Effectiveness of Transformer-Based Large Language Models in Identifying Adverse Drug Reaction Relations from Unstructured Discharge Summaries in Singapore.

Journal: Drug safety

Published Date: Feb 21, 2025

Abstract

INTRODUCTION: Transformer-based large language models (LLMs) have transformed the field of natural language processing and led to significant advancements in various text processing tasks. However, the applicability of these LLMs in identifying related drug-adverse event (AE) pairs within clinical context may be limited by the prevalent use of non-standard sentence structures and grammar.

Authors

Yen Ling Koon

Vigilance and Compliance Branch, Health Products Regulation Group, Health Sciences Authority, 11 Biopolis Way, #11-01 Helios, Singapore, 138667, Singapore.
Yan Tung Lam

Vigilance and Compliance Branch, Health Products Regulation Group, Health Sciences Authority, 11 Biopolis Way, #11-01 Helios, Singapore, 138667, Singapore.
Hui Xing Tan

Institute of Systems Science, National University of Singapore, 25 Heng Mui Keng Terrace, Singapore, 119615, Singapore. tan.huixing@gmail.com.
Desmond Hwee Chun Teo

Vigilance and Compliance Branch, Health Products Regulation Group, Health Sciences Authority, 11 Biopolis Way, #11-01 Helios, Singapore, 138667, Singapore.
Jing Wei Neo

Vigilance and Compliance Branch, Health Products Regulation Group, Health Sciences Authority, 11 Biopolis Way, #11-01 Helios, Singapore, 138667, Singapore.
Aaron Jun Yi Yap

Vigilance and Compliance Branch, Health Products Regulation Group, Health Sciences Authority, 11 Biopolis Way, #11-01 Helios, Singapore, 138667, Singapore.
Pei San Ang

Vigilance & Compliance Branch, Health Products Regulation Group, Health Sciences Authority, Singapore.
Celine Ping Wei Loke

Vigilance and Compliance Branch, Health Products Regulation Group, Health Sciences Authority, 11 Biopolis Way, #11-01 Helios, Singapore, 138667, Singapore.
Mun Yee Tham

Vigilance & Compliance Branch, Health Products Regulation Group, Health Sciences Authority, Singapore.
Siew Har Tan

Vigilance & Compliance Branch, Health Products Regulation Group, Health Sciences Authority, Singapore.
Sally Leng Bee Soh

Vigilance and Compliance Branch, Health Products Regulation Group, Health Sciences Authority, 11 Biopolis Way, #11-01 Helios, Singapore, 138667, Singapore.
Belinda Qin Pei Foo

Vigilance and Compliance Branch, Health Products Regulation Group, Health Sciences Authority, 11 Biopolis Way, #11-01 Helios, Singapore, 138667, Singapore.
Zheng Jye Ling

Regional Health System Office, National University of Singapore, National University Health System, Singapore, Singapore.
James Luen Wei Yip

Department of Cardiology, National University Heart Centre, Singapore, Singapore.
Sreemanee Raaj Dorajoo

Vigilance & Compliance Branch, Health Products Regulation Group, Health Sciences Authority, Singapore.

Keywords

Adverse Drug Reaction Reporting Systems Databases, Factual Drug-Related Side Effects and Adverse Reactions Humans Large Language Models Machine Learning Natural Language Processing Patient Discharge Patient Discharge Summaries Singapore

External Resources

View on PubMed Access via DOI PubMed (39982676)

Effectiveness of Transformer-Based Large Language Models in Identifying Adverse Drug Reaction Relations from Unstructured Discharge Summaries in Singapore.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals