Scholarlink

This paper presents an AI-powered mHealth application for personalized health monitoring, integrating real-time tracking of vital signs with predictive analytics and an intelligent chatbot. Our key contributions include: (1) an elderly-friendly interface with enhanced accessibility, (2) a neural network-based health forecasting system, and (3) a context-aware chatbot for personalized guidance. The methodology combines user-centered design, machine learning, and natural language processing, ensuring security through encryption and regulatory compliance. Testing with 50 elderly users over three months showed 85% retention and a 73% increase in health tracking. The predictive model achieved 89% accuracy, and the chatbot handled 92% of queries autonomously. Health outcomes improved, with a 45% reduction in unnecessary clinical visits and a 67% enhancement in chronic disease management. This research advances mHealth by addressing elderly-focused design, predictive healthcare, and automated assistance, offering insights for intelligent health systems. Future work will enhance predictive capabilities and healthcare integration.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AI-Driven Personalization in Mobile Health Applications: An Elderly-Focused Approach to Health Monitoring and Prediction

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Raquel Dias,
  • André Chaves,
  • Paulo Vàz,
  • José Silva,
  • Pedro Martins,
  • Maryam Abbasi

摘要

This paper presents an AI-powered mHealth application for personalized health monitoring, integrating real-time tracking of vital signs with predictive analytics and an intelligent chatbot. Our key contributions include: (1) an elderly-friendly interface with enhanced accessibility, (2) a neural network-based health forecasting system, and (3) a context-aware chatbot for personalized guidance. The methodology combines user-centered design, machine learning, and natural language processing, ensuring security through encryption and regulatory compliance. Testing with 50 elderly users over three months showed 85% retention and a 73% increase in health tracking. The predictive model achieved 89% accuracy, and the chatbot handled 92% of queries autonomously. Health outcomes improved, with a 45% reduction in unnecessary clinical visits and a 67% enhancement in chronic disease management. This research advances mHealth by addressing elderly-focused design, predictive healthcare, and automated assistance, offering insights for intelligent health systems. Future work will enhance predictive capabilities and healthcare integration.