Advances in the Web and healthcare data capture technologies have far-reaching benefits for the development of new clinical decision support systems that accelerate decision- making and generate personalized treatments. However, the diversity of healthcare data formats, the lack of computer interpretable representation of medical interventions, and the distribution of reliable medical knowledge sources constitute important barriers to better support the medical decision process. To deal with these issues, we propose the Treatment Plan Ontology (TPO) that formalizes medical interventions, and allows medical systems sharing and reasoning over them. This knowledge together with the acquired patient data are then reused by the autonomic processes that we have developed in order to timely detect anomalie s and support the physicians in personalizing the patient treatment at the right time. We demonstrate the system efficiency through a use case for managing hyperglycemia in type 2 diabetes.