Preliminary Program

Keynote Abstracts

Keynote Session 1

Multimodal Data Exploration with Agentic AI Kurt Stockinger, Zurich University of Applied Sciences

Generative AI and Large Language Models (LLMs) are increasingly shaping the future of digital health, biomedical research, and clinical care. Despite their promise, a major challenge remains their tendency to generate inaccurate or non-factual information, commonly referred to as hallucinations. In this talk, we will present work in agentic AI for the exploration and analysis of complex, multimodal health data. Our approach enables the integration of heterogeneous data sources, including structured clinical records, unstructured text, and medical imaging. We will demonstrate how agentic AI systems can interact reliably with these diverse datasets through natural language queries, allowing researchers and healthcare professionals to explore patient cohorts, identify clinically relevant patterns across modalities, and generate actionable insights.

Biography

Prof. Dr. Kurt Stockinger is Professor of Computer Science, Head of the Intelligent Information Systems Group and Board Member of the Quantum Lab at Zurich University of Applied Sciences. He is also affiliated with University of Zurich. Kurt Stockinger’s research focuses on Data Science with emphasis on Big Data, Natural Language Query Processing, Query Optimization and Quantum Computing. Essentially, his research interests are at the intersection of information systems, natural language processing and machine learning. Previously Kurt Stockinger was (1) a visiting scholar at University of Washington in Seattle, Washington, USA, (2) he worked at Credit Suisse in Zurich, Switzerland, (3) at Lawrence Berkeley National Laboratory in Berkeley, California, USA, (4) at California Institute of Technology in Pasadena, California, USA, (5) as well as at CERN in Geneva, Switzerland. He holds a Ph.D. in computer science from CERN / University of Vienna.

Keynote Session 3

From Hype to Implementation – Why Infrastructure, Processes and Space Decide the Economics

Artificial intelligence in healthcare is often discussed primarily as a question of technology or data. In clinical practice, however, its economic value is ultimately determined by implementation: by adapted processes, viable operating models, appropriate infrastructure, and spaces that enable new ways of working.

In his keynote, Valentin Simonett will explain why AI in Clinics should not be understood as an isolated IT project, but as a transformation challenge at the intersection of clinical practice, operations, infrastructure and planning. The talk will bridge the gap between digital innovation and practical implementation in everyday hospital and laboratory environments.

Biography

Valentin Simonett is Managing Director and Founder of Evomed AG, a company specialising in hospital and laboratory planning. He holds an engineering degree from EPFL and an MAS in Business Engineering Management. His work focuses on the planning and implementation of healthcare and laboratory environments.