Por favor, use este identificador para citar o enlazar este ítem: http://hdl.handle.net/10637/13662

De-identifying Spanish medical texts-named entity recognition applied to radiology reports


Vista previa

Ver/Abrir:
 De-identifying_Perez_JOBS_2021.pdf
2,08 MB
Adobe PDF
Título : De-identifying Spanish medical texts-named entity recognition applied to radiology reports
Autor : Pérez Díez, Irene
Pérez Moraga, Raúl
López Cerdán, Adolfo
Salinas Serrano, José María
Iglesia Vayá, María de la
Materias: Proceso de lenguaje natural.Natural lenguage processing.Radiología.Data protection.Diagnóstico radiológico.Diagnosis, Radioscopic.Protección de datos personales.Radiology.
Editorial : BioMed Central
Citación : Pérez-Díez, I., Pérez-Moraga, R., López-Cerdán, A., Salinas-Serrano, J.M. & Vayá, M.I. (2021). De-identifying Spanish medical texts - named entity recognition applied to radiology reports. Journal of Biomedical Semantics, vol. 12, art. 6 (29 mar.). DOI: https://doi.org/10.1186/s13326-021-00236-2
Resumen : Background: Medical texts such as radiology reports or electronic health records are a powerful source of data for researchers. Anonymization methods must be developed to de-identify documents containing personal information from both patients and medical staff. Although currently there are several anonymization strategies for the English language, they are also language-dependent. Here, we introduce a named entity recognition strategy for Spanish medical texts, translatable to other languages. Results: We tested 4 neural networks on our radiology reports dataset, achieving a recall of 97.18% of the identifying entities. Alongside, we developed a randomization algorithm to substitute the detected entities with new ones from the same category, making it virtually impossible to differentiate real data from synthetic data. The three best architectures were tested with the MEDDOCAN challenge dataset of electronic health records as an external test, achieving a recall of 69.18%. Conclusions: The strategy proposed, combining named entity recognition tasks with randomization of entities, is suitable for Spanish radiology reports. It does not require a big training corpus, thus it could be easily extended to other languages and medical texts, such as electronic health records.
Descripción : Este artículo se encuentra disponible en la siguiente URL: https://jbiomedsem.biomedcentral.com/track/pdf/10.1186/s13326-021-00236-2.pdf
URI : http://hdl.handle.net/10637/13662
Derechos: http://creativecommons.org/licenses/by/4.0/deed.es
ISSN : 2041-1480 (Electrónico)
Fecha de publicación : 29-mar-2021
Aparece en las colecciones: Dpto. Matemáticas, Física y Ciencias Tecnológicas





Los ítems de DSpace están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.