Ay
Cross-Sectional Study
Steps in Cross-Sectional Study 1. Select a sample from the population2. Simultaneously measure predictor and outcome variables
Population
+ Risk Factor
- Risk Factor
+ Risk Factor
+ -
-+
- Risk Factor
Present
23/01/2015---Cochin--Ay
23/01/2015---Cochin--Ay
Case-Control Study
Steps in Case Control Study • 1. Select a sample of patients who already have the disease (Cases)• 2. Select a sample of patients at risk but do not have the disease (Controls)• 3. Measure predictor variables
Population with Disease
-
Population without Disease
Risk Factor
++-
+-
PresentPast
23/01/2015---Cochin--Ay
• Case-Control Studies–an “observational” design comparing
exposures in disease cases vs. healthy controls from same population
–exposure data collected retrospectively–most feasible design where disease
outcomes are rare
23/01/2015---Cochin--Ay
Case Control Studies
23/01/2015---Cochin--Ay
Case Control Studies
23/01/2015---Cochin--Ay
Case
-Con
trol
Des
ign
Studypopulation
Cases(disease)
Controls(no disease)
factor present
factor absent
factor present
factor absent
presentpast
time
Study begins here23/01/2015---Cochin--Ay
Case-Control Study• Strengths
– Less expensive and time consuming
– Efficient for studying rare diseases
• 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
23/01/2015---Cochin--Ay
case-control studies
• Persons suffering from the studied disease are compared with controls who do not have the disease.
• The odds ratio (OR) is calculated as a comparative effect measure.
• = OR=• No of diseased exposed/no of diseased non
exposed• --------------------------------------------------------------------• No exp.control /non exposed control
23/01/2015---Cochin--Ay
Cohort Study
Steps in Cohort Study Design:1. Select a sample from the population2. Measure predictor variables3. Follow-up the cohort4. Measure outcome variables
Population
+ Risk Factor
- Risk Factor
Disease
+ -
-+
Present Future
Epidemiologic Study Designs• Cohort Studies
– an “observational” design comparing individuals with a known risk factor or exposure with others without the risk factor or exposure
– looking for a difference in the risk (incidence) of a disease over time
– best observational design– data usually collected prospectively (some
retrospective)
23/01/2015---Cochin--Ay
Coho
rt D
esig
n
time
Study begins here
Studypopulation
free ofdisease
Factorpresent
Factorabsent
disease
no disease
disease
no disease
presentfuture
23/01/2015---Cochin--Ay
Prospective Cohort study
Measure exposureand confounder
variables
Exposed
Non-exposed
Outcome
OutcomeBaseline
time
Study begins here
23/01/2015---Cochin--Ay
Retrospective Cohort study
Measure exposureand confounder
variables
Exposed
Non-exposed
Outcome
OutcomeBaseline
timeStudy begins here
the investigator collects data from past records and does not follow patients up as is the case with a prospective study. However, the starting point of this study is the same as for all cohort studies
23/01/2015---Cochin--Ay
Cohort Study• Strengths
– Exposure status determined before disease detection– Subjects selected before disease detection– Can study several outcomes for each exposure
• Limitations– Expensive and time-consuming– Inefficient for rare diseases or diseases with long latency– Loss to follow-up
23/01/2015---Cochin--Ay
Cohort studies
• Persons exposed to specific risk factors are compared with persons not exposed to these factors.
• The occurrence of diseases or deaths in these two groups is observed prospectively.
• incidence rate and mortality rate • Relative risk (RR) or hazard ratio (HR) Standardized
incidence ratios (SIR) or standardized mortality ratios (SMR) are used for comparison with the general population.
23/01/2015---Cochin--Ay
Cohort studies
No: disease in exposed / Total no: exposed
RR= -------------------------------------------
No: disease in non exp /Total no: of non exposed
23/01/2015---Cochin--Ay
ECOLOGICAL STUDY
TIME
Direction of injury
Population
E D+
E D-
ED+
ED-
Not Exposed
Exposed
23/01/2015---Cochin--Ay
studies of risk-modifying factors on health or other outcomes based on populations defined either geographically or temporally. Both risk-modifying factors and outcomes are averaged for the populations in each geographical or temporal unit and then compared using standard statistical methods.
Broad street –London
23/01/2015---Cochin--Ay
Ecological studies
Measures combined occurrence of risk factors and disease
in a population
Individual exposure and disease relationship cannot be
assessed
Eg: Occupational and industrial exposure to toxins,
Environmental risk
23/01/2015---Cochin--Ay
Epidemiologic Study Designs
23/01/2015---Cochin--Ay
Descriptive Study Design
• To determine the frequency & Burden of the Disease • To generate Hypotheses
23/01/2015---Cochin--Ay
Evidence Pyramid
23/01/2015---Cochin--Ay
Are you going to observe or experiment?
• Observational – cross sectional, case-control studies, cohort studies – identify participants– observe and record characteristics– look for associations
• Experimental – before and after, comparative trials (controlled or randomised trials) – identify participants– place in common context– intervene– observe/evaluate effects of intervention
23/01/2015---Cochin--Ay
So……..
• To identify the risk factors:
Case-Control Study Design
• To confirm the risk factors:
Cohort Study Design
23/01/2015---Cochin--Ay
Intervention Study
Essential Feature:
• Intervention Group Vs Control Group
• Comparison
• Prove the Causation/ Effect
23/01/2015---Cochin--Ay
Intervention /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.
23/01/2015---Cochin--Ay
Randomized Controlled Trials
Defined Population
Randomization
Treatment Group
Improve Do Not Improve
Standard Therapy
Improve Do Not Improve
23/01/2015---Cochin--Ay
Expe
rimen
tal D
esig
n
timeStudy begins here (baseline point)
Studypopulation
Intervention
Control
outcome
no outcome
outcome
no outcome
baselinefuture
RANDOMIZATION
23/01/2015---Cochin--Ay
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
23/01/2015---Cochin--Ay
Randomized Controlled Trials
• Disadvantages–Very expensive–Not appropriate to answer certain
types of questions• it may be unethical, for example, to
assign persons to certain treatment or comparison groups
23/01/2015---Cochin--Ay
Secondary Analysis• Systematic Review• Meta-Analysis
23/01/2015---Cochin--Ay
Meta-Analysis
23/01/2015---Cochin--Ay
Stu
d y D
esig
ns Case report
Case series
DescriptiveEpidemiology/survey
Descriptive
RCT
Before-Afterstudy
Cross-sectionalstudy
Case-Crossoverstudy
Case-Controlstudy
Cohort study
Analytic
Ecologic study
Qualitative study
23/01/2015---Cochin--Ay
Epidemiological Study Designs
Descriptive studies answer “what’s happening?” Analytic observational studies answer “why or how is it happening?”Analytic experimental studies answer “can it work?”
Descriptive Studies
Case-control Studies
Cohort Studies
Develop hypothesis
Investigate it’srelationship to
outcomes
Define it’s meaning with exposures
Clinical trialsTest link
experimentally
Incr
easi
ng K
now
ledg
e of
D
isea
se/E
xpos
ure
23/01/2015---Cochin--Ay
Research Designs…..Descriptive To: Describe an experience, programs, treatment, unusual observation
AnalyticExamine etiology, efficacy
ObservationalAssociation of cause and effectComparison between 2 treatments
ExperimentalEvaluate the efficacy of a therapeutic , or other interventions
Examples:1) Case Reports or series Side effect of a drug Cluster of cases 2) Population Prevalence or incidence of disease in populations3) Ecological study
Examples:
1) Cross-sectional2) Case-control3) Cohort
Examples:
1) Clinical Trial2) Community education
23/01/2015---Cochin--Ay
Hierarchy of Epidemiologic Study Design
23/01/2015---Cochin--Ay
Chance/Confounder/bias
• While the results of an epidemiological study may reflect the true effect of an exposure(s) on the development of the outcome under investigation, it should always be considered that the findings may in fact be due to an alternative explanation.
• Observational studies are particularly susceptible to the effects of chance, bias and confounding, and these need to be considered at both the design and analysis stage of an epidemiological study so that their effects can be minimized.
23/01/2015---Cochin--Ay
Confounding
23/01/2015---Cochin--Ay
Bias
23/01/2015---Cochin--Ay
Bias results from systematic errors in the research methodology
Information bias ---differences in the way data on exposure or outcome are obtained
Observer bias --differences in the way information is collected
Recall bias---in retrospective studies
Selection bias-- differences in the characteristics between those who are selected in both groups
Important epidemiological frequency measures and comparative measures;
23/01/2015---Cochin--Ay
Thank You
23/01/2015---Cochin--Ay