Abstract
Heart rate variability (HRV) is an important physiological marker for assessing the autonomic nervous system and a key indicator for monitoring progress in medical rehabilitation. This article explores how environmental factors, such as carbon dioxide (CO2) and particulate matter (PM), act as physiological stressors that can impact the effectiveness of the recovery process. A machine learning analysis was implemented to analyze HRV variations across diverse air quality conditions. The analysis shows that elevated concentrations of PM are significantly correlated with a reduction in HRV, indicating physiological stress that could hinder a patient’s recovery. The proposed system, which integrates real-time physiological and environmental monitoring using IoT devices, offers a new tool for personalizing rehabilitation. This study demonstrates the potential of using integrated monitoring systems and machine learning to optimize rehabilitation strategies, which can lead to more effective, personalized patient care and improved recovery outcomes.