Graph Neural Network–Driven Nano-Drug Interaction Modeling for Personalized Chemotherapy Planning in Intelligent Virtual Oncology Clinics
Journal of Nano Molecular Intelligence and Virtual Health Systems · 30.06.2025 · 1 (2) · 1
DOI: 10.70023/nmivhs.121 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Nano Molecular Intelligence and Virtual Health Systems, online erschienen am 30.06.2025. Verfasst von Lavanya B.
Themen: Onkologische Pflege
Abstract (Originalsprache)
Treatment planning for cancer is often complicated because of the interactions between the nanodrug, tumor biology and clinical characteristics of the patient. Traditional chemotherapy planning techniques tend to be nonspecific, insufficient in predicting the efficacy of chemotherapies, incomplete in modelling drug interactions and cannot determine the best treatment plan for a particular patient. Side effects, poor treatment efficacy, and health care burden can be a result of these restrictions. The work proposes a Graph Neural Network (GNN)–Driven Nano-Drug Interaction Modeling Framework for personalized chemotherapy planning in an intelligent virtual oncology clinic to address these challenges. The proposed framework is based on the concept of graph structures for nano-drugs, molecular targets, cancer biomarkers and patient health records, which can be used to extract complex biological and clinical relationships. The GNN model can learn these interactions to predict drug responses, toxicity and therapeutic suitability, and to propose a personalized chemotherapy treatment regimen, according to the patient's condition. The framework was evaluated by means of a comprehensive dataset of edges, which contains all the edges from clinical cancer repositories and virtual oncology databases. Experimental results showed excellent predictive performance, with high values of Accuracy (98.74%), Precision (98.31%), Recall (98.08%), F1-Score (98.19%), AUC (99.12%), and Specificity (97.95%). Furthermore, the model proposed was claimed to be more accurate than the conventional machine learning techniques in predicting adverse drug interactions with 34.6% accuracy. Based on the results, the framework can be a very important component of chemotherapy planning and can be used in clinical decision-making to enhance the effectiveness of chemotherapy.
Zitieren
APA
B, L. (2025). Graph Neural Network–Driven Nano-Drug Interaction Modeling for Personalized Chemotherapy Planning in Intelligent Virtual Oncology Clinics. Journal of Nano Molecular Intelligence and Virtual Health Systems, 1(2), 1. https://doi.org/10.70023/nmivhs.121
Vancouver
B L. Graph Neural Network–Driven Nano-Drug Interaction Modeling for Personalized Chemotherapy Planning in Intelligent Virtual Oncology Clinics. Journal of Nano Molecular Intelligence and Virtual Health Systems. 2025;1(2):1. doi:10.70023/nmivhs.121
BibTeX
@article{B2025,
author = {B, Lavanya},
title = {Graph Neural Network–Driven Nano-Drug Interaction Modeling for Personalized Chemotherapy Planning in Intelligent Virtual Oncology Clinics},
journal = {Journal of Nano Molecular Intelligence and Virtual Health Systems},
year = {2025},
volume = {1},
number = {2},
pages = {1},
doi = {10.70023/nmivhs.121}
}
EUVIMED