Key points are not available for this paper at this time.
The rapid advancement of artificial intelligence (AI) has significantly transformed the landscape of health monitoring systems, shifting the focus from reactive diagnostics to proactive, predictive analytics. This review provides a comprehensive analysis of AI algorithms employed in predictive health monitoring, with particular attention to their integration into mobile applications, wearable technologies, and immersive systems based on virtual and augmented reality (VR/AR). The study explores traditional machine learning models, deep learning architectures, and hybrid approaches applied to physiological data streams such as heart rate, oxygen saturation, motion, and sleep quality. Special emphasis is placed on the challenges of data heterogeneity, model interpretability, privacy, and real-time processing. Although real-world deployment examples are limited in academic literature, we discuss representative case studies and emerging applications to illustrate the current state of practice. This paper concludes by outlining future research directions, including the convergence of AI with immersive environments, digital twins, and explainable AI frameworks, paving the way toward intelligent, personalized, and context-aware health monitoring solutions.
Daineko et al. (Wed,) studied this question.