Abstract:
|
Clinical trials for rare diseases typically cannot recruit many patients, and yet still need to achieve sufficient statistical power to show efficacy. Predictive models can be used in a variety of ways to boost power in trials, but are not without potential pitfalls. The amyotrophic lateral sclerosis (ALS) community provides one instance of a rare disease with established predictive models (via “ice bucket challenge”-funded data competitions), as well as some examples of how these models are being implemented. These examples will be discussed, as well as their potential pitfalls, with looks to the future for other novel ways to implement predictive models to improve rare disease clinical trials.
|