Abstract
Mental disorders are highly prevalent conditions, causing a substantial burden of disease worldwide. Research gaps encompass their etiology, classification and optimization of treatment approaches based on neuroscientific knowledge. Novel methodological developments such as multivariate pattern recognition, embedded within a machine learning framework, bear potential inform scientists and clinicians by deriving predictions on the classification, prognosis or treatment outcome (theranostics) for individual patients, thus paving the way for precision psychotherapy and psychiatry. This lecture will give a brief introduction on the basics of predictive analytics, major methodological caveats and some examples on how we can apply this method to patients with mental disorders. Future perspective for neuroscience-informed mental health research developments are discussed.