Medical research and health care are facing a fundamental revolution due to increasing digitalization. Fundamental advances in sensor technology and imaging - both in everyday clinical practice and in the private setting - are providing new types of health-related data. The Future Health Laboratory bundles the competencies of Lower Saxony in these areas and provides application-oriented answers to promote innovative solutions in order to establish digital technologies for care and nursing.

Medical research and health care are facing a fundamental revolution due to increasing digitalization. Fundamental advances in sensor technology and imaging - both in everyday clinical practice and in the private setting - are providing new types of health-related data. The trans-sectoral networking of health care data links episodic data sets to heterogeneous data sets that cover the entire life span of citizens. The application of new data analysis technologies to these large data sets enables new approaches to understanding and treating complex diseases. These are not simply the use of new technologies, but fundamental changes in health care, which are represented by individualized care (e.g. precision medicine), new telemedical offers for self-determined life in rural areas, stronger personal responsibility of patients and new market participants.

This development provides new opportunities to meet social challenges such as demographic change, chronic widespread diseases and rare diseases. However, digitization also raises questions, e.g. with regard to ensuring digital participation and competence building in society, the right to privacy and anonymity and other social, ethical and legal issues. The Future Lab for Health bundles Lower Saxony's competencies in these areas and provides application-oriented answers to promote innovative solutions in order to establish digital technologies for care and nursing.

In order to benefit from the use of machine learning techniques, it is necessary to structure, standardize and digitally network data that different stakeholders have collected for different purposes and in different qualities. It is therefore absolutely necessary to ensure that especially highly sensitive patient data remain confidential during and after data analysis and to address several challenges such as the disclosure of anonymity and sensitive characteristics. In addition, current guidelines for maintaining anonymity only contain requirements at the highest level. From a technical point of view, medical data must therefore also be secured in the event of access. L3S contributes to this with various techniques such as "Differential Privacy" and "Distributed Privacy preserving Data Mining" to preserve privacy.