Bridging Usability and User Experience in AI-Based Fall Detection: A Systematic Literature Review on User-Centered Design Approach for Enhanced Adoption

This systematic literature review delves into the usability challenges and adoption factors of AI-based fall detection systems, emphasizing the importance of a user-centered design approach. The study identifies primary usability issues such as poor interface design, alert fatigue, and cumbersome data entry processes that hinder the adoption of these systems. It explores how user-centered design principles can create more personalized and adaptive alert mechanisms, catering to diverse user needs. The research follows the PRISMA methodology, systematically reviewing 30 studies to analyze the role of user-centered design in enhancing system adoption. Key findings highlight the significance of adaptive AI alerts and multimodal user experience in improving system effectiveness. The study also discusses the integration of advanced technologies like AI, AR, and blockchain with wearable devices, suggesting a trajectory toward more sophisticated and user-centric healthcare solutions. Future research directions include AI explainability, personalized AI-UX interactions, and longitudinal adoption studies to further improve the adoption rates and effectiveness of fall detection systems.