Drug Recommendation System In Medical Emergencies

souda Lakshmi Priya; gunda Durgesh; vadthyavath Naveen; Mrs.J.Santoshi

doi:10.62647/IJITCE2025V13I2PP1296-1300

Authors

souda Lakshmi Priya team Member,, Department Of Computer Science And Engineering Matrusri Engineering College Author
gunda Durgesh team Member,, Department Of Computer Science And Engineering Matrusri Engineering College Author
vadthyavath Naveen team Member,, Department Of Computer Science And Engineering Matrusri Engineering College Author
Mrs.J.Santoshi Assistant Professor Department Of Computer Science And Engineering Matrusri Engineering College Author

DOI:

https://doi.org/10.62647/IJITCE2025V13I2PP1296-1300

Keywords:

Drug Recommendation System, Transformer Model, Natural Language Processing, AI in Healthcare, Patient Safety, Drug Interaction Detection, Next.js, TailwindCSS, Deep Learning, Healthcare Informatics, Responsive Web Application, Symptom Analysis, Real-time Recommendations.

Abstract

In recent years, the convergence of artificial intelligence (AI) and healthcare has unlocked transformative possibilities for personalized patient care. This study presents a Drug Recommendation System that employs a transformer-based natural language processing (NLP) model to deliver medication suggestions based on a user’s reported symptoms, medical history, and profile data.
The system features a robust Python backend powered by a fine-tuned ClinicalBERT transformer, coupled with a Next.js and TailwindCSS frontend that provides a modern, responsive, and engaging user experience. It processes patient inputs in real-time, detects potential drug interactions, and generates context-aware recommendations using trusted medical databases.
Emphasis is placed on user safety, data privacy, and clinical reliability, making the system a valuable tool for both patients and healthcare professionals. This work demonstrates the potential of AI-driven platforms to support clinical decision-making by providing accurate, explainable, and proactive drug recommendations. By integrating deep learning and healthcare informatics into a responsive digital ecosystem, the system promotes safer, more personalized treatment adherence and empowers users in their healthcare journey.