final study design ppt

54
STUDY DESIGN

Upload: hanan-abbas

Post on 07-Nov-2014

111 views

Category:

Documents


3 download

DESCRIPTION

help new protocol writers to know basic information about study designdiscuss different scenarios of research questions, and pitfalls to avoid

TRANSCRIPT

Page 1: Final Study Design ppt

STUDY DESIGN

Page 2: Final Study Design ppt

Study DesignObjectivesObjectivesBy the end of this session candidates By the end of this session candidates

should be able to: should be able to: 1. Review the fundamental study designs

2. Discuss Studies

-Uses -Strengths/weaknesses

04/08/23 2research design/ hanan abbas

Page 3: Final Study Design ppt

Most problems in studies are due to poor design (not poor analysis)

04/08/23 3research design/ hanan abbas

Page 4: Final Study Design ppt

Research Design

• The research design is the master plan specifying the methods and procedures for collecting and analyzing the needed information.

04/08/23 4research design/ hanan abbas

Page 5: Final Study Design ppt

Study Design

Experimental• Randomized controlled trials• Quasi

Observational

Analytic • Cross sectional• Case-control• Cohort studies

Descriptive• Case report• Case series• Survey

04/08/23 5research design/ hanan abbas

Page 6: Final Study Design ppt

Epidemiologic Study Designs

Experimental Observational

DescriptiveAnalytical

Case-Control Cohort

+ cross-sectional & ecologic

(RCTs)

Quasi

04/08/23 6research design/ hanan abbas

Page 7: Final Study Design ppt

Analytical Studies

Observational

Experimental

04/08/23 7research design/ hanan abbas

Page 8: Final Study Design ppt

Observational Studies

Cross-sectional

Case-control

Cohort

04/08/23 8research design/ hanan abbas

Page 9: Final Study Design ppt

Epidemiologic Study Designs

Grimes & Schulz, 2002 (www)

04/08/23

9

research design/ hanan abbas

Page 10: Final Study Design ppt

Hierarchy of Epidemiologic Study Design

Tower & Spector, 2007 (www)

Page 11: Final Study Design ppt

Cross-sectional Study

Data collected at a single point in

time

Describes associations

Prevalence A “Snapshot”

04/08/23 11research design/ hanan abbas

Page 12: Final Study Design ppt

Example of a Cross-Sectional Study

Association between garlic

consumption and CAD in the Family

Practice Clinic

04/08/23 12research design/ hanan abbas

Page 13: Final Study Design ppt

Cross-Sectional Study

Strengths Quick Cheap

Weaknesses Cannot establish cause-effect

04/08/23 13research design/ hanan abbas

Page 14: Final Study Design ppt

Observational Studies

Case-Control Study

Start with people who have disease

Match them with controls that do not

Look back and assess exposures

* case-control (retrospective ): Begins with outcome (cancer cases

and healthy controls

04/08/23 14research design/ hanan abbas

Page 15: Final Study Design ppt

Example of a Case-Control Study

Are those with CAD less likely to

have consumed garlic?

04/08/23 15research design/ hanan abbas

Page 16: Final Study Design ppt

Advantages of Case-Control StudiesAdvantages of Case-Control Studies

- Cheap, easy and quick studies

- Multiple exposures can be examined

- Rare diseases and diseases with long latency can be studied

- Suitable when randomization is unethical (alcohol and pregnancy outcome)

04/08/23 16research design/ hanan abbas

Page 17: Final Study Design ppt

Disadvantages of Case-Control StudiesDisadvantages of Case-Control Studies

- Case and control selection troublesome

- Subject to bias (selection, recall, misclassification)

- Direct incidence estimation is not possible

- Multiple outcomes cannot be studied

04/08/23 17research design/ hanan abbas

Page 18: Final Study Design ppt

Case-Control Studies: Strengths Good for rare outcomes: cancer Can examine many exposures Useful to generate hypothesis Fast Cheap Provides Odds Ratio

04/08/23 18research design/ hanan abbas

Page 19: Final Study Design ppt

Case-Control Studies: Weaknesses Cannot measure

Incidence Prevalence Relative Risk

Can only study one outcome High susceptibility to bias

04/08/23 19research design/ hanan abbas

Page 20: Final Study Design ppt

Design pitfalls to look out for

Care should be taken to avoid confounding, which arises when an exposure and an outcome are both strongly associated with a third variable.

Controls should be subjects who might have been cases in the study but are selected independent of the exposure.

Cases and controls should also not be "over-matched."

04/08/23 20research design/ hanan abbas

Page 21: Final Study Design ppt

Is the control group appropriate for the population? Does the study use matching or pairing appropriately to avoid the effects of a confounding variable? Does it use appropriate inclusion and exclusion criteria?

04/08/23 21research design/ hanan abbas

Page 22: Final Study Design ppt

Real-life Examples

Chambers, C. D., Hernandez-Diaz, S., Van Marter, L. J., Werler, M. M., Louik, C., & Jones, K. L. et al. (2006). Selective serotonin-reuptake inhibitors and risk of persistent pulmonary hypertension of the newborn. New England Journal of Medicine, 354(6), 579-587.

This study used a matched design, matching infants who had persistent pulmonary hypertension with infants who did not have it, and compared the rates of exposure to SSRIs. 04/08/23 22research design/ hanan abbas

Page 23: Final Study Design ppt

Smedby, K. E., Hjalgrim, H., Askling, J., Chang, E. T., Gregersen, H., & Porwit-MacDonald, A. et al. (2006). Autoimmune and chronic inflammatory disorders and risk of non-hodgkin lymphoma by subtype. Journal of the National Cancer Institute, 98(1), 51-60.

This study matched patients with non-Hodgkin lymphoma (NHL) with control subjects and compared their history of autoimmune and chronic inflammatory disorders, markers of severity, and treatment. It found that the risk of NHL was increased in association with rheumatoid arthritis, primary Sjögren syndrome, systemic lupus erythematosus, and celiac disease.T

04/08/23 23research design/ hanan abbas

Page 24: Final Study Design ppt

Cohort Study

Begin with disease-free patients

Classify patients as

exposed/unexposed

Record outcomes in both groups

Compare outcomes using relative risk

04/08/23 24research design/ hanan abbas

Page 25: Final Study Design ppt

Example of a Cohort Study

To see the effects of garlic use

on CAD mortality in a population

cohort (prospective): Begins with an exposure (smokers and non-smokers)

04/08/23 25research design/ hanan abbas

Page 26: Final Study Design ppt

Examples of Cohort Studies

* Framingham Heart Study (www)

* NHANES Studies (www)

* MACS (www)

* Physicians' Health Study (www)

* Nurses' Health Study (www)

* ALSPAC (www)

04/08/23 26research design/ hanan abbas

Page 27: Final Study Design ppt

Advantages of Cohort Studies

- 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

- Magnitude of a risk factor’s effect can be quantified

- Selection and information biases are decreased

- Multiple outcomes can be studied (smoking > lung cancer, COPD, larynx cancer)

04/08/23 27research design/ hanan abbas

Page 28: Final Study Design ppt

Disadvantages of Cohort Studies

- Lengthy and expensive

- May require very large samples

- Not suitable for rare diseases

- Not suitable for diseases with long-latency

- Unexpected environmental changes may influence the association

- Non-response, migration and loss-to-follow-up biases

- Sampling, and observer biases are still possible

04/08/23 28research design/ hanan abbas

Page 29: Final Study Design ppt

Cohort Study: Strengths

Provides incidence data

Establishes time sequence for causality

Eliminates recall bias Allows for accurate measurement of

exposure variables

04/08/23 29research design/ hanan abbas

Page 30: Final Study Design ppt

Cohort Study: Strengths

Can measure multiple outcomes

Can adjust for confounding variables

Can calculate relative risk

04/08/23 30research design/ hanan abbas

Page 31: Final Study Design ppt

Cohort Study: Weaknesses

Expensive

Time consuming

Cannot study rare outcomes

Confounding variables

04/08/23 31research design/ hanan abbas

Page 32: Final Study Design ppt

Cohort Study: Weaknesses

Exposure may change over time

Disease may have a long pre-clinical

phase

Attrition of study population

04/08/23 32research design/ hanan abbas

Page 33: Final Study Design ppt

Design pitfalls to look out for

Design pitfalls to look out for The cohorts need to be chosen from

separate, but similar, populations. How many differences are there

between the control cohort and the experiment cohort? Will those differences cloud the study outcomes?

04/08/23 33research design/ hanan abbas

Page 34: Final Study Design ppt

Real-life Example

Ramchand, R., Ialongo, N. S., & Chilcoat, H. D. (2007). The effect of working for pay on adolescent tobacco use. American Journal of Public Health, 97(11), 2056-2062.

This study uses data collected from high school students from Baltimore, Maryland, and studies the differences in initiation of tobacco use between a cohort of adolescents that started working for pay and a cohort of adolescents that did not work. The results suggest that adolescents who work for pay have a higher risk of initiating tobacco use.

04/08/23 34research design/ hanan abbas

Page 35: Final Study Design ppt

Lindenauer, P. K., Rothberg, M. B., Pekow, P. S., Kenwood, C., Benjamin, E. M., & Auerbach, A. D. (2007). Outcomes of care by hospitalists, general internists, and family physicians. New England Journal of Medicine, 357(25), 2589-2600.

To study effects of hospitalists, general internists, and family physicians on patient care, patients that were hospitalized with certain conditions under the care of hospitalists, general internists, and family physicians were separated into three cohorts. The results showed that patients cared for by hospitalists had shorter hospital stays and lower costs than those cared for by general internists or family physicians.

04/08/23 35research design/ hanan abbas

Page 36: Final Study Design ppt

Nichol, K. L., Nordin, J. D., Nelson, D. B., Mullooly, J. P., & Hak, E. (2007). Effectiveness of influenza vaccine in the community-dwelling elderly. New England Journal of Medicine, 357(14), 1373-1381.

To determine the long-term effectiveness of influenza vaccines in elderly people, cohorts of vaccinated elderly and unvaccinated community-dwelling elderly were studied. The results suggest that the elderly who are vaccinated have a reduced risk of hospitalization for pneumonia or influenza

04/08/23 36research design/ hanan abbas

Page 37: Final Study Design ppt

Experimental Studies

Clinical trials provide the “gold

standard” of determining the

relationship between garlic and

cardiovascular disease prevention.

04/08/23 37research design/ hanan abbas

Page 38: Final Study Design ppt

Clinical Trials

Randomized

Double-blind

Placebo-controlled

04/08/23 38research design/ hanan abbas

Page 39: Final Study Design ppt

Clinical Trials

Strengths: Best measure of causal relationship Best design for controlling bias Can measure multiple outcomes

Weaknesses: High cost Ethical issues may be a problem Compliance

04/08/23 39research design/ hanan abbas

Page 40: Final Study Design ppt

Experimental

Design

timeStudy begins here (baseline point)

Studypopulation

Intervention

Control

outcome

no outcome

outcome

no outcome

baselinefuture

RANDOMIZATION

04/08/23 40research design/ hanan abbas

Page 41: Final Study Design ppt

Types of trials

B lind ed N o t b lind ed

R a nd o m ised N o t ran d om ised

C o n tro lled N o t co n tro lled

T ria l

04/08/23 41research design/ hanan abbas

Page 42: Final Study Design ppt

Double-blind design• Neither patient nor outcome evaluator knows Rx to whichpatient was assigned• Single-blind• Patient or evaluator is blinded as to Rx, but not both• Triple-blind• Patient, Physician, and Data analyst are blinded as to Rxidentity

04/08/23 42research design/ hanan abbas

Page 43: Final Study Design ppt

Design pitfalls to look out for An RCT should be a study of one

population only. Was the randomization actually

“random,” or are there really two populations being studied?

The variables being studied should be the only variables between the experimental group and the control group.

04/08/23 43research design/ hanan abbas

Page 44: Final Study Design ppt

Müller, O., Traoré, C., Kouyaté, B., Yé, Y., Frey, C., Coulibaly, B., et al. (2006). Effects of insecticide-treated bednets during early infancy in an African area of intense malaria transmission: A randomized controlled trial. Bulletin of the World Health Organization, 84(2), 120-126.

The study done in this example was to determine whether the early use of bed nets had an effect on the morbidity rate of infants in rural Burkina Faso. An experimental group of infants used bed nets at birth, and a control group of infants used bed nets at six months of age. Results showed no significant difference in morbidity rates, but use of bed nets from birth was related to lower incidence of both malaria and moderate to severe anemia.

04/08/23 44research design/ hanan abbas

Page 45: Final Study Design ppt

Krishna, S., Balas, E. A., Francisco, B. D., & König, P. (2006). Effective and sustainable multimedia education for children with asthma: A randomized controlled trial. Children's Health Care, 35(1), 75-90.

This article reports on the effect of multimedia education for children with asthma. A control group of pediatric patients with asthma was given standard asthma educational resources, while the experimental group of pediatric patients with asthma was given standard resources plus multimedia resources. The study found a reduction in daily symptoms, in emergency room visits, in school days missed, and in days of limited activity in the group given multimedia education resources.

04/08/23 45research design/ hanan abbas

Page 46: Final Study Design ppt

research design/ hanan abbas 46

Meta-Analyses

Systematic objective way to combine data from many studies

Pooled estimate of treatment effectiveness

Statistical significance Publication bias Theoretical framework Misleading results

04/08/23

Page 47: Final Study Design ppt

research design/ hanan abbas 47

Systematic Reviews

Comprehensive survey All relevant studies of highest level

of evidence Rigorous analysis Systematic review

04/08/23

Page 48: Final Study Design ppt

Conclusion (1)

Case-series is a coherent set of cases of a disease (or similar problem).

Cases are compared with reference group, we have a case control study

In a population studied at a specific time and place (a cross-section) the primary output is prevalence data, though association between risk factors and disease can be generated.

In cross-sectional studies, we are looking for both exposure and outcome

In case-control studies, we know the outcome, looking for the exposure

In cohort studies, we know the outcome, following up looking for the outcome in question

04/08/23 48research design/ hanan abbas

Page 49: Final Study Design ppt

Conclusion (2)

If the population in a cross-sectional survey is followed up to measure health outcomes, this study design is a cohort study.

If the population of such a study are, at baseline, divided into two groups, and the investigators impose a health intervention upon one of the groups the design is that of a trial.

Studies based on aggregated data are commonly referred to as ecological studies.

Mostly, ecological studies are mode of analysis, rather than a design.

Interpretation and application of data are easier when the relationship between the population observed and the target population is understood

RCTs represent the “gold standard” of research designs. They thus provide the most convincing evidence of relationship between exposure and effect..

04/08/23 49research design/ hanan abbas

Page 50: Final Study Design ppt

What are the risk factors for the development of sarcoidosis?

Page 51: Final Study Design ppt

What are the long-term effects of the daily use of topical minoxidil?

Page 52: Final Study Design ppt

Scenario 3

Is there a difference between pediatricians and family

physicians in the practice of neonatal circumcision?

04/08/23 52research design/ hanan abbas

Page 53: Final Study Design ppt

Scenario 4

Does cigarette smoking cause lung cancer?

04/08/23 53research design/ hanan abbas

Page 54: Final Study Design ppt