11.07.2015 Views

Clinical Trials

Clinical Trials

Clinical Trials

SHOW MORE
SHOW LESS
  • No tags were found...

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

<strong>Clinical</strong> <strong>Trials</strong>: A Practical Guide ■❚❙❘Table 1. Hormone replacement therapy (HRT) trial example: overall study results.Treatment Improvement in mental function Total number Proportion of womenYes No of women showing improvementNo HRT 64 336 400 16%HRT 96 304 400 24%Odds ratio = 1.66 (95% CI 1.16, 2.36; P < 0.005).Table 2. HRT trial example: improvement in mental function by socioeconomic status and treatment.Socioeconomic Treatment Improvement in mental function Total number Proportion of womenstatus Yes No of women showing improvementHigh No HRT 40 60 100 40%HRT 80 120 200 40%Low No HRT 24 276 300 8%HRT 16 184 200 8%Odds ratio for women in the high socioeconomic status group = 1.00 (95% CI 0.61, 1.63; P = 1.00).Odds ratio for women in the low socioeconomic status group = 1.00 (95% CI 0.52, 1.93; P = 1.00).Mantel–Haenszel estimate of the odds ratio, controlling for the socioeconomic status = 1.00 (95% CI 0.67, 1.48; P = 1.00).HRT = hormone replacement therapy.What causes confounding?We will use an extremely hypothetical example to explain how confounding canoccur in a clinical study. It has been reported that hormone replacement therapy(HRT) improves mental function (such as reasoning and verbal skills) inpostmenopausal women. Therefore, a study to evaluate the effect of HRT onmental function was conducted in 800 postmenopausal women. Half the womenrecruited were allocated to daily HRT, while the remainder were given placebo(the non-HRT group). The researchers evaluated the cognitive function of thewomen 5 years after recruitment, and the primary endpoint was whether mentalfunction was improved or not above a predefined level. The overall results fromthe study are summarized in Table 1.The overall results appear to suggest that while there were women in both groupswhose mental function improved after 5 years, HRT treatment resulted in asignificantly greater proportion of women showing improvement than placebo(24% vs 16%, odds ratio = 1.66 [95% CI 1.16, 2.36; P < 0.005]). However, whenthese data are analyzed by socioeconomic status (using the categories high or lowsocioeconomic status), as in Table 2, a different conclusion emerges.297

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!