Tibor V. Varga is the Deputy Director of Copenhagen Health Complexity Center and an Associate Professor at the University of Copenhagen specializing in epidemiology and health equity. Tibor has experience using big data and AI to address public health challenges, developing predictive models for complex disease and investigating health disparities.
Varga’s current work focuses on AI, epidemiology, and health equity, emphasizing the importance of mitigating biases in data and algorithms to prevent healthcare inequalities. Algorithmic fairness and bias have moved beyond theoretical discussions to real-world applications (e.g., clinical risk prediction models, chatbots “informing” us every step of the way, algorithms that aid hiring, admission, or criminal sentencing processes), making it imperative for epidemiologists to grapple with these issues.
This keynote lecture will tie together systems thinking, complexity science, and artificial intelligence to help the audience navigate in an increasingly confusing landscape of algorithmic decision making in healthcare.
Kerstin Bach is a Professor at the Norwegian University of Science and Technology, the Research Director at the NorwAI Research Center , Deputy Head of the Data and Artificial Intelligence Unit, and a member of the Norwegian Open AI Lab.
Bach is a highly experienced researcher and has worked with AI across several disciplines and industries throughout her career. Her work primarily focuses on developing methods for applied artificial intelligence, including building systems that support complex, knowledge-intensive decisions using heterogeneous data sources. Her research spans several health-related projects, including the management of low back pain, physical activity, sleep, and mental health.
AI is reshaping how we collect, understand, and act on health data: from outbreak detection to personalized prevention. Looking back, we can see both the breakthroughs and blind spots of data-driven models in public health. Looking forward, emerging approaches like self-supervised learning and privacy-preserving collaboration promise to unlock the value of large population studies such as HUNT. This talk will highlight key developments at the intersection of AI and epidemiology and discuss how these methods can enhance, not replace, the analytical strengths of epidemiologic research.
Adam Hulman is an Associate Professor at Aarhus University and a Senior Researcher leading the Machine Learning & Clinical Prediction Lab at Steno Diabetes Aarhus, Aarhus University Hospital, Denmark, where he is leading the area of machine learning and clinical prediction. Hulman has more than a decade of experience working in diabetes epidemiology and is an Associate Editor of Diabetologia.
In his work, Hulman applies machine learning methods to multimodal data from epidemiological cohorts and the healthcare sector to provide clinical insights and more comprehensive profiling of disease risk. This keynote lecture will give examples of how machine learning can be used in epidemiology with a special focus on clinical prediction, as well as provide perspectives on how AI is perceived by patients and the general public.