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. Summary statistics for bilirubin level (μmol/L) at baseline by treatment group (primary biliarycirrhosis trial).Statistics Placebo AzathioprineNo. of patients 94 97Mean 53.75 67.40Standard deviation 70.50 88.95Median 30.90 38.02Minimum 5.13 7.24Maximum 436.52 537.03Table 2. Summary statistics for survival outcome by treatment group (primary biliary cirrhosis trial).Statistics Placebo AzathioprineNo. of patients 94 97No. of deaths 49 47Person-years 357 393.54Incidence rate (/100) 13.73 11.94the impact of the bilirubin level on the primary endpoint using the Cox proportionalhazards model (see Chapter 21 for more details).To estimate the treatment effect without considering the baseline bilirubinimbalance in the analysis, we could use a Cox model with treatment only as anexplanatory variable. This can be written as follows:h i(t) = h 0(t)exp(b 1Treatment i)where:• h i(t) is the hazard of death for patient i• Treatment iis the treatment the patient received (1 = azathioprine,0 = placebo)• e b 1 is the hazard ratio of death between azathioprine and placeboParameter estimates for the above model and the PBC trial are reported in Table 3.The estimated unadjusted treatment effect is 0.86 with 95% confidence interval (CI)(0.57, 1.28), P = 0.455, suggesting that the active treatment did not significantlyimprove survival.289

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

Saved successfully!

Ooh no, something went wrong!