Skip to main content

Table 4 Sample size determination and interim analyses

From: Design and rationale of the Procalcitonin Antibiotic Consensus Trial (ProACT), a multicenter randomized trial of procalcitonin antibiotic guidance in lower respiratory tract infection

Sample size 1664
 Determination  H1o: Procalcitonin guideline implementation does not reduce antibiotic exposure by Day 30. (superiority)
 H2o: Procalcitonin guideline implementation increases the proportion of subjects who experience a composite endpoint of adverse outcomes by Day 30, by ≥4.5%. (non-inferiority)
  ▪ Sample size is driven by H2o
  ▪ 4.5% non-inferiority margin
  ▪ ≥ 80% power, 1-sided alpha of 0.05
  ▪ Lost to follow up and composite endpoint rates at 2nd interim data safety monitoring board meeting at ~2/3 accrual (April 2017)
 Interim analyses and stopping rules  Two interim analyses and one final analysis, approximately evenly spaced
 O-Brien and Fleming stopping boundaries