Development, Evaluation, and Deployment of a Multi-Agent System for Thoracic Tumor Board

Computer Science > Artificial Intelligence [Submitted on 14 Apr 2026] Development, Evaluation, and Deployment of a Multi-Agent System for Thoracic Tumor Board Tim Ellis-Caleo, Timothy Keyes, Nerissa Ambers, Faraah Bekheet, Wen-wai Yim, Nikesh Kotecha, Nigam H. Shah, Joel Neal Tumor boards are multidisciplinary conferences dedicated to producing actionable patient care recommendations with live review of primary radiology and pathology data. Succinct patient case summaries are needed to drive efficient and accurate case discussions. We developed a manual AI-based workflow to generate patient summaries to display live at the Stanford Thoracic Tumor board. To improve on this manually intensive process, we developed several automated AI chart summarization methods and evaluated them against physician gold standard summaries and fact-based scoring rubrics. We report these comparative evaluations as well as our deployment of the final state automated AI chart summarization tool along with post-deployment monitoring. We also validate the use of an LLM as a judge evaluation strategy for fact-based scoring. This work is an example of integrating AI-based workflows into routine clinical practice. Comments: 64 pages, 14 figures Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.12161 [cs.AI]   (or arXiv:2604.12161v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.12161 Focus to learn more Submission history From: Timothy Keyes [view email] [v1] Tue, 14 Apr 2026 00:35:40 UTC (4,303 KB) Access Paper: view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)