AI-Based Smart Healthcare Assistance System

Abstract: The healthcare landscape in India faces a unique set of challenges: a large patient-to-doctor ratio, limited physical access to specialists in rural areas, and high out-of-pocket costs. Digital tools that can partially address these gaps have become increasingly relevant. This paper presents an AI-Based Smart Healthcare Assistance System—a web- based platform built on the Django framework that integrates three conversational AI modules and a doctor appointment booking subsystem into a single application. The core modules include a symptom-based disease predictor using a trained random forest classifier with cosine-similarity-based input matching, a personalised Indian diet plan generator powered by a large language model (GPT-3.5-turbo), and a general health Q&A interface. Building on these, we have added a doctor appointment booking module where doctors and patients can register separately, doctors can manage their schedules and appointment requests from a dedicated dashboard, and patients can search for available doctors by specialisation, send appointment requests, track status, and cancel if needed. The system was tested for functional correctness, classification accuracy, and basic usability. Results show that the random forest classifier achieves 100% accuracy on the test set and all appointment lifecycle states function as expected. The platform demonstrates how a comparatively simple web stack can deliver meaningful AI-assisted healthcare access.

Keywords: Healthcare chatbot, disease prediction, random forest, diet planning, doctor appointment, Django, NLP, machine learning, telemedicine, GPT.