We hereby apply for a HEiKA project funding for a cooperation between the Karlsruhe Institute of Technology (KIT), Institute for Biomedical Technology (IBT) and the University Hospital of Heidelberg (UNI-HD), Institute for Medical Biometry and Informatics, Research Group Medical Informatics (IMBI) and Department of Oral and Maxillofacial Surgery (CMF) and Department of Orthodontics. The goal of this project is to explore and develop an innovative application for convolutional neural networks (CNN) in clinical medicine. As both universities excel in their field of interest and research, we are looking forward using the existing knowledge to develop the basis to a self-adaptive digital model of a patient, which we refer to as a digital twin. The topic of the initial research project is to lay the groundwork to a deep learning based diagnostic tool, that shall be trained to determine severe growth anomalies such as premature cranial synostosis of the face and skull in infants from mild growth anomalies and classify those conditions. Additionally, to engage a clinically relevant question in a scientifically not predescribed way, we are looking into the training of neural networks (NNs) for other questions of clinical relevance such as diagnostic or predictive clinical models. The gained knowledge and established workflows will lay the basis to a larger scaled research project. As research on artificial intelligence (AI) in medicine is a growing topic, the practical but essential questions of data handling are the basis for further projects. The results are published from a clinical and computational point of view. The findings will then be used to submit a successful Deutsche Forschungsgemeinschaft (DFG) application. The working title of this following DFG project is “The patients digital twin – a deep learning based model for diagnostics and prediction of clinical data” and the application for a consequential third-party funding is a part of the research project.