An agentic LLM reasoning system reached 79.6% agreement with expert consensus on myeloma care questions from longitudinal records, outperforming iterative RAG and full-context baselines by 3.8-4.2 points with larger gains on complex cases.
PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals
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
-
Agentic clinical reasoning over longitudinal myeloma records: a retrospective evaluation against expert consensus
An agentic LLM reasoning system reached 79.6% agreement with expert consensus on myeloma care questions from longitudinal records, outperforming iterative RAG and full-context baselines by 3.8-4.2 points with larger gains on complex cases.