Besides functional improvement the aesthetic outcome is a major concerns of patients undergoing orthognatic surgeries. As a consequence the simulation of the soft-tissue development became a standard procedure in planning this kind of interventions. In this paper we propose an efficient modeling approach to define the position of the hard-tissue segments (maxilla and mandible) on the basis of the desired facial appearance – in other words: a backward planning for orthognatic surgery. The method features an inverse modeling paradigm. It is presented under a clinically-oriented framework that employs a statistical shape model of the skull to automate the task of bone segmentation and to seemingly encode mechanical, surgical and simulation-specific information. To evaluate the proposed planning approach, the predicted osteotomy plan of six clinical cases that underwent CMF surgery were compared to the real clinical plan. Thereafter, simulated soft-tissue outcomes were compared using prediction and the real surgical plan. This preliminary retrospective comparison of both – osteotomy planning and facial outlook – shows a good correspondance and thereby underlines the potential of our application to serve as a new tool for planning orthognatic surgeries.