@inproceedings{brunello-etal-2026-comparative,
title = "A Comparative Study of Approaches to Anonymization of Clinical Free Text in {S}panish",
author = "Brunello, Florencia Luciana and
Alonso Alemany, Laura and
Villata, Serena and
Teruel, Milagro",
editor = "Ben Abacha, Asma and
Bethard, Steven and
Bitterman, Danielle and
Naumann, Tristan and
Roberts, Kirk",
booktitle = "Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical {NLP}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.clinicalnlp-1.31/",
doi = "10.63317/26nxpzmf4966",
pages = "270--280",
abstract = "The anonymization of clinical free-text records is a prerequisite for enabling the secondary use of healthcare data while preserving patient privacy. This challenge is particularly acute for Spanish clinical text, where annotated resources are scarce and practitioners lack clear empirical guidance on which technological approaches are more adequate to their particular restrictions and capabilities. In this work, we present a controlled comparative study of representative anonymization paradigms for Spanish clinical narratives, including a baseline rule-based approach, a general-purpose large language model under prompt-based inference, an off-the-shelf industrial NLP toolkit (spaCy) and comparable neural sequence labeling architectures. To ensure a fair and contamination-aware evaluation, particularly given the opacity of pretrained model training data, we introduce a synthetic clinical dataset. Recurrent neural network architectures, particularly the off-the-shelf spaCy toolkit, consistently achieve the best balance between effectiveness, computational efficiency, and deployment feasibility. We further observe that training task-specific embeddings end-to-end yields stronger generalization than incorporating pretrained representations. Although limited to Spanish and to representative instances of each paradigm, the study identifies stable performance tendencies across datasets. These results provide actionable guidance for institutions seeking to implement anonymization pipelines. This work contributes reproducible evaluation procedures and empirical evidence for privacy-preserving clinical NLP in Spanish."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brunello-etal-2026-comparative">
<titleInfo>
<title>A Comparative Study of Approaches to Anonymization of Clinical Free Text in Spanish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Florencia</namePart>
<namePart type="given">Luciana</namePart>
<namePart type="family">Brunello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Alonso Alemany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serena</namePart>
<namePart type="family">Villata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milagro</namePart>
<namePart type="family">Teruel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The anonymization of clinical free-text records is a prerequisite for enabling the secondary use of healthcare data while preserving patient privacy. This challenge is particularly acute for Spanish clinical text, where annotated resources are scarce and practitioners lack clear empirical guidance on which technological approaches are more adequate to their particular restrictions and capabilities. In this work, we present a controlled comparative study of representative anonymization paradigms for Spanish clinical narratives, including a baseline rule-based approach, a general-purpose large language model under prompt-based inference, an off-the-shelf industrial NLP toolkit (spaCy) and comparable neural sequence labeling architectures. To ensure a fair and contamination-aware evaluation, particularly given the opacity of pretrained model training data, we introduce a synthetic clinical dataset. Recurrent neural network architectures, particularly the off-the-shelf spaCy toolkit, consistently achieve the best balance between effectiveness, computational efficiency, and deployment feasibility. We further observe that training task-specific embeddings end-to-end yields stronger generalization than incorporating pretrained representations. Although limited to Spanish and to representative instances of each paradigm, the study identifies stable performance tendencies across datasets. These results provide actionable guidance for institutions seeking to implement anonymization pipelines. This work contributes reproducible evaluation procedures and empirical evidence for privacy-preserving clinical NLP in Spanish.</abstract>
<identifier type="citekey">brunello-etal-2026-comparative</identifier>
<identifier type="doi">10.63317/26nxpzmf4966</identifier>
<location>
<url>https://aclanthology.org/2026.clinicalnlp-1.31/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>270</start>
<end>280</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Comparative Study of Approaches to Anonymization of Clinical Free Text in Spanish
%A Brunello, Florencia Luciana
%A Alonso Alemany, Laura
%A Villata, Serena
%A Teruel, Milagro
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Bitterman, Danielle
%Y Naumann, Tristan
%Y Roberts, Kirk
%S Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F brunello-etal-2026-comparative
%X The anonymization of clinical free-text records is a prerequisite for enabling the secondary use of healthcare data while preserving patient privacy. This challenge is particularly acute for Spanish clinical text, where annotated resources are scarce and practitioners lack clear empirical guidance on which technological approaches are more adequate to their particular restrictions and capabilities. In this work, we present a controlled comparative study of representative anonymization paradigms for Spanish clinical narratives, including a baseline rule-based approach, a general-purpose large language model under prompt-based inference, an off-the-shelf industrial NLP toolkit (spaCy) and comparable neural sequence labeling architectures. To ensure a fair and contamination-aware evaluation, particularly given the opacity of pretrained model training data, we introduce a synthetic clinical dataset. Recurrent neural network architectures, particularly the off-the-shelf spaCy toolkit, consistently achieve the best balance between effectiveness, computational efficiency, and deployment feasibility. We further observe that training task-specific embeddings end-to-end yields stronger generalization than incorporating pretrained representations. Although limited to Spanish and to representative instances of each paradigm, the study identifies stable performance tendencies across datasets. These results provide actionable guidance for institutions seeking to implement anonymization pipelines. This work contributes reproducible evaluation procedures and empirical evidence for privacy-preserving clinical NLP in Spanish.
%R 10.63317/26nxpzmf4966
%U https://aclanthology.org/2026.clinicalnlp-1.31/
%U https://doi.org/10.63317/26nxpzmf4966
%P 270-280
Markdown (Informal)
[A Comparative Study of Approaches to Anonymization of Clinical Free Text in Spanish](https://aclanthology.org/2026.clinicalnlp-1.31/) (Brunello et al., ClinicalNLP 2026)
ACL