Drug exposure risk windows and unexposed comparator groups for cohort studies in pharmacoepidemiology
✍ Scribed by Alex D. McMahon; Josie M. M. Evans; Mark M. McGilchrist; Denis G. McDevitt; Thomas M. Macdonald
- Publisher
- John Wiley and Sons
- Year
- 1998
- Tongue
- English
- Weight
- 103 KB
- Volume
- 7
- Category
- Article
- ISSN
- 1053-8569
No coin nor oath required. For personal study only.
✦ Synopsis
Aim Ð To determine the appropriate size of risk windows in both exposed and unexposed subcohorts.
Method Ð Data was taken from a previous study of upper gastrointestinal haemorrhage and perforation. The length of each prescription for NSAIDs was estimated. The risk was calculated for the duration of a prescription plus increments of À30, À25, . . . , 115, 120 (i.e. 31 increments). Ten unexposed groups were re-sampled for each increment (strati®ed for age and sex), using the same lengths of risk window as the exposed group. Mean risks and rate-ratios were calculated (per thousand person-years).
Results Ð The NSAID risk rose from 3.52 at À30 days to a peak of 5.82 at À15 days, and then decreased gradually to 2.83 at 120 days. Unexposed risk was variable for the negative increments, and decreased gradually from 2.16 at 0 days to 1.54 at 120 days. The rate-ratio rose from 1.55 at À30 days to a peak of 2.85 at À5 days, and then decreased to 1.85 at 120 days.
Conclusion Ð Risk windows should be the same as (or slightly less than) the calculated length of a prescription. Lengthy windows should not be used for unexposed comparator groups (the exposed windows may be randomly allocated).