Title
Introduction
We demonstrate the application of our software using the data from a randomized controlled trial of the effect of an Angiotensin-converting-enzyme inhibitor (ACE inhibitor) called enalapril on survival in patients with reduced left ventricular ejection fraction and congestive heart failure (CHF).
Patients were randomized to either placebo (n=1284) or enalapril (n=1285).
The study showed that enalapril sigificantly reduced mortality and hospitalizations for heart failure. In the original paper the trial investigators (NEJM 1991) reported an overall treatment effect of 16% reduction in relative risk of mortality (95% CI: 5% - 26%, p-value = .0036). They also examined the consistency of this overall treatment effect in subgroups which were defined a priori in the study protocol.
The subgroups were defined according to the following 5 characteristics measured at baseline:k
- sodium level, by tertiles
- whether or not patients used vasodilators other than ACE inhibitors
- ejection fraction, by tertiles
- the cause of CHF (ischemia or other/unknown)
- functional status as per New York Heart Association (NYHA) classes (I - IV)
Analysis Plan
Here we conduct analyses using multivariate subgroups, i.e. subgroups defined using multiple baseline characteristics. If we used the original 5 charateristics, we will end up with 144 subgroups (144 = 3 x 2 x 3 x 2 x 4). This makes the analyses a bit unwieldy, even though our software can easily handle this complexity.
For the purposes of demonstrating the software, we considered multivariate subgroups defined by only 3 characteristics:
- sodium level, by tertiles
- whether or not patients used vasodilators other than ACE inhibitors
- ejection fraction, by tertiles
Reference
Solvd Investigators and others, Effect of enalapril on survival in patients with reduced left ventricular ejection fraction and congestive heart failure. N Engl j Med. 1991 ;325:293–302.