Natural Language Processing-Based Approach to Detect Common Adverse Events of Anticancer Agents from Unstructured Clinical Notes: A Time-to-Event Analysis
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti250931 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Masami Tsuchiya und 9 weiteren Autor:innen. Beteiligte Einrichtung: Keio University Faculty of Pharmacy. Hauptthemen laut MEDLINE: Natural Language Processing, Antineoplastic Agents, Electronic Health Records, Drug-Related Side Effects and Adverse Reactions. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Themen: Patientensicherheit
Abstract (Originalsprache)
This study assessed the effectiveness of natural language processing (NLP) in detecting adverse events (AEs) from anticancer agents by analyzing data from over 39,000 cancer patients. A specialized machine learning model identified known AEs from anticancer agents like capecitabine, oxaliplatin, and anthracyclines, revealing a significantly higher incidence in the treatment groups compared to non-users. While the NLP approach effectively detected most symptomatic AEs requiring manual review, it struggled with rarely documented conditions and commonly used clinical terms. Overall, the method shows promise for automated AE detection in medical records, particularly for symptoms without laboratory markers or diagnosis codes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Keio University Faculty of Pharmacy.
- Graduate School of Medicine, The University of Tokyo.
- Institute of Library, Information and Media Science, University of Tsukuba.
- Division of Information Science, Nara Institute of Science and Technology.
Zitieren
APA
Tsuchiya, M., Shimamoto, K., Kawazoe, Y., Shinohara, E., Yada, S., Wakamiya, S., Imai, S., Kizaki, H., Hori, S., & Aramaki, E. (2025). Natural Language Processing-Based Approach to Detect Common Adverse Events of Anticancer Agents from Unstructured Clinical Notes: A Time-to-Event Analysis. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250931
Vancouver
Tsuchiya M, Shimamoto K, Kawazoe Y, Shinohara E, Yada S, Wakamiya S, et al. Natural Language Processing-Based Approach to Detect Common Adverse Events of Anticancer Agents from Unstructured Clinical Notes: A Time-to-Event Analysis. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250931
BibTeX
@article{Tsuchiya2025,
author = {Tsuchiya, Masami and Shimamoto, Kiminori and Kawazoe, Yoshimasa and Shinohara, Emiko and Yada, Shuntaro and Wakamiya, Shoko and Imai, Shungo and Kizaki, Hayato and Hori, Satoko and Aramaki, Eiji},
title = {Natural Language Processing-Based Approach to Detect Common Adverse Events of Anticancer Agents from Unstructured Clinical Notes: A Time-to-Event Analysis},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti250931}
}
EUVIMED