动态血糖监测设备物联网技术的研究现状与展望

      Research Status and Prospects of Internet of Things Technology for Continuous Glucose Monitoring Devices

      • 摘要: 全球糖尿病患病率持续攀升,血糖监测作为糖尿病管理的核心环节,其技术革新至关重要。传统指尖采血监测存在明显局限,无法完整反映血糖动态变化过程,而融合物联网(Internet of Things,IoT)技术的动态血糖监测(continuous glucose monitoring,CGM),推动了糖尿病血糖管理从“间断点测”到“连续动态监测+智能干预”的模式转型,现已成为糖尿病全周期健康管理的重要技术支撑。该文系统梳理了CGM物联网技术的研究现状:核心传感器已形成植入式电化学、无创监测、柔性可穿戴三大技术路径,虚拟CGM技术拓展了应用边界;集成式动态血糖监测系统(integrated continuous glucosemonitoring,iCGM)通过标准化设计与多学科协同优化临床适配性;AI技术的深度融合推动血糖监测迈向“智能决策 ”,各类深度学习模型在预测精度与场景适配性上持续提升。同时,CGM物联网技术的临床转化与规模化应用仍面临多维度核心挑战,包括传感器长期稳定性不足、AI算法临床认证缺乏统一标准、设备成本高、数据隐私保护与共享机制不完善等。未来,CGM物联网技术将围绕传感技术创新、临床使用范式转移及产业生态化落地等方向持续演进。该研究为CGM物联网技术的转化与临床应用提供参考。

         

        Abstract: The global prevalence of diabetes continues to rise. As a core component of diabetes management, technological innovation in blood glucose monitoring plays a critical role. Traditional fingertip blood sampling monitoring has obvious limitations and cannot fully reflect dynamic glucose changes. In contrast, continuous glucose monitoring (CGM) integrated with the Internet of Things (IoT) technology has driven the transformation of diabetes blood glucose management from intermittent spot detection to continuous dynamic monitoring and intelligent intervention, serving as an important technical support for the full-cycle management of diabetes. This paper systematically reviews the research status of CGM-IoT technology. Three major technical approaches have been established for core sensors, including implantable electrochemical monitoring, non-invasive monitoring, and flexible wearable monitoring, while virtual CGM technology has further expanded its application boundaries. Integrated continuous glucose monitoring (iCGM) systems improve clinical adaptability through standardized design and multidisciplinary collaboration. The in-depth integration of artificial intelligence (AI) technology has driven the transformation of blood glucose monitoring toward intelligent decision-making, with various deep learning models achieving continuous improvements in prediction accuracy and scenario adaptability. Meanwhile, the clinical translation and large-scale application of CGM-IoT technology face multiple key challenges, including insufficient long-term stability of sensors, the lack of unified standards for the clinical certification of AI algorithms, high equipment costs, and imperfect mechanisms for data privacy protection and data sharing. In the future, CGM-IoT technology will continue to evolve in three key directions: innovation of sensing technology, paradigm shift in clinical application, and industrial ecosystem development. This study will provide a useful reference for the translational research and clinical application of CGM-IoT technology.

         

      /

      返回文章
      返回