ArogyaAI: An Integrated LLM-Powered Healthcare Intelligence System

Abstract: Healthcare systems continue to struggle with fragmented patient records, poor AI transparency, and limited telemedicine integration. ArogyaAI is a web-based platform built using Django and SQLite that addresses these issues in one place. It uses the LLaMA 3.3 70B language model through the Groq API to provide symptom guidance and automatically summarize medical reports. Integrated video consultations run directly in the browser via Jitsi Meet, and access is controlled based on user role—patient, doctor, or administrator. Testing shows the system handles multilingual conversations (English, Hindi, Hinglish), simplifies appointment workflows, and reduces the difficulty of reading clinical documents. The design demonstrates how modern web tools and large language models can work together to improve healthcare access.

Keywords: Artificial Intelligence, Electronic Health Records, Generative AI, Healthcare Web Application, LLaMA, Telemedicine.