EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Clustering Similar Diagnosis Terms

Stefan Schulz, Akhila Abdulnazar, Markus Kreuzthaler

Studies in Health Technology and Informatics · 18.05.2023

DOI: 10.3233/shti230284 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 18.05.2023. Verfasst von Stefan Schulz und 2 weiteren Autor:innen. Beteiligte Einrichtung: IMI, Medical University of Graz, Austria. Hauptthemen laut MEDLINE: Natural Language Processing, Language. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A large clinical diagnosis list is explored with the goal to cluster syntactic variants. A string similarity heuristic is compared with a deep learning-based approach. Levenshtein distance (LD) applied to common words only (not tolerating deviations in acronyms and tokens with numerals), together with pair-wise substring expansions raised F1 to 13% above baseline (plain LD), with a maximum F1 of 0.71. In contrast, the model-based approach trained on a German medical language model did not perform better than the baseline, not exceeding an F1 value of 0.42.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingLanguageElectronic Health RecordsRecordsCluster Analysis

Stichwörter der Autor:innen

Electronic Health RecordsNamed Entity Normalization

Autor:innen und Institutionen

  • IMI, Medical University of Graz, Austria.

Zitieren

APA

Schulz, S., Abdulnazar, A., & Kreuzthaler, M. (2023). Clustering Similar Diagnosis Terms. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti230284

Vancouver

Schulz S, Abdulnazar A, Kreuzthaler M. Clustering Similar Diagnosis Terms. Studies in Health Technology and Informatics. 2023. doi:10.3233/shti230284

BibTeX
@article{Schulz2023,
  author = {Schulz, Stefan and Abdulnazar, Akhila and Kreuzthaler, Markus},
  title = {Clustering Similar Diagnosis Terms},
  journal = {Studies in Health Technology and Informatics},
  year = {2023},
  doi = {10.3233/shti230284}
}
Kostenlos starten →