AI-Assisted Quantum-Enhanced 5G Smart Healthcare System for Multi-Symptom Disease Prediction

The growing need for accessible and efficient healthcare services has driven the creation of intelligent systems that can predict diseases in their early stages. This paper introduces an AI-enhanced smart healthcare system designed to predict multiple diseases based on symptoms reported by users. The system is built using React.js and JavaScript, and it relies on a structured JSON dataset that includes disease names, symptoms, causes, medicines, and risk levels. It matches user-provided symptoms with existing disease records, computes symptom similarity scores, and shows the most likely disease along with related health details. The system also includes user authentication and a record of previous predictions to ensure ease of access and better data management. The evaluation dashboard indicates that the system achieved a validation accuracy of 96.82%, macro-precision of 96.48%, macro-recall of 95.69%, and a macro F1-score of 95.54% over 12,060 test cases. This represents a significant improvement from the previous project's validation accuracy of 80.26%, showing an increase of 16.56 percentage points. The study also outlines the potential of 5G communication for enhancing connected healthcare services and Grover’s quantum search algorithm for future optimization in search processes. However, these technologies are currently conceptual and the system still relies on conventional JavaScript-based symptom matching. The objective of the system is to provide users with a user-friendly interface for accessing initial health information. However, it is explicitly stated that its predictions should not be used as a substitute for professional medical diagnosis or treatment.