Data-driven Healthcare

Group Leader: Dr. med., Dr. sc. nat. Michael Havranek, MD/PhD

The "Data-Driven Healthcare" research group focuses on leveraging health data to enhance healthcare quality, reduce costs, and optimize care processes and systems. The group applies advanced data science and machine learning techniques to both routinely collected data—such as electronic medical records—and newer, emerging sources like wearable technology data.

A particular area of expertise is healthcare quality assessment and cost analysis, with a focus on hospital benchmarking and provider comparisons. The group’s work emphasizes the generation of real-world evidence to support data-driven decision-making in a learning health system. Through applied and methodological research, the group aims to foster innovation and deliver meaningful insights to improve healthcare for individuals and society.

Machine Learning in Healthcare

Group Leader: Ass.-Prof. Christian Baumgartner, PhD

The "Machine Learning in Healthcare" research group is dedicated to improving patient outcomes through the application of machine learning and data science, with a particular emphasis on medical image analysis. Although those technologies are widely used in areas such as voice recognition and fraud detection, their integration into clinical practice remains limited due to the high demands for reliability, robustness, and interpretability in healthcare. To address this, we focus on developing machine learning methods that are not only accurate, but also safe, explainable, and clinically applicable. Our work spans a range of topics including uncertainty estimation, interpretable and human-in-the-loop systems, generative modelling on large-scale medical datasets, and meta-learning approaches for settings with limited data. By bridging the gap between cutting-edge machine learning and the realities of clinical practice, we aim to unlock the full potential of machine learning to support more effective, transparent, and trustworthy healthcare.

Functioning Epidemiology

Group Leader: Ass.-Prof. Adrian Martinez de la Torre, PhD

The "Functioning Epidemiology" group conducts research to advance the understanding of human functioning across health, disease, and rehabilitation. We integrate real-world data, advanced analytics, and clinical insight to generate evidence that supports person-centered care and strengthens health systems. Our work focuses on four pillars: developing functioning-based methods for decision-making at clinical, organizational, and policy levels; improving rehabilitation through predictive modeling and effectiveness research; investigating spinal cord injury to understand recovery and inform international care models; and applying functioning principles in sports rehabilitation for injury prevention and return-to-play strategies. Additional projects address circadian rhythms and fertility, vaccination policy, and pharmacoepidemiology, broadening our impact across clinical and public health domains.

Further information on the projects of the research groups can be found under Selected projects. To the contact details of the groups.