WEARABLE TECHNOLOGIES AND AI-DRIVEN ANALYTICS FOR CIRCADIAN RHYTHM MONITORING: OPPORTUNITIES AND CHALLENGES IN HEALTHCARE

Background: Circadian rhythm is a central regulator of human physiology, governing metabolic, endocrine, and neurobehavioral processes. Disruption of circadian alignment has been associated with obesity, insulin resistance, dyslipidemia, depression, and anxiety. Maintaining circadian health is therefore essential for both metabolic and mental well-being. In parallel, the rapid expansion of wearable technologies and digital health applications has enabled continuous, non-invasive monitoring of sleep–wake cycles and physiological parameters. When combined with artificial intelligence (AI), these tools offer new opportunities to assess and optimize circadian health in real-world settings. Objective: This review aims to summarize recent evidence on the use of wearable devices and AI-driven applications in monitoring circadian rhythm, with particular focus on their implications for metabolic and mental health. Methods: A literature review was conducted, focusing on publications between 2020 and 2025. Databases including PubMed, Scopus, and Web of Science were searched using keywords such as “circadian rhythm,” “wearables,” “digital health,” “artificial intelligence,” “metabolic disorders,” and “mental health.” Studies evaluating digital biomarkers, predictive algorithms, and clinical or public health applications of wearable-based monitoring were included. Results: Current evidence indicates that wearables reliably measure sleep duration, activity levels, heart rate variability, and proxies of circadian alignment. AI-driven analytics enhance the precision of these measurements, enabling early detection of circadian misalignment and prediction of health outcomes such as metabolic syndrome or depressive episodes. Applications include continuous monitoring in high-risk populations, integration with telemedicine platforms, and development of personalized lifestyle interventions. However, challenges persist, including limited validation against gold-standard clinical tools, data privacy concerns, lack of standardized protocols, and unequal access to digital health technologies. Conclusion: Wearable devices combined with AI-based analytics represent a promising approach to promoting circadian health and preventing related disorders. Future research should prioritize rigorous clinical validation, ethical frameworks for data management, and integration into healthcare systems to maximize their potential impact on both individual and population health.