Metraipolis › archive › dc_12423af4cddc

A Multi-Agent Pipeline for Source-Grounded Synthetic Note Generation from Longitudinal Structured EHR — arXiv:2609.22164

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22164
License (as archived)
CC0-1.0
Archived
2026-10-09T06:49:08.961Z
SHA-256 of the archived text
b1b4320725847d730d2a842a54d65b34d27ebb8cd6835bac630becddffd7e1ef
Stable URL of this page
https://metraipolis.com/documento/dc_12423af4cddc

How to cite

A Multi-Agent Pipeline for Source-Grounded Synthetic Note Generation from Longitudinal Structured EHR — arXiv:2609.22164 — arXiv (en), https://arxiv.org/abs/2609.22164 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_12423af4cddc (Metraipolis archive dc_12423af4cddc, sha256 b1b4320725847d730d2a842a54d65b34d27ebb8cd6835bac630becddffd7e1ef)
BibTeX
@misc{dc12423af4cddc,
  title = {A Multi-Agent Pipeline for Source-Grounded Synthetic Note Generation from Longitudinal Structured EHR — arXiv:2609.22164},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22164},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_12423af4cddc; sha256 b1b4320725847d730d2a842a54d65b34d27ebb8cd6835bac630becddffd7e1ef},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22164. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Structured EHR is abundant but sparse, coded, and difficult to use directly for note-centric clinical modeling. We present MedNotes, a multi-agent synthetic data generation pipeline that converts longitudinal structured EHR into source-grounded clinical note representations under explicit quality control. MedNotes treats structured-data-to-text synthesis as a closed-loop agentic process: a generator proposes a note, evaluator agents diagnose factual, coverage, structural, and hallucination-related failures, and a router accepts, revises, or rejects the draft. On 1,485 EHRSHOT encounters, MedNotes achieves a 91.4% pass rate, with mean factual accuracy of 0.980, completeness of 99.1%, structural fidelity of 0.761, and 0.028 critical hallucinations per encounter. Iterative refinement improves acceptance from 69.4% to 91.4%. The resulting synthetic corpus improves downstream CPT prediction and paragraph-level section prediction when combined with limited real data.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.22164 — 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 2026-10-09T06:48:44.859Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).