Metraipolis › archive › dc_b5fd894fa919

RAG-TRACE: Tracing Measurement Evidence and Diagnostic Completeness in AI-Generated ECG Reports — arXiv:2611.01409

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01409
License (as archived)
CC0-1.0
Archived
2026-11-03T11:10:26.848Z
SHA-256 of the archived text
ecaa090ecb6c316066dd24003ec4b9c208d8e9a2b93476fd3e84df06f7ec76d6
Stable URL of this page
https://metraipolis.com/documento/dc_b5fd894fa919

How to cite

RAG-TRACE: Tracing Measurement Evidence and Diagnostic Completeness in AI-Generated ECG Reports — arXiv:2611.01409 — arXiv (en), https://arxiv.org/abs/2611.01409 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b5fd894fa919 (Metraipolis archive dc_b5fd894fa919, sha256 ecaa090ecb6c316066dd24003ec4b9c208d8e9a2b93476fd3e84df06f7ec76d6)
BibTeX
@misc{dcb5fd894fa919,
  title = {RAG-TRACE: Tracing Measurement Evidence and Diagnostic Completeness in AI-Generated ECG Reports — arXiv:2611.01409},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01409},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b5fd894fa919; sha256 ecaa090ecb6c316066dd24003ec4b9c208d8e9a2b93476fd3e84df06f7ec76d6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01409. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Purpose: Retrieval-augmented generation (RAG) can introduce electrocardiogram (ECG) criteria that lack patient-specific measurement support. This study evaluates the reliability of retrieved diagnostic criteria in AI-generated ECG reports. Methods: We analyzed 1,083 human-validated PTB-XL patient records using a library of 47 criteria cards, including 33 without numeric verification rules. Language models generated structured reports with and without retrieval. Criterion applicability was evaluated using Marquette 12SL measurements, with independent assessment using Uni-G and comparison against expert-validated diagnostic labels. Results: Keyword retrieval introduced untestable or measurement-disconfirmed criteria in 46.8% of GPT-4.1-mini reports. A deterministic verification rule withdrew 647 criterion applications, including 639 without numeric checks, while preserving 268 of 269 applications independently supported by Uni-G. Restricting retrieval to 14 testable criteria reduced the initial unsupported-criterion rate to 13.8%. Under matched instructions and an identical output schema, retrieval increased unsupported-criterion reports from 17.4% to 31.1%, while hypertrophy recall remained unchanged at 62.6%. Conclusion: These findings identify a fundamental limitation of retrieval-based clinical report generation: retrieved criteria do not necessarily provide valid patient-specific evidence. Measurement-based verification can reduce unsupported criterion applications, but diagnostic validity requires independent assessment.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.01409 — 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 2026-11-03T10:59:52.299Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).