Skip to content
Co-financed by the European Union / Free State of Saxony – ERDF/ESF logoEurope funds Saxony – co-financed by the European Union, co-financed by the Free State of Saxony
Synagen
Research

Research that goes into the product

Our team works on making clinical information usable: turning unstructured documents, guidelines and imaging into structured, checkable evidence. The work is published in peer-reviewed venues, and the methods that hold up go into Co-Pilot and SynGuide.

Selected publications

Work by members of our team on medical AI agents, multimodal models, clinical trial matching and guideline retrieval – peer-reviewed in Nature, Nature Cancer, NEJM AI and elsewhere.

Towards autonomous medical artificial intelligence agents
Nature · 2026
Ferber D, Hilgers L, Höper C, Kinny-Köster B, Eckardt J-N, Egger-Heidrich K, Bill M, Schneider MMK, Clusmann J, Kadric L, Oehme M, Mayrhofer-Schmid M, Oeser A, Wölflein G, Wiest IC, Middeke JM, Iafrate AJ, Truhn D, Jäger D, Kather JN.
Read the paper ↗
Development and validation of an autonomous artificial intelligence agent for clinical decision-making in oncology
Nature Cancer · 2025
Ferber D, El Nahhas OSM, Wölflein G, Wiest IC, Clusmann J, Leßmann M-E, Foersch S, Lammert J, Tschochohei M, Jäger D, Salto-Tellez M, Schultz N, Truhn D, Kather JN.
Read the paper ↗
LLM Agents Making Agent Tools
ACL · 2025
Wölflein G, Ferber D, Truhn D, Arandjelović O, Kather JN.
Read the paper ↗
GPT-4 for Information Retrieval and Comparison of Medical Oncology Guidelines
NEJM AI · 2024
Ferber D, Wiest IC, Wölflein G, Ebert MP, Beutel G, Eckardt J-N., Truhn D, Springfeld C, Jäger D, Kather JN.
Read the paper ↗
End-To-End Clinical Trial Matching with Large Language Models
ArXiv · 2024
Ferber D, Hilgers L, Wiest IC, Leßmann M-E, Clusmann J, Neidlinger P, Zhu J, Wölflein G, Lammert J, Tschochohei M, Böhme H, Jäger D, Aldea M, Truhn D, Höper C, Kather JN.
Read the paper ↗
In-context learning enables multimodal large language models to classify cancer pathology images
Nature Communications · 2024
Ferber D, Wölflein G, Wiest IC, Ligero M, Sainath S, Ghaffari Laleh N, El Nahhas OSM, Müller-Franzes G, Jäger D, Truhn D, Kather JN.
Read the paper ↗
Large language models should be used as scientific reasoning engines, not knowledge databases
Nature Medicine · 2023
Truhn D, Reis-Filho JS, Kather JN.
Read the paper ↗

These publications are scientific work by members of the Synagen team. They are not a clinical evaluation or endorsement of Synagen products by the journals named.

Working with research and industry partners

Structured, source-linked clinical data is the basis for cohort analyses, feasibility work and real-world evidence. If you work on similar questions or with real-world oncology data, we would like to hear from you.