A pseudonymized corpus of occupational health narratives for clinical entity recognition in Spanish.

Autor: Dunstan J; Department of Computer Sciences, Pontificia Universidad Catolica de Chile, Santiago, Chile.; Institute for Mathematical and Computational Engineering, Pontificia Universidad Catolica de Chile, Santiago, Chile.; Millennium Institute for Foundational Research on Data, Santiago, Chile., Vakili T; Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden. thomas.vakili@dsv.su.se., Miranda L; Department of Computer Sciences, Pontificia Universidad Catolica de Chile, Santiago, Chile.; Millennium Institute for Foundational Research on Data, Santiago, Chile., Villena F; Millennium Institute for Foundational Research on Data, Santiago, Chile.; Department of Computer Science, Universidad de Chile, Santiago, Chile., Aracena C; Millennium Institute for Foundational Research on Data, Santiago, Chile.; Faculty of Physical and Mathematical Sciences, Universidad de Chile, Santiago, Chile., Quiroga T; Department of Computer Sciences, Pontificia Universidad Catolica de Chile, Santiago, Chile.; Millennium Institute for Foundational Research on Data, Santiago, Chile., Vera P; Servicio de Salud del Maule, Ministerio de Salud, Talca, Chile., Viteri Valenzuela S; Asociación Chilena de Seguridad, Santiago, Chile., Rocco V; Asociación Chilena de Seguridad, Santiago, Chile.
Jazyk: angličtina
Zdroj: BMC medical informatics and decision making [BMC Med Inform Decis Mak] 2024 Jul 24; Vol. 24 (1), pp. 204. Date of Electronic Publication: 2024 Jul 24.
DOI: 10.1186/s12911-024-02609-w
Abstrakt: Despite the high creation cost, annotated corpora are indispensable for robust natural language processing systems. In the clinical field, in addition to annotating medical entities, corpus creators must also remove personally identifiable information (PII). This has become increasingly important in the era of large language models where unwanted memorization can occur. This paper presents a corpus annotated to anonymize personally identifiable information in 1,787 anamneses of work-related accidents and diseases in Spanish. Additionally, we applied a previously released model for Named Entity Recognition (NER) trained on referrals from primary care physicians to identify diseases, body parts, and medications in this work-related text. We analyzed the differences between the models and the gold standard curated by a physician in detail. Moreover, we compared the performance of the NER model on the original narratives, in narratives where personal information has been masked, and in texts where the personal data is replaced by another similar surrogate value (pseudonymization). Within this publication, we share the annotation guidelines and the annotated corpus.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje