EUVIMEDEUVIMED entdecken
EvaluationsstudieOpen Access · CC BY 4.0

Entity-enhanced BERT for medical specialty prediction based on clinical questionnaire data

Soyeon Lee iD, Ye Ji Han, Hyun Joon Park, Byung Hoon Lee, DaHee Son, SoYeon Kim, HyeonJong Yang, TaeJun Han, EunSun Kim, Sung Won Han iD

PLOS ONE · 2025

DOI: 10.1371/journal.pone.0317795 ↗

Kurz gefasst

Evaluationsstudie in der Zeitschrift PLOS ONE, 2025. Verfasst von Soyeon Lee und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Industrial and Management Engineering, Korea University, Seongbuk-gu, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Triage, Natural Language Processing, Large Language Models, Remote Consultation. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea TechnoComplex Foundation Grant, National Research Foundation of Korea, Brain Korea 21 FOUR.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A medical specialty prediction system for remote diagnosis can reduce the unexpected costs incurred by first-visit patients who visit the wrong hospital department for their symptoms. To develop medical specialty prediction systems, several researchers have explored clinical predictive models using real medical text data. Medical text data include large amounts of information regarding patients, which increases the sequence length. Hence, a few studies have attempted to extract entities from the text as concise features and provide domain-specific knowledge for clinical text classification. However, it is still insufficient to inject them into the model effectively. Thus, we propose Entity-enhanced BERT (E-BERT), which utilizes the structural attributes of BERT for medical specialty prediction. E-BERT has an entity embedding layer and entity-aware attention to inject domain-specific knowledge and focus on relationships between medical-related entities within the sequences. Experimental results on clinical questionnaire data demonstrate the superiority of E-BERT over the other benchmark models, regardless of the input sequence length. Moreover, the visualization results for the effects of entity-aware attention prove that E-BERT effectively incorporate domain-specific knowledge and other information, enabling the capture of contextual information in the text. Finally, the robustness and applicability of the proposed method is explored by applying it to other Pre-trained Language Models. These effective medical specialty predictive model can provide practical information to first-visit patients, resulting in streamlining the diagnostic process and improving the quality of medical consultations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TriageNatural Language ProcessingLarge Language ModelsRemote ConsultationPredictive Learning ModelsSurveys and QuestionnairesEmergency Room VisitsPatient SatisfactionHealth ExpendituresHumansQuality ImprovementHospitals, UniversityRepublic of Korea

Autor:innen und Institutionen

  • School of Industrial and Management Engineering, Korea University, Seongbuk-gu, Seoul, Republic of Korea.
  • People's Health Co., Ltd., 403, BT-IT Convergence Center, Seongbuk-gu, Seoul, Republic of Korea.

ORCID-Profile: Soyeon Lee, Sung Won Han

Förderung

  • Korea TechnoComplex Foundation Grant
  • National Research Foundation of Korea
  • Brain Korea 21 FOUR

Zitieren

APA

Lee, S., Han, Y. J., Park, H. J., Lee, B. H., Son, D., Kim, S., Yang, H., Han, T., Kim, E., & Han, S. W. (2025). Entity-enhanced BERT for medical specialty prediction based on clinical questionnaire data. PLOS ONE. https://doi.org/10.1371/journal.pone.0317795

Vancouver

Lee S, Han YJ, Park HJ, Lee BH, Son D, Kim S, et al. Entity-enhanced BERT for medical specialty prediction based on clinical questionnaire data. PLOS ONE. 2025. doi:10.1371/journal.pone.0317795

BibTeX
@article{Lee2025,
  author = {Lee, Soyeon and Han, Ye Ji and Park, Hyun Joon and Lee, Byung Hoon and Son, DaHee and Kim, SoYeon and Yang, HyeonJong and Han, TaeJun and Kim, EunSun and Han, Sung Won},
  title = {Entity-enhanced BERT for medical specialty prediction based on clinical questionnaire data},
  journal = {PLOS ONE},
  year = {2025},
  doi = {10.1371/journal.pone.0317795}
}
Kostenlos starten →