METHODOLOGY STUDY DESIGN I:STUDY DESIGNS IN MEDICAL RESEARCH

Prof. Dr. Zaleha Md. Isa,

BSc(Hons)Clin. Biochem , PhD (Community Health),

Department of Community Health,

Faculty of Medicine,

Universiti Kebangsaan Malaysia Medical Centre,

Cheras, Kuala Lumpur.

Classification of study designs

1. Observational Studies

2. Experimental Studies

3. Meta-Analysis

Observational Studies

1. Descriptive or case-series

2. Case-control studies (retrospective)

3. Cross-sectional studies, surveys (prevalence)

4. Cohort studies (prospective)

5. Historical cohort studies

Case-series studies A simple descriptive account of interesting

characteristics observed in a group of patients.

Generally involve patients seen over a relatively short period of time and do not include control subjects (persons who do not have the disease or condition being described).

Advantage Easy to conduct and report can be produced faster. The study results are beneficial for researchers who

planned to do research – precursor to other studies.

Disadvantage Easily influenced by bias related to case selection and

characteristics observed.

Case-control studies (retrospective studies) Case-control studies begin with the absence or

presence of an outcome and then look backward in time to try to detect possible causes or risk factors that may have been suggested in a case series report.

The cases are individuals selected on the basis of some disease or outcome; the controls are individuals without the disease or outcome.

The history or previous events of both cases and controls are analyzed in an attempt to identify a characteristic or risk factor present in the cases’ histories but not in the controls’ histories.

Schematic diagram of case-control study design

Cases

Controls

Onset of studyTime

Direction of inquiry

Exposed

Unexposed

Exposed

Unexposed

Compare

Case-control studies Advantages

Suitable to study rare diseases or diseases that occur for a long period of time.

Preferably used to investigate initial hypothesis.

Results can be obtained faster.

Less expensive.

Disadvantages

Too many biases (misclassification of cases and subjects did not remember the risk factors studied).

It depends on the completeness of the existing records.

Case-control studies Matching is used to associate controls with

cases on factors like age and sex;

Example:

Usually two groups are recommended:

1. Group almost similar to cases e.g. patients in hospital.

2. Group that is healthy.

Cross-sectional studies Also known as surveys, epidemiologic studies, and

prevalence studies.

Analyze data collected on a group of subjects at one time rather than over a period of time. “What is happening?”

Advantages

Suitable to determine disease condition at one time.

Suitable to evaluate a diagnosis method.

Results can be obtained quickly.

Not expensive.

Schematic diagram of cross-sectional study design

Subjects selected for the study With outcome

Without outcome

Onset of studyTime

*No direction of inquiry

Cross-sectional studiesDisadvantages

Provide just a temporary picture of a disease –as a consequence, it gives wrong information.

Main problem – to obtain sufficiently large response.

Cohort studies (prospective studies)

A cohort is a group of people who have something in common and who remain part of a group over an extended period of time.

A continuation of case-control study.

Subjects in cohort studies are selected by some defining characteristic (or characteristics) suspected of being a precursor to or risk factor for a disease or health effect. “What will happen?”

Cohort studies (prospective studies)

Cohort population remains the same throughout the study except:

death

migration

lost to follow-up

Dinamic population – individuals can enter and exit the study according to the determined criteria. Fixed population – population must be defined at the onset of the study.

Schematic diagram of cohort study design

Cohort selected

for study

Subjects

(exposed)

Controls

(unexposed)

With

outcome

Without

outcome

With

outcome

Without

outcome

Direction of inquiryOnset of study

time

compare

Historical cohort studies (retrospective cohort study) Historical cohort is a cohort study using

information collected in the past and kept in records or files.

This approach to a study is possible if the records on follow-up are complete and adequately detailed and if the investigators can ascertain the current status of the patients.

The events being evaluated actually occurred before the onset of the study.

Schematic diagram of historical cohort study design

Records selected

for study

Subjects

(exposed)

Controls

(unexposed)

With

outcome

Without

outcome

With

outcome

Without

outcome

Direction of inquiry (still forward)

Onset of study time

Experimental studies or clinical trials Experimental studies in medicine that involve

humans are called clinical trials because their purpose is to draw conclusions about a particular procedure or treatment.

1. Controlled trialsstudies in which the experimental drug or procedure is compared with another drug or procedure, sometimes a placebo and sometimes the previously accepted treatment.

2. Uncontrolled trialsstudies in which the investigators’ experience with the experimental drug or procedure is described, but the treatment is not compared with another treatment.

Experimental studies or clinical trials

1. Experiment – the strongest study design to prove causation (cause & effect).

2. Quasi-experiment (one of the characteristics is missing ie. either no randomization or no control)

Three characteristics of classic experimental design:1. Manipulation

Researcher applied something on a group of subjects in a study.

2. ControlOne or more control groups to compare with experimental group.

3. RandomizationTo assign subjects randomly into the control

and experimental group.

Controlled trials

1. Trials with independent concurrent controls1. Randomized clinical trials

2. Non-randomized trials

2. Trials with self-controls1. Self-controlled study

2. Cross-over study

3. Trials with external controls (historical controls)

4. Uncontrolled studies (quasi-experiment)

Trials with independent concurrent controls

Perform trial on two study groups.

Concurrent controls. Treated the same for both groups. Double-blind trials; blind trials.

Receive the studied

treatment

Receive placebo @

conventional/standard

treatment

group 1

(experimental group)

group 2

(control group)

Randomized clinical trials

The epitome of all research designs because it provides the strongest evidence for concluding causation.

Provides the best insurance that the result was due to the intervention.

Schematic diagram of randomized clinical trial design

Subjects meeting

entry criteria

Experimental subjects

Controls

With

outcome

Without

outcome

With

outcome

Without

outcome

Onset of study TimeIntervention

Non-randomized trials

Do not use randomized assignment.

Open to so many sources of bias that their conclusions are highly questionable.

Self-controlled study

Experimental

group

Control

group

Self-controlled study

Use the same group of subjects for both experimental and control options.

Patients are assessed before and after the intervention.

Advantage – reduce number of subjects –simplify study implementation and save cost.

Disadvantage – vulnerable to Hawthorne effect (people change their behaviour and sometimes improve simply because they receive special attention by being in a study and not because of the study intervention itself).

Cross-over study

A combination of concurrent and self-controls.

One group is assigned to the experimental treatment, and the second group is assigned to the placebo or control treatment.

After a period of time, the experimental treatment and placebo are withdrawn from both groups for a “washout” period. The groups are then given the alternative treatment, the first group now receives the placebo and the second group receives the experimental treatment.

The design is powerful when used appropriately.

Schematic diagram of trial with cross-over.

Subjects

meeting

entry criteria

Experimental

subjects

Controls

With outcome

With outcome

Without outcome

Without outcome

Experimental subjects

Controls

With outcome

With outcome

Without

outcome

Without

outcome

Onset of study Intervention Intervention Washout period

Time

Trials with external controls

Use controls external to the study.

1. The result of another investigator’s research is used as a comparison.

2. The controls are patients the investigator has previously treated in another manner (historical controls).

Schematic diagram of trial with external controls.

Subjects

Results from previous study

(historical)

With

outcome

Without

outcome

With

outcome

Without

outcome

Onset of studyIntervention in subjects only Time

Uncontrolled studies There were no comparisons with patients

treated in another manner.

Disadvantage – investigators assume that the procedure used and described is the best one.

Advantages of clinical trials 1. The gold standard, or reference in medicine.

2. The basic design against which other designs are judged.

3. Provides the greatest justification for concluding causality and is subject to the least number of problems or biases.

4. The best type of study to use when the objective is to establish the efficacy of a treatment or a procedure.

5. Trials in which patients are randomly assigned to different treatments are the strongest design of all.

Disadvantages of clinical trials

1. Great expense and long duration.

2. Certain practices become established and accepted by the medical community, even though they have not been properly justified.

3. Difficulty obtaining approval to perform properly designed clinical trials from the human subjects committees that oversee the ethics of research in many hospitals and research institutions.

Meta-Analysis “Meta” – later and more highly organized.

Meta-analysis used published information from other studies and combines the results so as to permit an overall conclusion.

Meta-analysis is similar to review articles but additionally includes a quantitative assessment and summary of the findings.

Especially appropriate when the studies that have been reported have small numbers of subjects or come to different conclusions.

THANK YOU

1. Dawson-Saunders, B. & Trapp, R.G. 1990. Basic and

Clinical Biostatistics. Prentice-Hall International Inc.

London.

2. Md. Idris Mohd. Nor. 1995. Asas Statistik dan

Penyelidikan, Dewan Bahasa dan Pustaka, Kuala

Lumpur.

3. Elston, R.C. & Johnson, W.D. 1987. Essential of

Biostatistics, F.A. Davis Company, Philadelphia.