Comment on "Black Box Prediction Methods in Sports Medicine Deserve a Red Card for Reckless Practice: A Change of Tactics is Needed to Advance Athlete Care"

Abstract

In this paper we examine the claims made by Bullock et. al. on the applicability of black-box injury risk approaches in the sports injury domain. Overall, we agree that transparency is necessary for Machine Learning models to be useful in this field. However, there are areas of research that address precisely the concerns of the authors and strongly temper their conclusions. In the following we look at how these issues are being tackled by the Machine Learning community.