mDOT TR&D3 (Translation): Translation of Temporally Precise mHealth via Efficient and Embeddable Privacy-aware Biomarker Implementations

mDOT TR

• 批准号: 10541810
• 负责人: Emre Ertin
• 金额: $ 28.14万
• 依托单位: UNIVERSITY OF MEMPHIS
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-07-15 至 2025-11-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10541810
• 关键词: Address; Algorithms; Architecture; Awareness; Behavioral; Biological Markers; Cellular Phone; Chronic Disease; Clinic; Cloud Computing; Collaborations; Collection; Communication; Communities; Companions; Computational Technique; Computer software; Computing Methodologies; Data; Data Collection; Development; Devices; Digital biomarker; Disease Outcome; Eating; Ensure; Fatigue; Feedback; Frequencies; Generations; Health; Healthcare; Image; Individual; Infrastructure; Intelligence; Intervention; Lead; Life; Life Cycle Stages; Machine Learning; Medical; Medicine; Metadata; Methodology; Methods; Modality; Motion; Noise; Observational Study; Ohio; Participant; Patients; Personally Identifiable Information; Physiological; Physiology; Principal Investigator; Privacy; Research; Research Activity; Research Design; Research Personnel; Resource-limited setting; Resources; Risk; Running; Sampling; Services; Side; Signal Transduction; Smoking; Software Design; Stream; Stress; Structure; System; Technology; Time; Training; Translations; Trust; Universities; Work; biopsychosocial; cloud platform; craving; data reduction; data sharing; denoising; design; healthy lifestyle; high dimensionality; improved; mHealth; machine learning algorithm; mobile computing; multiple chronic conditions; next generation; open source; point of care; prevent; prototype; public health relevance; radio frequency; reconstruction; research study; sensor; signal processing; software development; synergism; technological innovation; technology research and development; tool; usability; wearable device; wearable platform; wearable sensor technology

Principal Investigator: Kumar, Santosh TR&D3: Translation of Temporally Precise mHealth via Efficient and Embeddable Privacy-aware Biomarker Implementations Lead: Dr. Emre Ertin, The Ohio State University; 10% effort (1.2 CM) Abstract: The mHealth Center for Discovery, Optimization & Translation of Temporally-Precise Interventions (the mDOT Center) will enable a new paradigm of temporally-precise medicine to maintain health and manage the growing burden of chronic diseases. The mDOT Center will develop and disseminate the methods, tools, and infrastructure necessary for researchers to pursue the discovery, optimization and translation of temporally- precise mHealth interventions. Such interventions, when dynamically personalized to the moment-to-moment biopsychosocial-environmental context of each individual, will precipitate a much-needed transformation in healthcare by enabling patients to initiate and sustain the healthy lifestyle choices necessary for directly managing, treating, and in some cases even preventing the development of medical conditions. Organized around three Technology Research & Development (TR&D) projects, mDOT represents a unique national resource that will develop multiple methodological and technological innovations and support their translation into research and practice by the mHealth community in the form of easily deployable wearables, apps for wearables and smartphones, and a companion mHealth cloud system, all open-source. TR&D3 will develop, validate and disseminate algorithms, tools and software/hardware designs for translation of temporally-precise mHealth interventions through resource efficient, real time, low-latency and privacy-aware implementation of an array of digital biomarkers that can be deployed at scale. Our approach is centered around a hierarchical computing framework that reduces the data into minimal modular abstractions called Micromarkers computed at the edge devices (Aim 1). Modular Micromarker abstractions are used to compress task-specific information relevant to biomarker computations at the edge devices while stripping nuisance variables such as hardware biases/drifts and background levels not pertinent to inference. Our hierarchical computing framework can be extended to implement high data rate sensor arrays at edge devices to be used at new point of care and ambulatory settings. This is accomplished through integrating a compressive sensing pre-processor to achieve signal acquisition in a resource constrained setting (Aim 2). Finally, TR&D3 will create computational mechanisms and a general biomarker privacy framework to enable participant control over the privacy-utility trade-offs during study design, data collection, and sharing of collected mHealth data for third party research when data cross trust domains (Aim 3). These technologies will be developed in collaboration with collaborative projects and will be disseminated to service projects to ensure that TR&D3 technologies can solve real problems facing the health research community and ensure the usability of these technologies by investigators who are external to the mDOT investigating team. TR&D3 will synergistically work in partnership with the other TR&D projects, the Training and Dissemination Core, and the Administration Core to maximize the societal impact of TR&D3 technologies. 1

首席研究员：库马尔，桑托什 TR＆D3：通过高效且可嵌入的隐私意识转换时间精确的MHealth 生物标志物实现 负责人：俄亥俄州立大学Emre Ertin博士； 10％的努力（1.2厘米） 摘要：MHealth发现，优化和翻译的暂时性干预中心 （MDOT中心）将使暂时药物的新范式保持健康和管理 慢性疾病的负担越来越大。 MDOT中心将开发和传播方法，工具， 研究人员追求时间的发现，优化和翻译所需的基础设施 精确的MHealth干预措施。这样的干预措施，当动态性地对瞬间 每个个体的生物心理社会环境环境将促成急需的转变 通过使患者能够直接启动和维持健康的生活方式选择来进行医疗保健 管理，治疗，在某些情况下甚至阻止医疗状况的发展。有组织 MDOT大约三个技术研发（TR＆D）项目，代表了一个独特的国家 将开发多种方法论和技术创新并支持其翻译的资源 以易于部署的可穿戴设备的形式进入MHealth社区的研究和练习 可穿戴设备和智能手机，以及配套MHealth云系统，都是开源的。 TR＆D3将开发，验证和传播用于翻译的算法，工具和软件/硬件设计 通过资源效率，实时，低延迟和隐私意识，暂时专门的MHealth干预措施 可以大规模部署的一系列数字生物标志物的实施。我们的方法集中在 一个分层计算框架，将数据简化为最小模块化抽象称为MicroMARMARKERS 在边缘设备上计算（AIM 1）。模块化微标志物抽象用于压缩特定于任务的特定 与边缘设备上的生物标志物计算相关的信息，同时剥离滋扰变量，例如 硬件偏见/漂移和背景级别与推理无关。我们的分层计算框架 可以扩展以在边缘设备上实现高数据速率传感器阵列以在新的护理点和 门诊环境。这是通过集成压缩感应前处理器来实现的 在资源约束设置中获取信号（AIM 2）。最后，TR＆D3将创建计算 机制和一般的生物标志物隐私框架，以使参与者控制隐私效果 在研究设计，数据收集和共享的MHealth数据共享第三方研究期间的权衡取舍 当数据交叉信任域（AIM 3）时。 这些技术将与协作项目合作开发，并将被传播到 服务项目以确保TR＆D3技术可以解决健康研究面临的实际问题 社区并确保MDOT外部调查人员的这些技术可用性 调查团队。 TR＆D3将与其他TR＆D项目，培训和 传播核心和管理核心，以最大化TR＆D3技术的社会影响。 1