ToxicFreeMed: BERT-enhanced BPR algorithm for toxic-free medication recommendation
Health Information Science and Systems · 01.08.2026 · 14 (1)
DOI: 10.1007/s13755-026-00475-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Health Information Science and Systems, online erschienen am 01.08.2026. Verfasst von Stavros Davidopoulos und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information and Communication Systems Engineering, University of the Aegean, Karlovasi, 83200 Samos Greece. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Medication recommendation aims to predict effective drug combinations for patients with complex conditions. Critically-ill patients often experience polypharmacy, which increases the risk of adverse drug–drug interactions (DDIs). In this paper, we use a BERT-enhanced variation of Bayesian Personalized Ranking (BPR) algorithm for providing Toxic-free Medication Recommendations. Our model, denoted as ToxicFreeMed, integrates patients’ electronic discharge notes, drug descriptions, and the DDI knowledge graph to recommend both accurate and safe drug combinations. ToxicFreeMed leverages pretrained discharge notes embeddings-capturing patient’s disease, therapy, and medication context-and pretrained drug descriptions embeddings within a multitask learning framework that jointly optimizes ranking accuracy and a toxicity-weighted DDI loss. We have evaluated ToxicFreeMed on the MIMIC-III dataset augmented with DrugBank knowledge and show that it effectively balances accuracy and safety, outperforming other strong recommendation algorithms while reducing DDIs. Our results indicate that ToxicFreeMed is a promising approach that has the potential to assist clinicians in identifying therapeutically appropriate and pharmacologically safer treatment options.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Information and Communication Systems Engineering, University of the Aegean, Karlovasi, 83200 Samos Greece.
- Department of Industrial Engineering and Management, International Hellenic University, 57001 Thessaloníki, Greece.
- Department of Computer Science, University of York, Europe Campus, 54626 Thessaloníki, Greece.
- Department of Computer Science, University of Nicosia, 1700 Nicosia, Cyprus.
- Department of Medicine, European University Cyprus, 2404 Nicosia, Cyprus.
- Eunomia Ltd, Dublin, D02 P593 Ireland.
ORCID-Profile: Stavros Davidopoulos
Zitieren
APA
Davidopoulos, S., Symeonidis, P., Andras, C., Manolopoulos, Y., & Danilatou, V. (2026). ToxicFreeMed: BERT-enhanced BPR algorithm for toxic-free medication recommendation. Health Information Science and Systems, 14(1). https://doi.org/10.1007/s13755-026-00475-6
Vancouver
Davidopoulos S, Symeonidis P, Andras C, Manolopoulos Y, Danilatou V. ToxicFreeMed: BERT-enhanced BPR algorithm for toxic-free medication recommendation. Health Information Science and Systems. 2026;14(1). doi:10.1007/s13755-026-00475-6
BibTeX
@article{Davidopoulos2026,
author = {Davidopoulos, Stavros and Symeonidis, Panagiotis and Andras, Christos and Manolopoulos, Yannis and Danilatou, Vasiliki},
title = {ToxicFreeMed: BERT-enhanced BPR algorithm for toxic-free medication recommendation},
journal = {Health Information Science and Systems},
year = {2026},
volume = {14},
number = {1},
doi = {10.1007/s13755-026-00475-6}
}
EUVIMED