Making sense of mobile health data: an open architecture to improve individual- and population-level health.
Making sense of mobile health data: an open architecture to improve individual- and population-level health.
复制标题
DOI：
10.2196/jmir.2152
复制
发表时间：
2012-08-09
影响因子：
7.4
通讯作者：
Sim I
中科院分区：
文献类型：
--
作者：
Chen C;Haddad D;Selsky J;Hoffman JE;Kravitz RL;Estrin DE;Sim I
移动电话和设备凭借其持续存在、数据连接和多个内置传感器，可以支持与日常生活集成的全天候慢性病预防和管理。这些移动健康(MHealth)设备可以产生大量位置丰富、实时、高频的数据。不幸的是，这些数据往往充满了偏见、噪声、可变性和差距。还没有开发出强大的工具和技术来使mHealth数据对患者和临床医生更有意义。为了最有用，健康数据应该可以在多个mHealth应用程序之间共享，并连接到电子健康记录。缺乏数据共享以及缺乏理解健康数据的工具和技术是限制移动健康在改善健康结果方面的影响的严重瓶颈。我们描述了Open mHealth，这是一个非营利性组织，它正在构建一个开放的软件体系结构来解决这些数据共享和“意义制造”瓶颈。我们的体系结构由开放源码软件模块组成，这些模块使用最小的公共元数据集定义良好的接口。已经开发了一套名为InfoVis的初始模块，用于数据分析和可视化。第二组模块，我们的个人证据架构，将支持来自mHealth数据的科学推理。这些个人证据架构模块将包括标准化的、经过验证的临床测量，以支持新的评估方法，如n-of-1研究。Open mHealth的所有模块都被设计为可在多个应用程序、疾病状况和用户群中重复使用，以最大限度地提高影响和灵活性。我们还在建立一个开放的开发人员和卫生创新者社区，仿照互联网最初发展时采取的开放方法，以促进围绕新工具和技术的有意义的跨学科合作。一个开放的移动健康社区和架构将促进提高移动健康的效率、效力和创新。
Mobile phones and devices, with their constant presence, data connectivity, and multiple intrinsic sensors, can support around-the-clock chronic disease prevention and management that is integrated with daily life. These mobile health (mHealth) devices can produce tremendous amounts of location-rich, real-time, high-frequency data. Unfortunately, these data are often full of bias, noise, variability, and gaps. Robust tools and techniques have not yet been developed to make mHealth data more meaningful to patients and clinicians. To be most useful, health data should be sharable across multiple mHealth applications and connected to electronic health records. The lack of data sharing and dearth of tools and techniques for making sense of health data are critical bottlenecks limiting the impact of mHealth to improve health outcomes. We describe Open mHealth, a nonprofit organization that is building an open software architecture to address these data sharing and “sense-making” bottlenecks. Our architecture consists of open source software modules with well-defined interfaces using a minimal set of common metadata. An initial set of modules, called InfoVis, has been developed for data analysis and visualization. A second set of modules, our Personal Evidence Architecture, will support scientific inferences from mHealth data. These Personal Evidence Architecture modules will include standardized, validated clinical measures to support novel evaluation methods, such as n-of-1 studies. All of Open mHealth’s modules are designed to be reusable across multiple applications, disease conditions, and user populations to maximize impact and flexibility. We are also building an open community of developers and health innovators, modeled after the open approach taken in the initial growth of the Internet, to foster meaningful cross-disciplinary collaboration around new tools and techniques. An open mHealth community and architecture will catalyze increased mHealth efficiency, effectiveness, and innovation.
登录
查看更多内容
影响因子：
4.2
作者：
Nikles, C Jane;Yelland, Michael;Del Mar, Chris
通讯作者：
Del Mar, Chris
影响因子：
6.6
作者：
Kravitz, RL;Duan, NH;Braslow, J
通讯作者：
Braslow, J
影响因子：
6.6
作者：
Kravitz, Richard L.;Duan, Naihua;Weisner, Thomas S.
通讯作者：
Weisner, Thomas S.
影响因子：
4.7
作者：
Haug, Severin;Meyer, Christian;John, Ulrich
通讯作者：
John, Ulrich
影响因子：
2.4
作者：
Obermayer, JL;Riley, WT;Jean-Mary, J
通讯作者：
Jean-Mary, J