Over 800 000 people die due to suicide every year and it is estimated that for each suicide there may have been more than 20 others attempting suicide, involving huge human and societal costs. In recent years, digital tools have changed the way data are collected on patients. We present the main results of a comprehensive data mining process carried out on a sample of suicidal patients from two European hospitals. The first objective is to identify groups of similar patients and the second objective is to identify risk factors associated with the number of attempts. Unsupervised methods (ACM and clustering) and supervised methods (regression trees) are applied to address these two research objectives. The results highlight the high potential of data mining for descriptive or explanatory purposes.