Wearable smart electronic devices, intelligent home appliances, smart cities, geographic localization services, internet tracking, electronic financial transactions generate and form an unprecedented data stream about events, actions, even intentions of an individual. The corresponding medical history contains a sequence of physiological parameters, clinical laboratory parameters, and electronic health records. Advanced genetic sequencing technologies can complement this with full inherited genomic information, tissue-specific epigenetic changes, and changes of organ-specific microbiomes. Despite these technological advancements, expected healthspan, time spent without chronic conditions and medications, will decrease further while prevalence of multimorbidity continues to grow in industrial societies.

Artificial Intelligence (AI) and machine learning methods exceeded human-level performance in many image recognition, planning, game playing, and natural language processing tasks. However, scientific discovery boosted by AI is still limited by the fragmentation of healthcare data, such as personal data, patient reported data, and clinical data. In our research, we will develop artificial intelligence methods to learn from distributed data sets while preserving privacy at both personal and institutional levels. Specifically, we will investigate the interaction of diseases, multimorbidity networks, and patient trajectories, with special emphasis on health, healthy aging, and effects of gene-environment interactions and modifiable lifestyle factors. The main application areas will be allergy and diseases of the central nervous system, such as mental diseases and neurodegenerative diseases.