Health Data Science Day 2025

Comparing calendars, making travel arrangements... Stay tuned!

Here's a hint: Big data. Quantitative genomics. Molecular bioscience. Complex psychiatric disease.

Unlocking the Potential of Health Data: Navigating the Challenges of Predictive Modeling in Clinical Decision-Making

The adoption of AI systems in medicine has become an essential asset for analyzing the vast amounts of multimodal health-related data generated daily. However, several challenges persist, including limited sample sizes, systematic biases, and the lack of interpretable and reliable predictions. To address these challenges, novel machine learning and bioinformatics algorithms are essential to support the analysis of the emerging complex multimodal biomedical data and their transition toward clinical applications. 

Anne-Christin Hauschild heads the Institute for Predictive Deep Learning for Medicine and Healthcare at Justus-Liebig University Gießen. She was previously a junior professor at the Institute of Medical Informatics at the University Medical Center Göttingen and headed the Clinical Decision Support group. Her research is dedicated to developing machine learning methods and systems medicine approaches for analyzing biomedical data and their transfer into clinical practice. 

Her group focuses on integrative analysis of multi-modal medical data, such as electronic patient records, molecular data such as gene and protein expression, and medical imaging data to support disease prediction and therapy optimization. ML technologies have been applied successfully in numerous health research domains, such as oncology, psychiatry, and cardiology. However, several challenges persist, impeding the translation of these advances into research and practice. Specifically, limited sample sizes, data privacy, and systematic biases within individual patient cohorts contribute to data scarcity and heterogeneity in medical registries and biomedical data. Additionally, the lack of interpretable and reliable predictions undermines trust in otherwise highly accurate models. Prof. Hauschilds group aims to address these challenges through employing and developing novel computational architectures and algorithms, including transfer learning to overcome data integration issues and accommodate small sample sizes, online and time-critical event prediction, federated learning for integrating distributed medical datasets and databases, as well as the use of explainable artificial intelligence methods to enhance model and prediction interpretability. 

Artificial Intelligence in Diabetes Research and Care

Adam Hulman is a Senior Researcher leading the Machine Learning & Clinical Prediction Lab at Steno Diabetes Center Aarhus, Aarhus University Hospital, Denmark. He is also an Associate Professor at the Department of Public Health at Aarhus University. He has a PhD and 15 years of experience in working with diabetes epidemiology. His team’s overarching goal is to turn health data into clinical insights and applications by using advanced statistical and machine learning methods. More specifically, the group works on the development and application of deep learning methods to be able to integrate clinical data of different types (tabular, images, time series, voice) in risk prediction of diabetic complications.

He is committed to hearing the users’ voices about AI and to building bridges between diabetes researchers, clinicians and the data science community. Adam is an active academic citizen: steering committee member of the European Diabetes Epidemiology Group, member of the EASD Guidelines Oversight Committee, and chairman of the Danish Data Science Academy’s Cross-academy Collaboration Committee. He is associate editor at Diabetolgia and PLOS Digital Health. He received the Danish Diabetes & Endocrine Academy Education & Networking Award for his outstanding engagement in diabetes research education and training of early-career researchers in 2024. 

Title - To be announced

Didem was at Stanford University as a Marie Skłodowska-Curie Fellow on Human-centered and Sustainable Cyber-physical Systems and at the University of Cambridge as a Research Associate in Cyber-physical Systems. Didem received a Ph.D. in Mechatronics from the Royal Institute of Technology. 

Didem is an Institute of Electrical and Electronics Engineers Senior Member due to significant performance and excellence in science. Didem was also named as part of 100 Women in AI Ethics and Global Top 100 Innovators in Data & Analytics. Didem teaches at Oxford University and the University of Cambridge in a few courses and modules.  

Didem cares about the future of the world and nature. Didem is a computer scientist who aims to make future cyber-physical systems interoperable and sustainable.  An analytical thinker with a passion for design thinking, a researcher with a future perspective, an engineer who likes problems more than solutions, and a teacher who likes to play during lectures, Didem wants to bring new perspectives to designing the future intelligent machines.  

Currently, Didem is an Associate senior lecturer and Assistant Professor at Uppsala University in the Department of Information Technology’s Division of Computer Systems.  

Challenges and Chance of Mining Routine Care Electronic Health Records for Rare Diseases

Hospitals around the globe are gathering data in an increasing pace, yet we are starved for data, in particular when looking at rare diseases. How can that be, where are the roadblocks? The answer is data lack in data standardization, complex regulatory frameworks and also the particularity of rare diseases. In this talk, he will report on the experiences gathered from training machine models on routine care data for rare polyneuropathies and myopathies.

Richard Röttger is a Professor for Bioinformatics at the University of Southern Denmark (SDU) at the Department for Mathematics and Computer Science (IMADA) and head of the Computational Biology Group. He started at SDU in Summer 2014 as Assistant Professor, became Associate Professor in November 2017, and a Full Professor in November 2022. He has since been actively researching various kinds of machine learning of biomedical data. 

He spent a 5 months on Sabbatical leave at the University of Cambridge at the Medical Research Council Laboratory of Molecular Biology (MRC-LMB) in the group of Prof. Madan Babu.

Before joining SDU, Richard received his PhD (Dr. rer. nat.) from the Max-Planck-Institute for Informatics, in Saarbrücken for my work on Active Transitivity Clustering. He was awarded an International Max Planck Research School (IMPRS) PhD fellowship for his research at the Max Planck Institute. Before my PhD studies, he studied computer science at the Technical University of Munich (TUM) and Technology Management at the Center for Digital Technology and Management (CDTM). During his studies he had two research visits at the University of California at Berkeley at the School of Information as well as at the International Computer Science Institute where his diploma thesis originated. His thesis on the completeness of gene regulatory networks was awarded with the prestigious Siemens prize.