A multi-agent LLM system for automated chart summarization was developed, evaluated against physician gold standards, deployed at Stanford Thoracic Tumor Board, and monitored post-deployment, with validation of LLM-as-judge scoring.
type": "DocumentReference
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Development, Evaluation, and Deployment of a Multi-Agent System for Thoracic Tumor Board
A multi-agent LLM system for automated chart summarization was developed, evaluated against physician gold standards, deployed at Stanford Thoracic Tumor Board, and monitored post-deployment, with validation of LLM-as-judge scoring.