MediLens: An AI-Powered Medicine Information and Assistance System
Abstract
Medication errors and difficulty accessing reliable
drug information remain significant challenges in modern healthcare.
MediLens is an AI-powered web-based medicine information
and assistance system designed to provide accurate,
accessible, and easy-to-understand medication details for users.
The system integrates Optical Character Recognition (OCR) to
identify medicines from images of drug labels or packaging and
retrieves verified information from trusted biomedical databases.
Natural Language Processing (NLP) and a cloud-based Large
Language Model (LLM) are used to generate contextual summaries
and answer user queries through an interactive conversational
assistant. The backend is implemented using the FastAPI
framework and communicates with external knowledge sources
and AI services through secure API integration. MediLens follows
a modular architecture that includes OCR processing, information
retrieval, and AI-driven response generation to ensure
scalability and reliability. Core functionalities include medicine
identification from images, structured drug information retrieval,
automated summarization, and interactive question answering.
By combining retrieval-based verification with conversational
AI, MediLens aims to improve public health literacy, reduce
misinformation about medications, and demonstrate the practical
application of artificial intelligence in healthcare information
systems.
Keywords:
Artificial Intelligence, Healthcare Informatics, Large Language Models, Medicine Information System, FastAPIPublished
Issue
Section
License
Copyright (c) 2026 International Journal on Emerging Research Areas

This work is licensed under a Creative Commons Attribution 4.0 International License.
All published work in this journal is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
How to Cite
Similar Articles
- Evelyn Susan Jacob, Joel John, Raynell Rajeev, Steve Alex , Syam Gopi , Malware Classification using Image Analysis , International Journal on Emerging Research Areas: Vol. 5 No. 1 (2025): IJERA
- Dr.Sinciya P.O, Aaron Varughese Bino, Anamin Fathima Anish, Aathira Krishna, Dona Maria Joseph, Unveiling Stress through Facial Expressions: A Literature Review on Detection Methods , International Journal on Emerging Research Areas: Vol. 4 No. 1 (2024): IJERA
- Jose P Pittappillil, Midhun Mohan, Nimisha Nigel, Nitin Sunil Thomas, Driving Agricultural Innovation: A Review of Technological Advancements in Smart Farming , International Journal on Emerging Research Areas: Vol. 4 No. 1 (2024): IJERA
- Joel Gijo, Bibin Kunnathettu Biju, K Ryan George, Bipin Dev B, Anju J Prakash, Machine Learning and Medical Authority Engagement for Antimicrobial Resistance Management: A Review of Surveillance, Prediction, and Stewardship , International Journal on Emerging Research Areas: Vol. 6 No. 1 (2026): IJERA
- Rema M K, Muhamed Ajmal K R, Deepak T G, Roshini M, Muhammed Bazir, INTERACTIVE TOY , International Journal on Emerging Research Areas: Vol. 3 No. 1 (2023): IJERA
- Aaron Samuel Mathew, Adhil Salim , From Exorbitant to Affordable: The Evolution of AI Training Costs , International Journal on Emerging Research Areas: Vol. 3 No. 1 (2023): IJERA
- Honey Joseph, A Survey and Analysis on Predicting Heart Disease Using Machine Learning Techniques , International Journal on Emerging Research Areas: Vol. 3 No. 1 (2023): IJERA
- Prinu Vinod Nair, Rohit Subash Nair, Samuel Thomas Mathew S, Ansamol Varghese, Weed detection using YOLOv3 and elimination using organic weedicides with Live feed on Web App , International Journal on Emerging Research Areas: Vol. 4 No. 1 (2024): IJERA
- Ansamol Varghese, Anoushkha Tresa, Athira John, Ignatious Ealias Roy, M S Gautham Sankar, A Machine Learning Approach to Fake News Detection , International Journal on Emerging Research Areas: Vol. 3 No. 1 (2023): IJERA
- Dipjyoti Deka, Rituparna Seal, Shubham Banik, Unmasking Fraudulent Job Ads: A Critical Review of Machine Learning Techniques for Detecting Fake Jobs , International Journal on Emerging Research Areas: Vol. 3 No. 1 (2023): IJERA
You may also start an advanced similarity search for this article.
