Learn more about our Focus Areas

The rapid growth of biomedical data and AI-driven methods raises fundamental ethical challenges. Our research addresses issues such as algorithmic bias and the responsible use of sensitive health information. By integrating ethical reflection into technical development, we strive to ensure that biomedical informatics not only advances scientific innovation but also safeguards trust, fairness, and societal responsibility.

High-quality medical AI depends on data that is not only accurate, but also consistent, connected, and usable across systems. Therefore, we focus on integrating heterogeneous data sources, ensuring interoperability, and advancing the use of open standards. By harmonizing clinical information from clinical records we enable reliable analytics, reproducible research, and scalable AI solutions. This work lays the foundation for transforming fragmented healthcare data into meaningful insights that support better decision-making, improved patient outcomes, and more efficient workflows.

Biosignals are time-series data derived, among others, from the heart, nerves, the brain or muscles. Biosignal research in medicine requires complex collaborative work, starting from the support of efficient clinical flows and data integration processes, through employing advanced engineering methods for signal processing, exploring the low-dimensional signal representations and quality control [...]

Large Language Models are transforming the way we process and understand biomedical data. In our research, we study how these models can be adapted to the specific challenges of medicine and life sciences—for example, by extracting knowledge from clinical records, supporting structured data integration, or assisting healthcare professionals with decision-making. At the same time, we critically assess the limitations of LLMs to ensure their applications remain robust, transparent, and safe for real-world use.