Purpose of review. Machine learning (ML) is an artificial intelligence technique that allows computers to perform a task without being explicitly programmed. ML can be used to assist diagnosis and prognosis of brain disorders. While the earliest papers date from more than ten years ago, research increases at a very fast pace. Recent findings. Recent works using ML for diagnosis have moved from classification of a given disease versus controls to differential diagnosis. Intense research has been devoted to the prediction of the future patient state. While a lot of earlier works focused on neuroimaging as data source, the current trend is on the integration of multimodal. In terms of targeted diseases, dementia remains dominant, but approaches have been developed for a wide variety of neurological and psychiatric diseases. Summary. ML is extremely promising for assisting diagnosis and prognosis in brain disorders. Nevertheless, we argue that key challenges remain to be addressed by the community for bringing these tools in clinical routine: good practices regarding validation and reproducible research need to be more widely adopted; extensive generalization studies are required; interpretable models are needed to overcome the limitations of black-box approaches.