Article Details
  • Published Online:
    January  2026
  • Product Name:
    The IUP Journal of Computer Sciences
  • Product Type:
    Article
  • Product Code:
    IJCS030126
  • DOI:
    10.71329/IUPJCS/2026.20.1.27-37
  • Author Name:
    M Roohi Jahan, Swiya Jaiswal and Prashasti Kanikar
  • Availability:
    YES
  • Subject/Domain:
    Engineering
  • Download Format:
    PDF
  • Pages:
    27-37
Volume 20, Issue 1, January-March 2026
A Knowledge Graphs-Based System for Personalized Drug Allergy Evaluations and Recommendations
Abstract

A significant challenge of modern healthcare is adverse drug reactions, of which drug allergies pose serious threats to patient safety. Personalized drug allergy recommendation systems are of great importance in mitigating such risks; however, current models cannot adapt to the individual requirements of patients. The paper presents a new approach that integrates knowledge graphs with graph neural networks (GNN) for personalized drug allergy recommendations. By modeling patients, drugs and allergies as nodes and their interactions as edges, the model can trace complex relationships within patient data. This advances personalized healthcare by providing a scalable, dynamic approach for drug safety recommendations based on individual patient profiles.

Introduction

Adverse drug reactions (ADRs) result in hospitalization, increased cost and death (Li et al., 2021; Wang et al., 2019).