Observational studies and STROBE

Gary Collins and Elaine Beller

Observational studies

• Observational (epidemiological) studies– large proportion of published research

• Ensuring transparent reporting particularly important– vulnerable to bias and confounding– findings are often over-interpreted– findings often generate health scares

Types of Observational Study Design

• Cohort

• Case-control

• Cross-sectional

Bias and confoundingSelection bias• In a cohort study, are participants in the exposed and unexposed groups similar in all

important respects except for the exposure?• In a case-control study, are cases and controls similar in all important respects except for the

disease in question?

Information bias• In a cohort study, is information about outcome obtained in the same way for those exposed

and unexposed?• In a case-control study, is information about exposure gathered in the same way for cases

and controls?

Confounding• Could the results be accounted for by the presence of a factor associated with both the

exposure and the outcome (but not directly involved in the causal pathway)?• e.g. people who carry matches are more likely to develop lung cancer, but smoking is the

confounding factor

STROBE

Scope of STROBE

• Epidemiological research comprises several study designs and multiple topic areas

• STROBE initially covers 3 broad study types– Case-control, cohort, cross-sectional studies– Adopted/endorsed by many journals

• STROBE extensions cover, e.g.– Genetic association studies (STREGA)– Molecular epidemiology (STROBE-ME)

STROBE Checklist

• Checklist of 22 items that should be addressed somewhere in the research article

• Single checklist with 4 items that have separate sub-items depending on study design (cohort, case-control, cross-sectional)

• Separate checklists depending on study design– Available at www.strobe-statement.org

STROBE Checklist [OVERVIEW]1. TITLE and ABSTRACTINTRODUCTION2. Background/rationale3. Objectives METHODS4. Study design5. Setting6. Participants 7. Variables8. Data

sources/measurement9. Bias10. Study size11. Quantitative variables12. Statistical methods

RESULTS13. Participants 14. Descriptive data15. Outcome data 16. Main results 17. Other analysesDISCUSSION18. Key results19. Limitations20. Interpretation 21. Generalisability OTHER INFORMATION22. Funding

Design-specific items

• Participants

• Statistical methods

• Descriptive data

• Outcome data

Participants (item 6a)• Cohort study:

– give eligibility criteria– give sources and methods of selection of participants– describe follow-up methods

• Case-control study:– give eligibility criteria– give sources and methods of case ascertainment and control selection– give rationale for the choices of cases and controls

• Cross-sectional study:– give eligibility criteria– give sources and methods of participant selection

Example• ‘‘We retrospectively identified patients with a principal

diagnosis of myocardial infarction (code 410) according to the International Classification of Diseases, 9th Revision, Clinical Modification, from codes designating discharge diagnoses, excluding the codes with a fifth digit of 2, which designates a subsequent episode of care (. . .) A random sample of the entire Medicare cohort with myocardial infarction from February 1994 to July 1995 was selected (...) To be eligible, patients had to present to the hospital after at least 30 minutes but less than 12 hours of chest pain and had to have ST-segment elevation of at least 1 mm on two contiguous leads on the initial electrocardiogram’’ [Canto et al, N Engl J Med 2000]

Statistical methods (item 12)

• Cohort study– explain how loss to follow-up was addressed

• Case-control study– explain how matching of cases and controls was

addressed

• Cross-sectional study– describe analytical methods taking account of

sampling strategy

Example

• ‘‘We used McNemar’s test, paired t test, and conditional logistic regression analysis to compare dementia patients with their matched controls for cardiovascular risk factors, the occurrence of spontaneous cerebral emboli, carotid disease, and venous to arterial circulation shunt’’

Descriptive data (item 14)

• For a cohort study– Summarise follow-up time (e.g. average and total

amount)

‘‘During the 4366 person-years of follow-up(median 5.4, maximum 8.3 years), 265 subjects were diagnosed as having dementia, including 202 with Alzheimer’s disease’’

Outcome data (item 15)

• Cohort study– Report number of outcome events or summary

measures over time• Case-control study

– Reporting numbers in each exposure category, or summary measures of exposure

• Cross-sectional study– Report numbers of outcome events of summary

measures

Variables (item 7)

• Clearly define all outcomes, exposures, predictors, potential confounders, and effect modifiers. Give diagnostic criteria, if applicable – Helps readers know what has been adjusted for– Help readers know what hasn’t been adjusted for

• Important confounders / prognostic variables

Example• ‘‘Only major congenital malformations were included

in the analyses. Minor anomalies were excluded according to the exclusion list of European Registration of Congenital Anomalies (EUROCAT). If a child had more than one major congenital malformation of one organ system, those malformations were treated as one outcome in the analyses by organ system (...) In the statistical analyses, factors considered potential confounders were maternal age at delivery and number of previous parities. Factors considered potential effect modifiers were maternal age at reimbursement for antiepileptic medication and maternal age at delivery’’

Reporting & Conduct

• Adhering to STROBE ensures all key important information is reported

• Helps researchers include results from an observational study in a systematic review

• STROBE does not prescribe how to conduct research– But clearly there are snippets of good practice

emphasised in the long Explanation & Elaboration paper [an invaluable resource]

STRATOS (www.stratos-initiative.org)