Exercise constitutes an important intervention aiming to improve health and quality of life for several categories of patients. Personalized exercise prescription is a rather complicated issue, requiring several aspects to be taken into account, e.g. patient's medical history and response to exercise, medication treatment, personal preferences, etc. The present work proposes an ontology-based framework designed to facilitate healthcare professionals in personalized exercise prescription. The framework encapsulates the necessary domain knowledge and the appropriate inference logic, so as to generate exercise plan suggestions based on patient's profile. It also supports readjustments of a prescribed plan according to the patient's response with respect to goal achievement and changes in physical-medical status. An instantiation of the proposed framework for cardiac rehabilitation illustrates the virtue and the applicability of this work.