Metraipolis › archive › dc_10c8df563235

Meddies-PII: A Multilingual Framework for Personally Identifiable Information Extraction in Clinical De-identification — arXiv:2609.12544

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12544
License (as archived)
CC0-1.0
Archived
2026-10-16T03:03:28.373Z
SHA-256 of the archived text
a900dc32dafffa7078a2ba2146284207dab06029bb344fad2823d2be3cdb5af1
Stable URL of this page
https://metraipolis.com/documento/dc_10c8df563235

How to cite

Meddies-PII: A Multilingual Framework for Personally Identifiable Information Extraction in Clinical De-identification — arXiv:2609.12544 — arXiv (en), https://arxiv.org/abs/2609.12544 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_10c8df563235 (Metraipolis archive dc_10c8df563235, sha256 a900dc32dafffa7078a2ba2146284207dab06029bb344fad2823d2be3cdb5af1)
BibTeX
@misc{dc10c8df563235,
  title = {Meddies-PII: A Multilingual Framework for Personally Identifiable Information Extraction in Clinical De-identification — arXiv:2609.12544},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12544},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_10c8df563235; sha256 a900dc32dafffa7078a2ba2146284207dab06029bb344fad2823d2be3cdb5af1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12544. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Clinical de-identification relies on accurately identifying personally identifiable information (PII). However, manually annotated datasets are costly to construct, while existing synthetic alternatives often provide limited details about their generation process or rely on relatively simple synthesis strategies. We introduce Meddies-PII-Dataset, a corpus of one million synthetic clinical documents spanning seventeen languages and nine PII labels. The documents are generated using attribute-conditioned prompts and validated through thirteen deterministic gates that enforce structural and annotation consistency. To evaluate the dataset's utility, we train Meddies-PII-Model, a BIOES token classifier, and compare it with existing PII extraction systems using exact-match entity-level F1. Meddies-PII-Model achieves the highest performance among the evaluated systems on all reported benchmarks, with a mean F1 of 0.827 across fifteen external benchmarks, compared with 0.658 for the strongest baseline. Upon acceptance, we will publicly release the dataset, benchmark suite, model, generation framework, and evaluation code to support research on multilingual clinical de-identification.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.12544 — 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 2026-10-16T02:51:27.921Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).