Unsupervised Extraction of Body-Text from Clinical PDF Documents
Studies in Health Technology and Informatics · 2024
DOI: 10.3233/shti240382 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2024. Verfasst von Adel Bensahla und 3 weiteren Autor:innen. Beteiligte Einrichtung: Division of Medical Information Sciences, Geneva University Hospitals, Switzerland. Hauptthemen laut MEDLINE: Natural Language Processing. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Automatic extraction of body-text within clinical PDF documents is necessary to enhance downstream NLP tasks but remains a challenge. This study presents an unsupervised algorithm designed to extract body-text leveraging large volume of data. Using DBSCAN clustering over aggregate pages, our method extracts and organize text blocks using their content and coordinates. Evaluation results demonstrate precision scores ranging from 0.82 to 0.98, recall scores from 0.62 to 0.94, and F1-scores from 0.71 to 0.96 across various medical specialty sources. Future work includes dynamic parameter adjustments for improved accuracy and using larger datasets.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Medical Information Sciences, Geneva University Hospitals, Switzerland.
- Department of Radiology and Medical Informatics, University of Geneva, Switzerland.
Zitieren
APA
Bensahla, A., Zaghir, J., Gaudet-Blavignac, C., & Lovis, C. (2024). Unsupervised Extraction of Body-Text from Clinical PDF Documents. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti240382
Vancouver
Bensahla A, Zaghir J, Gaudet-Blavignac C, Lovis C. Unsupervised Extraction of Body-Text from Clinical PDF Documents. Studies in Health Technology and Informatics. 2024. doi:10.3233/shti240382
BibTeX
@article{Bensahla2024,
author = {Bensahla, Adel and Zaghir, Jamil and Gaudet-Blavignac, Christophe and Lovis, Christian},
title = {Unsupervised Extraction of Body-Text from Clinical PDF Documents},
journal = {Studies in Health Technology and Informatics},
year = {2024},
doi = {10.3233/shti240382}
}
EUVIMED