Emulating a Novel Clinical Trial Using Existing Observational Data. Predicting Results of the PreVent Study

What is it about?

Randomized experiments are widely considered to be the most definitive way to answer clinical questions that compare treatments. However, they are expensive and time-consuming. Existing data and modern statistical methods can be used to 'emulate' a randomized experiment. In this paper, we showed that such methods can be used with previously collected data to closely predict the results of a randomized experiment.

Featured Image