| APPLICATION OF ARTIFICIAL INTELLIGENCE METHODS IN MONITORING AND PERFORMANCE ASSESSMENT OF OLDER ADULTS: A REVIEW OF EMERGING TECHNOLOGIES |
| Paper ID : 1417-SPORTCONGRESS |
| Authors |
|
Fatemeh Zendehpour *, Sadegh Amanishalamzari Department of Exercise Physiology, Faculty of Physical Education and Sport Sciences, Kharazmi University, Tehran, Iran |
| Abstract |
| Abstract Introduction: This study provides a systematic and comprehensive review of artificial intelligence (AI) applications in monitoring, evaluating, and managing the physical and behavioral performance of older adults. Advanced AI-driven technologies based on machine learning, computer vision, and biosignal analytics developed to enhance the quality of life, prevent functional decline, and improve safety and self-care are critically examined. Additionally, technical, ethical, and operational challenges related to data accuracy, privacy, and user acceptance are analyzed. Methods: An analytical comparative review approach was employed. Intelligent health monitoring platforms, including Health Arc, Binah.ai, One Step, Teton.ai, and Metrifit, were analyzed in terms of technical functionality, data acquisition methods (vital signs, motor activity, and behavioral patterns), employed AI algorithms, and integration with healthcare systems. Extracted data were synthesized to identify key strengths, limitations, and cross-platform challenges, including privacy concerns, algorithmic reliability, and accessibility barriers. Based on these findings, a conceptual framework was proposed to guide the design of integrated, intelligent elderly monitoring systems. Results: The analysis revealed that AI technologies can enable non-invasive, real-time monitoring of physiological parameters such as heart rate, heart rate variability (HRV), blood pressure, respiratory rate, oxygen saturation (SpO₂), sleep quality, and motor performance (e.g., gait, balance, movement velocity). These systems can detect abnormal physiological patterns and predict fatigue, performance decline, or fall risk. However, challenges such as physiological data instability, reduced algorithmic accuracy in chronic conditions, motion artifacts, and privacy issues remain significant. Conclusion: AI-driven technologies demonstrate strong potential to revolutionize elderly care by enabling continuous, accurate, and personalized health monitoring. Future efforts should prioritize human-centered, ethically grounded, and technically robust systems that improve precision, trust, and usability. The proposed framework outlines a pathway to bridge current knowledge gaps and advance intelligent elderly monitoring solutions. |
| Keywords |
| Keywords: Application, Monitoring, Technologies |
| Status: Abstract Accepted (Poster Presentation) |
