EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Weakly-Supervised Multilingual Medical NER for Symptom Extraction for Low-Resource Languages

Rigon Sallauka, Umut Arioz, Matej Rojc, Izidor Mlakar

Applied Sciences · 16.05.2025 · 15 (10) · 5585

DOI: 10.3390/app15105585 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 16.05.2025. Verfasst von Rigon Sallauka und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union Horizon Europe Research and Innovation Program Project SMILE, Marie Skłodowska-Curie Doctoral Networks Actions, Project BosomShield.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Patient-reported health data, especially patient-reported outcomes measures, are vital for improving clinical care but are often limited by memory bias, cognitive load, and inflexible questionnaires. Patients prefer conversational symptom reporting, highlighting the need for robust methods in symptom extraction and conversational intelligence. This study presents a weakly-supervised pipeline for training and evaluating medical Named Entity Recognition (NER) models across eight languages, with a focus on low-resource settings. A merged English medical corpus, annotated using the Stanza i2b2 model, was translated into German, Greek, Spanish, Italian, Portuguese, Polish, and Slovenian, preserving the entity annotations medical problems, diagnostic tests, and treatments. Data augmentation addressed the class imbalance, and the fine-tuned BERT-based models outperformed baselines consistently. The English model achieved the highest F1 score (80.07%), followed by German (78.70%), Spanish (77.61%), Portuguese (77.21%), Slovenian (75.72%), Italian (75.60%), Polish (75.56%), and Greek (69.10%). Compared to the existing baselines, our models demonstrated notable performance gains, particularly in English, Spanish, and Italian. This research underscores the feasibility and effectiveness of weakly-supervised multilingual approaches for medical entity extraction, contributing to improved information access in clinical narratives—especially in under-resourced languages.

Förderung

  • European Union Horizon Europe Research and Innovation Program Project SMILE
  • Marie Skłodowska-Curie Doctoral Networks Actions
  • Project BosomShield

Zitieren

APA

Sallauka, R., Arioz, U., Rojc, M., & Mlakar, I. (2025). Weakly-Supervised Multilingual Medical NER for Symptom Extraction for Low-Resource Languages. Applied Sciences, 15(10), 5585. https://doi.org/10.3390/app15105585

Vancouver

Sallauka R, Arioz U, Rojc M, Mlakar I. Weakly-Supervised Multilingual Medical NER for Symptom Extraction for Low-Resource Languages. Applied Sciences. 2025;15(10):5585. doi:10.3390/app15105585

BibTeX
@article{Sallauka2025,
  author = {Sallauka, Rigon and Arioz, Umut and Rojc, Matej and Mlakar, Izidor},
  title = {Weakly-Supervised Multilingual Medical NER for Symptom Extraction for Low-Resource Languages},
  journal = {Applied Sciences},
  year = {2025},
  volume = {15},
  number = {10},
  pages = {5585},
  doi = {10.3390/app15105585}
}
Kostenlos starten →