Fig. 2
From: From algorithms to action: improving patient care requires causality
Illustration of the difference between outcome prediction model accuracy and its value for treatment decision making. Validation of an outcome prediction model following the AJCC checklist leads to a reliable estimate of the outcome prediction model’s accuracy if the treatment policy does not change. However, because the outcome prediction model relies on a fixed historic treatment policy, prediction accuracy does not imply value for decision making, as visualized with the gap. This gap can only be bridged with causality