Olawade David B, Aderinto Nicholas, Clement David-Olawade Aanuoluwapo, Egbon Eghosasere, Adereni Temitope, Popoola Mayowa Racheal, Tiwari Ritika
Department of Allied and Public Health, School of Health, Sport and Bioscience, University of East London, London E16 2RD, UK; Department of Research and Innovation, Medway NHS Foundation Trust, Gillingham, Kent ME7 5NY, UK; Department of Public Health, York St John University, London E14 2BA, UK.
Department of Medicine and Surgery, Ladoke Akintola University of Technology, Ogbomoso, Nigeria.
Clin Neurol Neurosurg. 2025 Feb;249:108689. doi: 10.1016/j.clineuro.2024.108689. Epub 2024 Dec 10.
Stroke is a leading cause of morbidity and mortality worldwide, and early detection of risk factors is critical for prevention and improved outcomes. Traditional stroke risk assessments, relying on sporadic clinical visits, fail to capture dynamic changes in risk factors such as hypertension and atrial fibrillation (AF). Wearable technology (devices), combined with biometric data analysis, offers a transformative approach by enabling continuous monitoring of physiological parameters. This narrative review was conducted using a systematic approach to identify and analyze peer-reviewed articles, reports, and case studies from reputable scientific databases. The search strategy focused on articles published between 2010 till date using pre-determined keywords. Relevant studies were selected based on their focus on wearable devices and AI-driven technologies in stroke prevention, diagnosis, and rehabilitation. The selected literature was categorized thematically to explore applications, opportunities, challenges, and future directions. The review explores the current landscape of wearable devices in stroke risk assessment, focusing on their role in early detection, personalized care, and integration into clinical practice. The review highlights the opportunities presented by continuous monitoring and predictive analytics, where AI-driven algorithms can analyze biometric data to provide tailored interventions. Personalized stroke risk assessments, powered by machine learning, enable dynamic and individualized care plans. Furthermore, the integration of wearable technology with telemedicine facilitates remote patient monitoring and rehabilitation, particularly in underserved areas. Despite these advances, challenges remain. Issues such as data accuracy, privacy concerns, and the integration of wearables into healthcare systems must be addressed to fully realize their potential. As wearable technology evolves, its application in stroke care could revolutionize prevention, diagnosis, and rehabilitation, improving patient outcomes and reducing the global burden of stroke.
中风是全球发病和死亡的主要原因之一，早期发现风险因素对于预防和改善预后至关重要。传统的中风风险评估依赖于不定期的临床就诊，无法捕捉高血压和心房颤动（AF）等风险因素的动态变化。可穿戴技术（设备）与生物特征数据分析相结合，通过实现对生理参数的持续监测，提供了一种变革性的方法。本叙述性综述采用系统方法，从著名科学数据库中识别和分析同行评审的文章、报告和案例研究。搜索策略聚焦于使用预先确定的关键词在2010年至今发表的文章。相关研究根据其对可穿戴设备和人工智能驱动技术在中风预防、诊断和康复方面的关注进行选择。所选文献按主题分类，以探索应用、机会、挑战和未来方向。该综述探讨了可穿戴设备在中风风险评估中的现状，重点关注其在早期检测、个性化护理以及融入临床实践中的作用。该综述强调了持续监测和预测分析带来的机会，其中人工智能驱动的算法可以分析生物特征数据以提供量身定制的干预措施。由机器学习驱动的个性化中风风险评估能够制定动态和个性化的护理计划。此外，可穿戴技术与远程医疗的整合促进了远程患者监测和康复，特别是在服务不足的地区。尽管取得了这些进展，但挑战依然存在。数据准确性、隐私问题以及可穿戴设备融入医疗保健系统等问题必须得到解决，以充分发挥其潜力。随着可穿戴技术的发展，其在中风护理中的应用可能会彻底改变预防、诊断和康复，改善患者预后并减轻全球中风负担。
J Med Internet Res. 2025-5-6
Neuroscience. 2025-4-19
BMC Oral Health. 2025-4-18
J Med Internet Res. 2024-9-10
J Pers Med. 2024-11-1
Phys Act Nutr. 2024-12
Nat Rev Endocrinol. 2025-9-8
J Cardiovasc Dev Dis. 2025-7-23
Diagnostics (Basel). 2025-6-9
Sensors (Basel). 2025-3-11
Am J Prev Cardiol. 2025-3-9
Clin Neurol Neurosurg. 2025-2
Zotero 插件