This document discusses medical data mining of Danish healthcare registries. It describes how Denmark has national healthcare registries containing data on all hospital contacts, prescriptions, and more for its entire population since 1968. This structured data can be mined to study diagnosis trajectories, comorbidities, and adverse drug reactions at a population level while accounting for confounding factors. The document also discusses mining of unstructured free-text data using natural language processing to identify mentions of diseases, drugs, and adverse events, and how this can provide additional insights when combined with structured data analyses.