Metraipolis › archive › dc_bec7abea60e4
OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories — arXiv:2609.32810
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32810
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:52:23.530Z
- SHA-256 of the archived text
3cf569c353a8216fe1034dad832021a4099e3c470eaae77fe82240f1137246d2- Stable URL of this page
https://metraipolis.com/documento/dc_bec7abea60e4
How to cite
OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories — arXiv:2609.32810 — arXiv (en), https://arxiv.org/abs/2609.32810 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bec7abea60e4 (Metraipolis archive dc_bec7abea60e4, sha256 3cf569c353a8216fe1034dad832021a4099e3c470eaae77fe82240f1137246d2)
BibTeX
@misc{dcbec7abea60e4,
title = {OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories — arXiv:2609.32810},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32810},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bec7abea60e4; sha256 3cf569c353a8216fe1034dad832021a4099e3c470eaae77fe82240f1137246d2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32810. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multidisciplinary tumor boards integrate multimodal clinical observations and longitudinal patient histories through specialist discussions, yet benchmarks rarely capture these real-world trajectories. We introduce OpenTumorBoard, a benchmark with 611 patient cases and 19,157 discussion turns across ten specialist roles, transcribed from 12,534 minutes of publicly available tumor board recordings on YouTube. The benchmark evaluates two settings: SPECIALIST TURN, in which an LLM responds to a clinically significant question posed during a real discussion, and BOARD SIMULATION, in which it generates an entire back-and-forth discussion and reaches a consensus on therapy recommendations, surgical plans, next actions and clinical trial matching. Evaluation of 14 general-purpose frontier and medical LLMs reveals substantial limitations: the best models score 3.43 out of 5 in clinical equivalence to specialist answers and 2.78 out of 5 in alignment with recorded board conclusions. Supervised finetuning and reinforcement learning improve performance on a held-out test set, suggesting that real-world discussion trajectories can support model adaptation. Three M.D. experts review a subset of the benchmark, finding high information coverage and factuality of patient cases and strong fidelity of extracted consensus conclusions. We will release OpenTumorBoard and its automated curation pipeline to support the development and evaluation of LLMs for multidisciplinary, personalized cancer decision-making. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.32810 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T21:27:08.468Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).