Retrospective cohort studies: advantages and disadvantagesBMJ 2014; 348 doi: https://doi.org/10.1136/bmj.g1072 (Published 24 January 2014) Cite this as: BMJ 2014;348:g1072
- Philip Sedgwick, reader in medical statistics and medical education1
- 1Centre for Medical and Healthcare Education, St George’s, University of London, London, UK
Researchers investigated whether differences exist between the sexes in the risk of ischaemic stroke in patients with atrial fibrillation.1 A nationwide retrospective cohort study design was used. Data were taken from the Swedish national discharge register. Participants were 100 802 patients with a first diagnosis of atrial fibrillation between 1 July 2005 and 31 December 2008, with a total follow-up of 139 504 years at risk (median 1.2). Information about drug treatment was taken from the Swedish drug register. Patients were excluded if at baseline they were prescribed warfarin, had mitral stenosis, or had previous valvular surgery. Patients who died less than 14 days from baseline were also excluded.
The primary outcome measure was the occurrence of ischaemic stroke. It was reported that ischaemic strokes were more common in women than in men (6.2% v 4.2% per year; P<0.0001). The unadjusted hazard ratio of ischaemic stroke for women compared with men was 1.47 (95% confidence 1.40 to 1.54). After adjustment for 35 co-risk factors for stroke, an increased risk of stroke in women remained (1.18, 1.12 to 1.24). It was concluded that women with atrial fibrillation have a moderately increased risk of stroke compared with men, and thus, female sex should be considered when making decisions about anticoagulation treatment.
Which of the following statements, if any, are true?
a) Patient data were collected retrospectively
b) Selection bias was minimised
c) Recall bias was minimised
d) It was possible to estimate the population at risk
e) Causality could be inferred from the association between female sex and ischaemic stroke in patients with atrial fibrillation
Statements b, c, and d are true, whereas a and e are false.
The aim of the study was to investigate whether differences exist between the sexes in the risk of ischaemic stroke in patients with …