EUVIMEDEUVIMED entdecken
Crossref

Automated Multi-Label Adverse drug Reaction Extraction from Malaysia’s National Pharmacovigilance Narratives

Sze Gee Lim, Maizatul Akmar Ismail

Journal of Medical Systems · 31.07.2026 · 50 (1)

DOI: 10.1007/s10916-026-02448-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Medical Systems, online erschienen am 31.07.2026. Verfasst von Sze Gee Lim und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Systems, Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur, 50603, Malaysia. Hauptthemen laut MEDLINE: Pharmacovigilance, Adverse Drug Reaction Reporting Systems, Drug-Related Side Effects and Adverse Reactions, Natural Language Processing. Die Arbeit nennt 45 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Extracting multiple adverse drug reaction (ADR) terms from unstructured narratives remains challenging, particularly under severe label imbalance that limits the detection of rare ADRs. This study aimed to develop and evaluate a multi-label natural language processing framework for automated ADR extraction within Malaysia's national pharmacovigilance reporting system. We evaluated classical machine learning and transformer-based models within a common framework, incorporating domain-specific preprocessing and imbalance-aware optimization strategies to improve the detection of rare ADRs. The framework was applied to 28,980 real-world ADR narratives annotated with 80 Medical Dictionary for Regulatory Activities (MedDRA) Preferred Terms (PTs) from the Skin and Subcutaneous Tissue Disorders System Organ Class (SOC). Performance was evaluated using micro-F1, macro-F1, precision, recall, and label coverage using a predefined 80/20 train-test evaluation strategy, complemented by pharmacist pilot review. Transformer-based models achieved the strongest performance, with the augmented model attaining a micro-F1 of 0.88, macro-F1 of 0.55, recall of 0.88, and the highest label coverage, correctly predicting 60 of 80 PTs (75%). However, a 70/10/20 sensitivity analysis on the improved transformer model yielded lower micro-F1 and precision, highlighting the impact of further data partitioning on model performance. Improved classical models also showed substantial gains over their baseline models, particularly in micro-F1, macro-F1, recall, and label coverage, consistent with improved detection of rare ADRs. During the pilot review, pharmacists accepted the model-preselected PTs without modification in 19 of 25 narratives (76%), while additional PTs were added in the remaining cases. Although the study was limited to a single SOC and one national pharmacovigilance database, the findings demonstrate that optimization strategies, domain-specific feature enrichment, and targeted augmentation can substantially improve multi-label ADR classification under severe imbalance. These findings support further evaluation of AI-assisted pharmacovigilance with pharmacist oversight in real-world practice.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PharmacovigilanceAdverse Drug Reaction Reporting SystemsDrug-Related Side Effects and Adverse ReactionsNatural Language ProcessingData MiningMalaysiaHumansMachine Learning

Stichwörter der Autor:innen

Adverse Drug ReactionsMedDRAMulti-label ClassificationNatural Language ProcessingPharmacovigilanceReal-World Data

Autor:innen und Institutionen

  • Department of Information Systems, Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur, 50603, Malaysia.
  • Department of Information Systems, Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur, 50603, Malaysia. maizatul@um.edu.my.

Zitieren

APA

Lim, S. G., & Ismail, M. A. (2026). Automated Multi-Label Adverse drug Reaction Extraction from Malaysia’s National Pharmacovigilance Narratives. Journal of Medical Systems, 50(1). https://doi.org/10.1007/s10916-026-02448-4

Vancouver

Lim SG, Ismail MA. Automated Multi-Label Adverse drug Reaction Extraction from Malaysia’s National Pharmacovigilance Narratives. Journal of Medical Systems. 2026;50(1). doi:10.1007/s10916-026-02448-4

BibTeX
@article{Lim2026,
  author = {Lim, Sze Gee and Ismail, Maizatul Akmar},
  title = {Automated Multi-Label Adverse drug Reaction Extraction from Malaysia’s National Pharmacovigilance Narratives},
  journal = {Journal of Medical Systems},
  year = {2026},
  volume = {50},
  number = {1},
  doi = {10.1007/s10916-026-02448-4}
}
Kostenlos starten →