The Need for Causal Inference

One of the later trends in the field of machine learning is the concept of causal inference or causality. What is the impact of one feature (called treatment) on another feature (called response or outcome)? Causal inference is by no means a new method -- it is known for at least 50 years and used in the social sciences, economics, and political sciences for a long time already. What is the impact of administering a pill on the patients' probability of survival? Here, the treatment is binary (give pill?