Study Types

Study type strengths Limitations

A. Observational and descriptive Studies
Case series, Case report 1. Help describe rare 1. Purely descriptive and considered to
Case reports and series are manifestations and new be the weakest form of evidence.
helpful in recognizing and diseases. 2. Lack of control group (no
describing new disease 2. Identify emerging health comparison)
processes or rare conditions. 3. Can not be used to test for the
manifestations and identify 3. Better suited to describing the presence of a valid statistical
emerging health conditions. characteristics of the disease association.
“documents unusual adverse than identify causality. 4. Based on the experience of only one
events observed in single person.
patients”

Cross-sectional study 1. Fast and inexpensive. Cannot estimate incidence

1.
Prevalence study 2. Avoids the problem of loss to Difficult to establish causal
2.
“It is a survey of the total follow-up. relationship
population for the exposure 3. A cross-sectional study 3. Impractical for the study of rare
and disease (or drug use conducted at the beginning of a diseases and requires a large sample
problems) at a single point cohort or clinical trial provides size
in time”. demographic and clinical 4. Only a snapshot at a time leading to
characteristics at baseline. a misinformation
5. The result not representative of the
whole population (only individuals
who participate in the study).
B. Observational and analytical Studies
Case-control study 1. Relatively inexpensive 1. Low internal validity (data
Compare cases with a because of smaller sample collection is based on event recall).
disease to controls without sizes. 2. High chance of bias because of
the disease, looking for 2. It is useful for studying a separate sampling of cases and
differences in exposures relatively rare disease controls and retrospective
(multiple possible causes of 3. Multiple etiologic factors can measurement of various predictor
a single disease). be studied. variables.
4. Useful for generating 3. Cannot estimate incidence or
hypotheses about the causes prevalence.
of an outcome variable. 4. Only one outcome can be studied,
5. One does not need an ethical whereas cohort and cross-sectional
consent. studies can evaluate multiple
6. There is no risk to the subject outcome variables
.

Cohort study 1. Can measure incidence. 1. Expensive because of large sample

Can be prospective or 2. Establish temporal association size and long follow-up.
retrospective 3. Good for common diseases. 2. Not good for rare diseases.
In a prospective cohort 4. Good for rare exposures. 3. Confounding factors
study, patients are identified 5. Possible to study associations 4. A number of potential biases must be
at the beginning of the study of an exposure with several taken into account in conducting
based on their exposure outcome variables. cohort studies.
status (exposed or not a. Bias in assessment of the outcome
exposed) and followed up b. Information bias or recall bias.
for a period from exposure c. Biases from lack of response due to loss to
to outcome follow-up.
d. Analytic bias.
 Both designs are identical, comparing exposed and non-exposed populations. The only difference is calendar
time.
 The duration of follow-up and cost, associated with prospective cohort studies may be reduced by conducting
retrospective cohort studies.
 C. Intervention Study (Experimental)
Randomized controlled 1. Exposure is under the control 1. Expensive
study of investigator. 2. Subject exclusion may limit ability to
Subjects in a population are 2. Randomization generalize findings to other patients.
randomly allocated into 3. Blinding eliminates bias 3. A long period of time is often
groups, usually called study 4. Control on time span required to reach a conclusion.
and control groups to receive 5. Confounding factors can be 4. A large number of participants may
and not receive an controlled be required.
experimental preventive or 6. Best method to study causal 5. Need an ethical consent.
therapeutic procedure. relationship 6. Subjects may not comply with
7. We can confirm or refute treatment assignments.
"The investigator applies an etiological hypothesis on 7. May expose participants to potential
intervention and observes evidence. harm.
the effect on one of more 8. More than one outcome can
outcomes". be measured.
Clinical trials
Preclinical The first step in development of a new drug is bench research using tissue cultures or
animal models. Information on mechanism of action, efficacy, toxicity,
pharmacokinetics, and pharmacodynamics is obtained from these studies
Phase I trial This phase emphasizes safety. It involves 20 to 80 healthy volunteers. Information on
the drug’s most frequent adverse effects, drug metabolism, and excretion are obtained
from phase I studies
Phase II trial The goal of phase II trials is to obtain preliminary data on whether the drug works in
patients who have a certain disease or condition. It typically involves hundreds of
patients. Safety continues to be evaluated, and short-term adverse effects are studied.
Phase III trial Phase III trials typically involve hundreds or thousands of patients and gather more
information on safety and efficacy (RCT)
New Drug Application If the phase III trial is successful, the sponsor applies for an New Drug Application to the
review FDA. This process includes a review of the proposed professional labeling and
inspection of the manufacturing facility. If the review is favorable, the FDA may
approve the drug for marketing.
Phase IV or postmarketing This trial happen after the FDA has approved medication. This phase involves thousands
surveillance of participants and can last for many years.
Investigators use this phase to get more information about the medication’s long-term
safety, effectiveness, and any other benefits.
14/2/2019