EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Contrastive learning of adverse events to provide effective and interpretable vector representations for machine-assisted pharmacovigilance

Olivér M Balogh, Mátyás Pétervári, Áron M Csernák, Eszter Puhl, András Horváth, Péter Ferdinandy, Bence Ágg iD

Briefings in Bioinformatics · 01.09.2026 · 27 (5)

DOI: 10.1093/bib/bbag463 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 03.09.2026. Verfasst von Olivér M Balogh und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pharmacology and Pharmacotherapy, Semmelweis University, Üllői út 26., Üllői út 26., H-1085 Budapest, Hungary. Hauptthemen laut MEDLINE: Pharmacovigilance, Drug-Related Side Effects and Adverse Reactions, Machine Learning, Adverse Drug Reaction Reporting Systems. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: European Commission, HUN-REN Hungarian Research Network and the National Research, Development and Innovation Office of Hungary, Thematic Excellence Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Post-marketing surveillance is crucial for drug safety, yet the tools of pharmacovigilance rely solely on text-based data that may limit contemporary machine learning methodologies in the support of decision-making. With the recent surge of employing large language models (LLMs) for text-based tasks, there also arises an unmet need for a different approach which is not grounded in the linguistic patterns of unfiltered natural text, like LLMs, but rather based on real-world drug safety data. Here, we adapt contrastive learning algorithms to generate adverse event vector representations from spontaneous adverse event reports to serve as machine-readable (i.e. numerical) resources for downstream pharmacovigilance applications, such as drug–event association prediction for signal detection or causality assessment. We present comprehensive interpretability analyses of the resulting representations through density-based clustering, semantic evaluation, and comparison of multivariate dispersions, revealing patterns that reflect both functional and causal relations of the adverse events while also capturing drug-safety-related information better than existing medical terminologies and encoder-only LLMs. Furthermore, we demonstrate the applicability of our representations as input features in our downstream classifier model, outperforming the reporting odds ratio method, commonly used by regulatory agencies, and also LLM-generated representations (area under the receiver operating characteristic curve: 0.88 versus 0.76–0.83) on drug–event association prediction benchmarks. Therefore, we propose an interpretable adverse event vector representation, serving as a general resource that could enable the development of a wide array of machine learning applications to support decision-making in pharmacovigilance and facilitate patient safety.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PharmacovigilanceDrug-Related Side Effects and Adverse ReactionsMachine LearningAdverse Drug Reaction Reporting SystemsHumansLarge Language ModelsAlgorithms

Stichwörter der Autor:innen

adverse drug reactioncausality assessmentdrug safetyembeddinginterpretable ai

Autor:innen und Institutionen

  • Department of Pharmacology and Pharmacotherapy, Semmelweis University, Üllői út 26., Üllői út 26., H-1085 Budapest, Hungary.
  • Center for Pharmacology and Drug Research and Development, Semmelweis University, Üllői út 26., Üllői út 26., H-1085 Budapest, Hungary.
  • HUN-REN-SU System Pharmacology Research Group, Department of Pharmacology and Pharmacotherapy, Semmelweis University, Üllői út 26., H-1089 Budapest, Hungary.
  • Pharmahungary Group, Szeged, Hajnóczy utca 6., H-6722 Szeged, Hungary.
  • Sanovigado Kft, Somfa köz 11., Somfa köz 11., H-1107 Budapest, Hungary.
  • Faculty of Information Technology and Bionics, Pázmány Péter Catholic University, Práter utca 50/A., H-1083 Budapest, Hungary.

ORCID-Profile: Bence Ágg

Förderung

  • European Commission
  • HUN-REN Hungarian Research Network and the National Research, Development and Innovation Office of Hungary
  • Thematic Excellence Program
  • Ministry for Innovation and Technology in Hungary
  • Therapeutic Development and Bioimaging thematic programs of the Semmelweis University
  • New National Excellence Program
  • Digital Renewal Operational Program Plus

Zitieren

APA

Balogh, O. M., Pétervári, M., Csernák, Á. M., Puhl, E., Horváth, A., Ferdinandy, P., & Ágg, B. (2026). Contrastive learning of adverse events to provide effective and interpretable vector representations for machine-assisted pharmacovigilance. Briefings in Bioinformatics, 27(5). https://doi.org/10.1093/bib/bbag463

Vancouver

Balogh OM, Pétervári M, Csernák ÁM, Puhl E, Horváth A, Ferdinandy P, et al. Contrastive learning of adverse events to provide effective and interpretable vector representations for machine-assisted pharmacovigilance. Briefings in Bioinformatics. 2026;27(5). doi:10.1093/bib/bbag463

BibTeX
@article{Balogh2026,
  author = {Balogh, Olivér M and Pétervári, Mátyás and Csernák, Áron M and Puhl, Eszter and Horváth, András and Ferdinandy, Péter and Ágg, Bence},
  title = {Contrastive learning of adverse events to provide effective and interpretable vector representations for machine-assisted pharmacovigilance},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  volume = {27},
  number = {5},
  doi = {10.1093/bib/bbag463}
}
Kostenlos starten →