Journal article · 2026 · Open access

Towards reliable Spanish clinical text de-identification through comparative evaluation of language model approaches

D. Vallejo-Sanchez, Andrés Felipe Giraldo-Forero, Andrés Orozco‐Duque

Journal of Biomedical Semantics, 17(1) · Published 15 July 2026 · DOI 10.1186/s13326-026-00362-9

Open full textCite this paper

In brief

“Towards reliable Spanish clinical text de-identification through comparative evaluation of language model approaches” is a 2026 journal article by D. Vallejo-Sanchez and 2 co-authors, published in Journal of Biomedical Semantics. OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at Journal of Biomedical Semantics.

Citations
0
References
46
Authors
3

Abstract

BACKGROUND: Unstructured clinical narratives in electronic health records contain essential information for healthcare delivery and research. However, the presence of personally identifiable information poses significant privacy risks, which limit the secondary use of data. Therefore, reliable automated de-identification is a prerequisite for the reuse of clinical texts. This study aims to evaluate different strategies for Spanish clinical text de-identification by assessing the performance of language models on synthetic and real-world datasets. METHODS: This study presents a comparative evaluation of de-identification approaches using two datasets in Spanish: MEDDOCAN, a publicly available synthetic corpus, and ObstEHR, real-world clinical narratives from an obstetrics department. Three de-identification strategies were assessed: (i) inference with a pre-trained task-specific model used as-is, (ii) prompt-based inference using locally deployed large language models (LLMs), and (iii) fine-tuned task-specific models. Model performance was evaluated using precision, recall, and F1 score on test sets. In addition, a text preservation metric was introduced to assess prompt-based LLMs, and the impact of training set size was analyzed using progressively larger subsets of annotated ObstEHR data. RESULTS: Models without fine-tuning and prompt-based LLMs showed limited performance, with macro-averaged F1 scores ranging from 0.14 to 0.5 on ObstEHR and from 0.19 to 0.5 on MEDDOCAN. Fine-tuned models achieved higher performance, reaching macro-averaged F1 scores of up to 0.956. Learning curve analyses showed consistently high precision and gradual improvements in recall as the amount of training data increased, with high performance achieved with moderate amounts of annotated data. CONCLUSION: Fine-tuning-based approaches outperform models without task-specific adaptation and prompt-based strategies. Despite their flexibility in generative settings, LLM-based prompt strategies show limited reliability and information preservation in clinical de-identification. Prompt-based LLMs make slight textual modifications that cause token misalignment, leading to a subsequent decrease in evaluation metrics. Therefore, domain-specific fine-tuning remains the most effective strategy for real-world clinical text de-identification.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Vallejo-Sanchez, D., Giraldo-Forero, A. F., & Orozco‐Duque, A. (2026). Towards reliable Spanish clinical text de-identification through comparative evaluation of language model approaches. Journal of Biomedical Semantics, 17(1). https://doi.org/10.1186/s13326-026-00362-9

MLA 9

Vallejo-Sanchez, D., et al. “Towards reliable Spanish clinical text de-identification through comparative evaluation of language model approaches.” Journal of Biomedical Semantics, vol. 17, no. 1, 2026. https://doi.org/10.1186/s13326-026-00362-9.

Chicago

Vallejo-Sanchez, D., Andrés Felipe Giraldo-Forero, and Andrés Orozco‐Duque. 2026. “Towards reliable Spanish clinical text de-identification through comparative evaluation of language model approaches.” Journal of Biomedical Semantics 17 (1). https://doi.org/10.1186/s13326-026-00362-9.

Harvard

Vallejo-Sanchez, D., Giraldo-Forero, A. F. and Orozco‐Duque, A. (2026) ‘Towards reliable Spanish clinical text de-identification through comparative evaluation of language model approaches’, Journal of Biomedical Semantics, 17(1). doi:10.1186/s13326-026-00362-9.

IEEE

D. Vallejo-Sanchez, A. F. Giraldo-Forero, and A. Orozco‐Duque, “Towards reliable Spanish clinical text de-identification through comparative evaluation of language model approaches,” Journal of Biomedical Semantics, vol. 17, no. 1, 2026, doi: 10.1186/s13326-026-00362-9.

BibTeX

@article{vallejosanchez2026towards,
  title     = {{Towards reliable Spanish clinical text de-identification through comparative evaluation of language model approaches}},
  author    = {Vallejo-Sanchez, D. and Giraldo-Forero, Andrés Felipe and Orozco‐Duque, Andrés},
  journal   = {Journal of Biomedical Semantics},
  year      = {2026},
  volume    = {17},
  number    = {1},
  doi       = {10.1186/s13326-026-00362-9},
  url       = {https://doi.org/10.1186/s13326-026-00362-9}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • Spanish language
  • large language models
  • fine-tuning
  • personally identifiable information
  • electronic health records
  • text preservation
  • training data size
  • learning curve

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Vallejo-Sanchez, D., Giraldo-Forero, A. F., & Orozco‐Duque, A. (2026). Towards reliable Spanish clinical text de-identification through comparative evaluation of language model approaches. Journal of Biomedical Semantics, 17(1). https://doi.org/10.1186/s13326-026-00362-9

How many times has this paper been cited?

0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Journal of Biomedical Semantics: sign in and open the full text from this page.

Who wrote this paper?

D. Vallejo-Sanchez, Andrés Felipe Giraldo-Forero, Andrés Orozco‐Duque.

What is the DOI of this paper?

10.1186/s13326-026-00362-9, permanently at https://doi.org/10.1186/s13326-026-00362-9. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.