TAXN: Translate Align Extract Normalize, a multilingual extraction tool for clinical texts - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

TAXN: Translate Align Extract Normalize, a multilingual extraction tool for clinical texts

Abstract

Several studies have shown that about 80% of the medical information in an electronic health record is only available through unstructured data. Resources such as medical terminologies in languages other than English are limited and restrain the NLP tools. We propose here to leverage English based resources in other languages using a combination of translation, word alignment, entity extraction and term normalization (TAXN). We implement this extraction pipeline in an opensource library called "medkit". We demonstrate the interest of this approach through a specific use-case: enriching a phenotypic dictionary for post-acute sequelae in COVID-19 (PASC). TAXN proved to be efficient to propose new synonyms of UMLS terms using a corpus of 70 articles in French with 356 terms enriched with at least one validated new synonym. This study was based on freely available deeplearning models.
Fichier principal
Vignette du fichier
neuraz_et_al_medinfo2023.pdf (221.21 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04069590 , version 1 (14-04-2023)

Identifiers

  • HAL Id : hal-04069590 , version 1

Cite

Antoine Neuraz, Ivan Lerner, Olivier Birot, Camila Arias, Larry Han, et al.. TAXN: Translate Align Extract Normalize, a multilingual extraction tool for clinical texts. MedInfo 2023 – the 19th world congress on Medical and Health Informatics, International Medical Informatics Association (IMIA), Jul 2023, Syndney, Australia. ⟨hal-04069590⟩
192 View
144 Download

Share

Gmail Mastodon Facebook X LinkedIn More