Recent advances in mobile technology have created new opportunities for observational and intervention studies in health research. Building on our established, highly configurable, and modular ecological momentary assessment (EMA) and Just-in-Time Adaptive Intervention (JITAI) mobile app framework, we enhance its capabilities with passive sensing, gamification, and artificial intelligence (AI)-based personalization. These enhancements support dynamic, context-sensitive interventions and mitigate the static nature of traditional large-scale electronic health (eHealth) studies and ecological momentary interventions (EMI). Passive mobile sensing allows unobtrusive monitoring of user behavior, health data, and context, while gamification boosts engagement and loyalty. AI-driven features will enable real-time, adaptive interventions tailored to individual user needs and conditions. We present in detail the enhanced cross-platform mobile app framework deployed in a large-scale EU study on adolescent physical activity and nutrition. We emphasize the potential of new features to improve user experience and Mobile Health (mHealth) intervention effectiveness. Additionally, we discuss the background, technical and ethical challenges, lessons learned, and implications for future applications in behavior change research.

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

Extending a Highly Configurable EMA and JITAI Mobile App Framework with Passive Sensing, Gamification, and AI Features for a Large-Scale Physical Activity and Nutrition Study

  • Carsten Vogel,
  • Robin Kraft,
  • Rodrigo Antunes Lima,
  • Abdul Rahman Idrees,
  • Patrick Steiger,
  • Rüdiger Pryss

摘要

Recent advances in mobile technology have created new opportunities for observational and intervention studies in health research. Building on our established, highly configurable, and modular ecological momentary assessment (EMA) and Just-in-Time Adaptive Intervention (JITAI) mobile app framework, we enhance its capabilities with passive sensing, gamification, and artificial intelligence (AI)-based personalization. These enhancements support dynamic, context-sensitive interventions and mitigate the static nature of traditional large-scale electronic health (eHealth) studies and ecological momentary interventions (EMI). Passive mobile sensing allows unobtrusive monitoring of user behavior, health data, and context, while gamification boosts engagement and loyalty. AI-driven features will enable real-time, adaptive interventions tailored to individual user needs and conditions. We present in detail the enhanced cross-platform mobile app framework deployed in a large-scale EU study on adolescent physical activity and nutrition. We emphasize the potential of new features to improve user experience and Mobile Health (mHealth) intervention effectiveness. Additionally, we discuss the background, technical and ethical challenges, lessons learned, and implications for future applications in behavior change research.