Scholarlink

<p>The rising prevalence of chronic diseases demands a more effective healthcare management approach to overcome the constraints of existing health monitoring devices, including user intrusiveness and fragmented data. This perspective proposes the peri-body perception space, as a human-centric framework for chronic disease management. Conceived as a human-centric intelligent environment, it enables continuous, non-intrusive acquisition of multi-dimensional physiological and behavioral data by integrating contact-based and non-contact sensing. The framework features four characteristics: boundary plasticity, multi-sensory integration, functional adaptability, and social extensibility. For instance, when a patient moves from hospital to home, the system supports boundary plasticity through seamless transition from hospital-grade to home-based devices. It achieves multi-sensory integration through joint vital sign tracking by wearable and ambient sensors, enables functional adaptability by dynamically adjusting alert thresholds based on the patient’s personal baseline, and demonstrates social extensibility by sharing data across care settings. This framework directly serves the three goals of predictive, preventive and personalized medicine (PPPM). It turns these concepts into practical actions through continuous non-intrusive monitoring and adaptive data analysis. Built on a closed-loop system, this framework starts with human-centered, non-intrusive continuous health monitoring and leverages advanced signal processing and artificial intelligence to enable a transition from multi-modal data fusion to early risk warning. We also critically examine the existing challenges in hardware-software integration, multi-modal data fusion, and human-machine interaction within the peri-body perception space. Looking ahead, the integration of flexible sensing devices and cross-scenario privacy protection, adaptive modeling and intervention simulation, and human-machine interaction and personalized feedback will enable more autonomous, precise, and context-aware chronic disease management, marking a significant step forward in healthcare.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

New healthcare management framework informed by peri-body perception space: a perspective

  • 期刊论文

  • 发表日期：

    2026年7月8日

查看全文
  • Chaoqun Dong,
  • Yan Ji,
  • Ruzhen Luo,
  • Xuemei Fu,
  • Zhongmin Fu,
  • Yingying Huang,
  • Ting Yi,
  • Zhifei Chen,
  • Yiwen Hu,
  • Ziqi Chen,
  • Shimeng Dai,
  • Guangming Tao,
  • Hongyu Sun

摘要

The rising prevalence of chronic diseases demands a more effective healthcare management approach to overcome the constraints of existing health monitoring devices, including user intrusiveness and fragmented data. This perspective proposes the peri-body perception space, as a human-centric framework for chronic disease management. Conceived as a human-centric intelligent environment, it enables continuous, non-intrusive acquisition of multi-dimensional physiological and behavioral data by integrating contact-based and non-contact sensing. The framework features four characteristics: boundary plasticity, multi-sensory integration, functional adaptability, and social extensibility. For instance, when a patient moves from hospital to home, the system supports boundary plasticity through seamless transition from hospital-grade to home-based devices. It achieves multi-sensory integration through joint vital sign tracking by wearable and ambient sensors, enables functional adaptability by dynamically adjusting alert thresholds based on the patient’s personal baseline, and demonstrates social extensibility by sharing data across care settings. This framework directly serves the three goals of predictive, preventive and personalized medicine (PPPM). It turns these concepts into practical actions through continuous non-intrusive monitoring and adaptive data analysis. Built on a closed-loop system, this framework starts with human-centered, non-intrusive continuous health monitoring and leverages advanced signal processing and artificial intelligence to enable a transition from multi-modal data fusion to early risk warning. We also critically examine the existing challenges in hardware-software integration, multi-modal data fusion, and human-machine interaction within the peri-body perception space. Looking ahead, the integration of flexible sensing devices and cross-scenario privacy protection, adaptive modeling and intervention simulation, and human-machine interaction and personalized feedback will enable more autonomous, precise, and context-aware chronic disease management, marking a significant step forward in healthcare.