Machine Learning, Health Disparities, and Causal Reasoning

Rajkomar and colleagues warn us that the introduction of machine-learned predictive algorithms into medicine might inadvertently reinforce or create inequitable treatment of protected groups, for which the computer science community has adopted the terminology of "fairness." They present a taxonomy of pitfalls and an oversight structure to minimize ethical harms. The editorialists discuss the taxonomy and oversight structure Rajkomar and colleagues propose and conclude that no formulaic solution will be sufficient to achieve fairness.

https://ift.tt/2KTry7h