Peer-Reviewed Publication
NPJ Precis Oncol2026;10(1)October 14, 2026Journal Article
Skill-guided agentic reasoning enables longitudinal synthesis of myeloma records at expert-level concordance.
Johannes Moll1,2,3, Jannik Lübberstedt4, Christoph Nuernbergk5, Jacob Stroh5, Luisa Mertens5, Anna Purcarea5, Christopher Zirn4, Zeineb Benchaaben4, Fabian Drexel6,4, Hartmut Häntze4,7, Anirudh Narayanan4,7, Friedrich Puttkammer4,7, Andrei Zhukov8, Jacqueline Lammert9,10, Sebastian Ziegelmayer4, Markus Graf4, Marion Högner5, Marcus Makowski4, Florian Bassermann5,11,12,13, Lisa C Adams4, Jiazhen Pan6,14,15, Daniel Rueckert6,15,16, Krischan Braitsch5, Keno K Bressem4,17,18,19
1Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM) and TUM University Hospital, Munich, Germany. johannes.moll@tum.de.
2Technical University of Munich, School of Medicine and Health, TUM University Hospital, Klinikum rechts der Isar, Department of Diagnostic and Interventional Radiology, Munich, Germany. johannes.moll@tum.de.
3Technical University of Munich, School of Medicine and Health, TUM University Hospital, German Heart Center, Department of Cardiovascular Radiology and Nuclear Medicine, Munich, Germany. johannes.moll@tum.de.
4Technical University of Munich, School of Medicine and Health, TUM University Hospital, Klinikum rechts der Isar, Department of Diagnostic and Interventional Radiology, Munich, Germany.
5Technical University of Munich, School of Medicine and Health, TUM University Hospital, Klinikum rechts der Isar, Department of Medicine III, Munich, Germany.
6Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM) and TUM University Hospital, Munich, Germany.
7Department of Radiology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany.
8Department of Gastroenterology, Infectious Diseases and Rheumatology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany.
9Chair of Medical Informatics, Institute of Artificial Intelligence in Medicine and Healthcare, TUM School of Medicine and Health, Technical University of Munich, Munich, Germany.
10Clinical Department of Gynecology, TUM University Hospital, TUM School of Medicine and Health, Munich, Germany.
11TranslaTUM, Center for Translational Cancer Research, Technical University of Munich, Munich, Germany.
12Deutsches Konsortium für Translationale Krebsforschung, Heidelberg, Germany.
13Bavarian Cancer Research Center, Munich, Germany.
14Department of Engineering Science, University of Oxford, Oxford, UK.
15Munich Center for Machine Learning (MCML), Munich, Germany.
16Department of Computing, Imperial College London, London, UK.
17National Center for Tumor Diseases West, Essen, Germany.
18Institute of Artificial Intelligence in Medicine, University Hospital Essen, Essen, Germany.
19Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Essen, Germany.
Abstract
Patients with multiple myeloma accumulate hundreds of clinical documents over years of sequential therapy, and every treatment decision depends on synthesis across that history. Whether large language model-based systems can match expert agreement on this task, and where they fail, has not been established. On longitudinal records of 811 patients treated over 25 years (44,962 documents and 1,334,6…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans