Karolin J. Paprottka
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Karolin J. Paprottka has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Bastien Le Guellec
Neuroradiology Department, Lille University Hospital, Lille, France
1 shared publication - Benedikt Wiestler
Technical University of Munich
1 shared publication - Constanze Ramschütz
Department of Diagnostic and Interventional Neuroradiology, TUM University Hospital, School of Medicine and Health, Technical University of Munich, Munich, Germany
1 shared publication - Dennis Martin Hedderich
Institute of Diagnostic and Interventional Neuroradiology, TUM University Hospital, Rechts der Isar Hospital, Munich, Germany
1 shared publication - Evamaria Olga Riedel
Department of Neuroradiology, School of Medicine and Health, Technical University of Munich, Munich, Germany
1 shared publication - Felix Busch
School of Medicine and Health, Department of Diagnostic and Interventional Radiology, Klinikum rechts der Isar, TUM University Hospital, Technical University of Munich, Munich, Germany
1 shared publication
Latest Publications
- 1 May 2026
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 319 (2) , e253477
Performing Best When Needed Least: Reader Experience Shapes Accuracy Gains in Large Language Model–assisted Brain MRI Differential Diagnosis
With increasing reader experience, large language model accuracy improved, whereas diagnostic gains from model assistance paradoxically diminished, highlighting the divergence between model performance and clinically relevant benefits for readers.
- 1 May 2026
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 319 (2) , e253477
Performing Best When Needed Least: Reader Experience Shapes Accuracy Gains in Large Language Model–assisted Brain MRI Differential Diagnosis
With increasing reader experience, large language model accuracy improved, whereas diagnostic gains from model assistance paradoxically diminished, highlighting the divergence between model performance and clinically relevant benefits for readers.