Wearable Edge-IoT and AI-Driven Cardiopulmonary Health Monitoring: A Review of Geofenced Air-Quality Intervention Frameworks

Abstract

Air pollution has emerged as one of the most critical environmental health challenges of the twenty-first century, significantly contributing to cardiovascular and respiratory diseases worldwide. Long-term exposure to pollutants such as particulate matter (PM₂.₅ and PM₁₀), nitrogen dioxide (NO₂), sulphur dioxide (SO₂), ozone (O₃), and carbon monoxide (CO) has been associated with an increased risk of hypertension, myocardial infarction, chronic obstructive pulmonary disease (COPD), asthma, stroke, and other cardiopulmonary disorders. Conventional Air Quality Index (AQI)-based monitoring systems provide general environmental information but lack the capability to assess individual physiological responses or deliver personalized health recommendations. This limitation has motivated the development of intelligent healthcare systems that integrate environmental monitoring with real-time physiological sensing. This review presents a comprehensive analysis of wearable Edge-IoT architectures for AI-driven cardiopulmonary health monitoring, emphasizing environmental sensing, physiological biomarkers, machine learning-based risk prediction, geospatial intelligence, and personalized intervention frameworks. It also discusses key mathematical models supporting intelligent healthcare systems, including Air Quality Index (AQI) computation, Haversine distance-based geofencing, exposure assessment methods, and the Total Health Risk Index (THRI), which integrates environmental exposure and physiological parameters into a unified health risk score. Furthermore, the review examines recent developments in supervised learning, deep learning, and explainable artificial intelligence for disease prediction and clinical decision support. Finally, it identifies current research challenges related to sensor accuracy, multimodal data fusion, interoperability, energy-efficient edge computing, cybersecurity, privacy, and clinical validation, while highlighting future research directions involving federated learning, digital twins, explainable Edge-AI, and 6G-enabled healthcare ecosystems.