Clinical decision support (CDS) systems promise to improve the quality of clinical care by helping physicians to make better, more informed decisions efficiently. However, the design and testing of CDS systems for practical medical use is cumbersome. It has been recognized that this may easily lead to a problematic mismatch between the developers' idea of the system and requirements from clinical practice. In this paper, we will present an approach to reduce the complexity of constructing a CDS system. The approach is based on an ontological annotation of data resources, which improves standardization and the semantic processing of data. This, in turn, allows to use data mining tools to automatically create hypotheses for CDS models, which reduces the manual workload in the creation of a new model. The approach is implemented in the context of EU research project p-medicine. A proof of concept implementation on data from an existing Leukemia study is presented.