Dr. Markus Wenzel is a senior scientist in the Artificial Intelligence department of Fraunhofer HHI in Berlin, where he applies machine learning to the life sciences and medicine. Dr. Wenzel has contributed to explainable AI for protein language models and to machine learning in brain-computer-interfacing and medical imaging, as published in 20 journal papers. Currently, he is involved in the Testing and Experimentation Facility for Health AI and Robotics (TEF-Health) and the G-TERM-AI project (with Fraunhofer USA Center Mid-Atlantic CMA). Recently, we have published "MADE: A Living Benchmark for Multi-Label Text Classification with Uncertainty Quantification of Medical Device Adverse Events" (accepted at ACL 2026). This paper benchmarks large language models on the classification of medical device incident reports, with a particular focus on the models' uncertainty quantification capabilities.