Graph neural network-based subgraph analysis for predicting adverse drug events.

Autor: Zhou F; School of Project Management, Faculty of Engineering, The University of Sydney, Australia. Electronic address: fangyu.zhou@sydney.edu.au., Khushi M; School of Computer Science, Faculty of Engineering, The University of Sydney, Australia; Department of Computer Science, Brunel University London, Uxbridge, London, UK. Electronic address: matloob.khushi@brunel.ac.uk., Brett J; St Vincent's Clinical School, The University of New South Wales, Sydney, New South Wales, Australia; Department of Clinical Pharmacology and Toxicology, St Vincent's Hospital Sydney, Sydney, New South Wales, Australia. Electronic address: j.brett@unsw.edu.au., Uddin S; School of Project Management, Faculty of Engineering, The University of Sydney, Australia. Electronic address: shahadat.uddin@sydney.edu.au.
Jazyk: angličtina
Zdroj: Computers in biology and medicine [Comput Biol Med] 2024 Dec; Vol. 183, pp. 109282. Date of Electronic Publication: 2024 Oct 23.
DOI: 10.1016/j.compbiomed.2024.109282
Abstrakt: Purpose: Adverse drug events (ADEs) are a significant global public health concern, and they have resulted in high rates of hospital admissions, morbidity, and mortality. Prior to the use of machine learning and deep learning methods, ADEs may not become well recognized until long after a drug has been approved and is widely used, which poses a significant challenge for ensuring patient safety. Consequently, there is a need to develop computational approaches for earlier identification of ADEs not detected during pre-registration clinical trials.
Methods: This paper presents a state-of-the-art network-based approach that models patients as subgraphs composed of nodes of International Classification of Diseases (ICD) codes and directed edges illustrating disease progression. Four Graph Neural Network (GNN) variants were employed to make sub-graph level predictions that answer three Research Questions (RQ): 1) whether ADE(s) would occur given a patient's prior diagnoses history, 2) when an ADE would occur, and 3) which ADE would occur. The first and second RQs were addressed using a binary classification approach. The third RQ was addressed using a multi-label classification model.
Results: The proposed network-based approach demonstrated superior performance in predicting ADEs, with the GraphSage model exhibiting the highest accuracy for both RQ 1 (0.8863) and RQ 3 (0.9367), while the Graph Attention Networks (GAT) model was found to perform best for RQ 2 (0.8769). Furthermore, an analysis segmented by ADE classification revealed that while RQs 1 and 3 exhibited minimal variance across different ADE categories, a distinct advantage was observed for categories B, C, and E in the context of RQ 2 when applying this sub-graph method.
Conclusion: The network-based approach demonstrates the potential of GNNs in supporting the early detection and prevention of ADEs. Accurately predicting ADEs could enable healthcare professionals to make informed clinical decisions, take preventive measures and adjust medication regimens before serious adverse events occur. The proposed prediction method could also lead to optimized usage of healthcare resources by preventing hospital admissions and reducing the overall burden of adverse drug events on the healthcare systems.
Competing Interests: Declaration of competing interest None Declared.
(Copyright © 2024 The Authors. Published by Elsevier Ltd.. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: