Postdoctoral Researcher
at Bielefeld University
About Me
I am a postdoctoral researcher in computer science working at the Semantic Computing Group at Bielefeld University, Germany. My research focuses on Federated Learning, particularly within the healthcare domain and with a strong emphasis on dynamic participation and explainability. Previously, I contributed to the KINBIOTICS project funded by the German Federal Ministry of Health, which concluded in 2024. Since then, I have continued exploring Federated Learning with a specific focus on its applications in healthcare.
Beyond Federated Learning, I am broadly interested in enhancing medical treatment through data-driven Clinical Decision Support Systems and the use of explainable Artificial Intelligence. My goal is to leverage data science and machine learning techniques to address real-world challenges in healthcare and improve patient outcomes.
Originally from a small town of North Rhine-Westphalia, Germany, I received my PhD at Bielefeld University, my B.Sc. in Business Information Systems at FHDW Paderborn, Germany, and my Master's degree (M.Sc. Business Information Systems, focusing on Data Science) at Paderborn University. During that time, I worked at Bertelsmann SE & Co. KGaA for four years and joined the Social Computing Group of Paderborn University as Student Assistant. Finally, I joined the Semantic Computing Group in October 2021.
My research interests include:
We share some research interests? Feel free to contact me to exchange some ideas!
We present a federated LSTM for early sepsis onset prediction. By enabling variable prediction horizons within a single model, our approach improves early detection performance while reducing computational and communication overhead.
This dissertation introduces Federated Learning Platforms (FLPs), a platform-oriented extension of federated learning designed for dynamic, real-world collaboration. It develops mechanisms for scalable governance, explainable client admission, imbalance-aware training, andlearning under concept drift, transforming federated learning from a static protocol into a continuously evolving, privacy-preserving machine learning platform.
We show how the accuracy of explanations for sepsis onset predictions in a federated learning environment can be improved through secure and privacy-preserving background dataset synthesis.
Courses (Level, Type, Semesters):
