In the 20th century, evidence-based medicine has put clinical practice on much more solid ground. For instance, randomized clinical trials have provided strong evidence on useful interventions, thanks to double-blind treatment application and tests for treatment associations with clinical outcomes. However, precision medicine in the 21st century strives for accurate prediction of what is beneficial for individual patients.1 Prediction, as opposed to association, comes into play when forecasting outcomes that are yet unobserved or hard to obtain.2 The machine-learning community has long cultivated and widely adopted practices that can be used to empirically evaluate successful generalization of extracted models on new individuals. We reinforce calls (eg, Stephan et al3) for wider adoption of statistical procedures that explicitly model and test extrapolation to individuals who have not yet been seen as a crucial avenue to hold up to the promises of precision psychiatry.