07 Jan 2026
The AI4Prevention scoping workshop brought together experts from academia and practice to rethink the future potential of artificial intelligence for anticipatory and personalized prevention. The workshop focused on interdisciplinary exchange, a shared assessment of the current state of AI technologies, and the development of strategic research themes—guided by a clear message: the time is ripe for AI-based prevention, as long-term affordability of healthcare depends on a paradigm shift toward prevention. Participants jointly developed key guidelines for a position paper and initiated impulses for future collaborations and third-party funded research initiatives. The workshop clearly demonstrated how AI can become a key enabler of a preventive, effective, and future-oriented healthcare system.
Under the title Effective (Digital) Prevention, the workshop focused on how digital technologies can make prevention smarter, more effective, and more equitable. Experts from public health, AI research, and prevention science explored how AI-based pattern recognition, systematic horizon scanning, and innovative data models can help to identify and predict successful conditions for prevention at an early stage. The participants jointly developed new taxonomies, predictive models, and decision-support tools that facilitate the transfer of evidence and enable the adaptation of prevention strategies to different contexts. In doing so, the workshop paved the way toward a shared knowledge infrastructure, laying the foundation for the future of digitally supported prevention.
How can health and disease trajectories be predicted across the entire lifespan? The Artificial Intelligence through the Lifespan workshop addressed this very question. The focus was on how continuously collected biosignal data can be leveraged to obtain a more comprehensive understanding of health and disease. The workshop presented methods for harmonizing incomplete data, modeling temporal disease trajectories, and simultaneously providing explainable and transparent AI-based decisions. These approaches aim to enable precise predictions, improve understanding of disease mechanisms, and elevate personalized prevention and lifelong health monitoring to a data-driven level.
The AI Toolbox Hackathon & Strategic Workshop focused on concrete research questions in artificial intelligence for healthcare, bringing together interdisciplinary expertise and practice-oriented challenges. Through interactive sessions, participants developed prototypes and concepts, including explainable AI approaches to enhance model transparency and interpretability, fair and generalizable algorithms capable of reliably handling biased or incomplete data, and robust neural networks that are more resilient to perturbations. Beyond developing technical solutions, the workshop aimed to strengthen the scientific network, foster exchange between research institutions, and make ideas for follow-up projects visible. In doing so, the workshop laid the foundation for the next generation of AI applications in healthcare that are both innovative and practice-oriented.
