Hybrid Fused Transformer Approach for Adverse Drug Reaction Detection

DOI

10.2991/978-94-6239-756-9_2How to use a DOI?

Keywords

Pharmacovigilance; Adverse Drug Reaction; Drug–Drug Interaction; Hybrid Transformer; Drug Safety

Abstract

Titanium Pharmacovigilance objective is to increase the care for the patients, recognize wellbeing in medicinal use and take measures to decrease the unwanted harm to patients from medicinal products and assess the advantage and risk ratio. The study of drug safety saves lives by finding dangerous side effects in timely manner and through the information exchange it helps lower healthcare costs. Pharmacovigilance is designed for people living with conditions like diabetes and high blood pressure who need to keep track of many different medicines. When a person is taking many diverse medications (known as polypharmacy), it is more likely they will have bad reactions or harmful interactions between the drugs. Recognizing these reactions in initial phases and forecasting possible health risks can benefit in saving many lives. However, traditional pharmacovigilance methods, including manual reviews, laboratory testing, and clinical monitoring, are exclusive and time-consuming, which confines their usage on a huge scale. This research proposes a method that method uses public adverse drug reactions diabetes datasets for model training and evaluation. Model performance will be conducted by standard, established and widely accepted metrics. The findings may confirm to validate that the proposed approach outperforms existing techniques over current methods. The model is designed to give better results under both balanced datasets and highly imbalanced datasets where ADR occurrences are rare. The result of integration of many transformer architectures with attention-based convolutional neural networks, with the help of this model’s robust and streamlined approach in the early identification of adverse drug reactions that in turn raises patient wellbeing and fitness by empowering prompt results in pharmacovigilance. Additionally, this improvement can enable healthcare practitioners in taking improved clinical decisions.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sonal R. Kulkarni
AU  - Anjali S. More
PY  - 2026
DA  - 2026/08/31
TI  - Hybrid Fused Transformer Approach for Adverse Drug Reaction Detection
BT  - Proceedings of the Conference on Bioengineering for Global Health (SYMRESEARCH 2.0 2025)
PB  - Atlantis Press
SP  - 7
EP  - 20
SN  - 2468-5747
UR  - https://doi.org/10.2991/978-94-6239-756-9_2
DO  - 10.2991/978-94-6239-756-9_2
ID  - Kulkarni2026
ER  -