BD Spokes: SPOKE: SOUTH: Large-Scale Medical Informatics for Patient Care Coordination and Engagement

BD Spokes：SPOKE：SOUTH：用于患者护理协调和参与的大规模医疗信息学

• 批准号: 1636933
• 负责人: Gari Clifford
• 金额: $ 100万
• 依托单位: Emory University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2016
• 资助国家: 美国
• 起止时间: 2016-09-01 至 2021-02-28
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1636933&HistoricalAwards=false
• 关键词: BD; Spokes; SPOKE; SOUTH; Large

This project brings together six universities to design and construct a patient-focused and personalized health system that addresses the fractured nature of healthcare information, and the lack of engagement of individuals in their own healthcare. By taking advantage of the enormous amount of information being created about our environment, through the confluence of real-time, mobile and wearable devices and the availability of rich social media data on patient behavior, the team will create a detailed and comprehensive picture of a patient's health, and a tool to help manage patients' engagement with their health care providers. The system has four key aims to: (1) provide a human-centered approach for integrating electronic health record data generated by traditional methods with data collected "in the wild" (such as personal fitness devices, mobile phone usage, local weather, pollution or even fast food restaurant maps, etc.); (2) develop a framework for deciding which data sources are trustworthy; (3) create a cloud-based system to allow users to view and track their own data over time and improve healthcare outcomes; and (4) provide educational outreach and community participation, particularly in minority populations, to design a system which benefits users in both the short term (through employment and education) and the long term (through increased engagement and trust).This project will leverage modern distributed cloud-based computing infrastructure (including mobile phones and Amazon Web Services), and the unique capacities of the South BD Hub to house and analyze the enormous volumes of health-related data that are generated every day by people, and their environment. By linking electronic medical records, external databases and data 'in the wild' harvested from patient's Internet-enabled devices, the project will address several issues related to the integration of high-resolution data for longitudinal tracking of patients. These include acceptability of the technology, particularly by vulnerable groups, usability, veracity of data collected, and scalability/integration across a large heterogeneous landscape. By employing patient-centric agile development, the team will work with communities to implement a cloud-based architecture to improve tracking of study participants, increase the ease with which data can be captured, improve patient engagement, and facilitate care coordination. The resultant platform will integrate big data analytics, real time scalable data collection, and social media analytics on patient behavior to analyze cardiovascular disease outcomes among disadvantaged African American and Hispanic patient populations. Additionally, the team will implement data fusion techniques to ensure the veracity of the varying qualities of data collected, and develop machine learning models to identify at-risk patient populations in order to reduce health disparities. Finally, patient engagement and health outcomes will be measured to assess the validity and success of the system.

该项目汇集了六所大学，设计并构建了一个以患者为中心的个性化医疗系统，以解决医疗信息的断裂性，以及个人在自己的医疗保健中缺乏参与的问题。通过实时、移动和可穿戴设备的融合，以及丰富的关于患者行为的社交媒体数据的可用性，该团队将利用有关我们环境的大量信息，创建一个详细而全面的患者健康图景，并创建一个工具来帮助管理患者与医疗保健提供者的互动。该系统有四个主要目标：(1)提供一种以人为本的方法，将传统方法产生的电子健康记录数据与“野外”收集的数据（如个人健身设备、手机使用情况、当地天气、污染甚至快餐店地图等）整合起来；(2)制定一个框架，以确定哪些数据源是值得信赖的；(3)创建基于云的系统，使用户可以长期查看和跟踪自己的数据，并改善医疗保健结果；(4)提供教育外展和社区参与，特别是在少数民族人口中，以设计一个在短期（通过就业和教育）和长期（通过增加参与和信任）有利于用户的系统。该项目将利用现代分布式云计算基础设施（包括移动电话和亚马逊网络服务），以及南BD中心的独特能力来存储和分析人们及其环境每天产生的大量与健康相关的数据。通过将电子医疗记录、外部数据库和从患者联网设备中获取的“野外”数据连接起来，该项目将解决与整合高分辨率数据以纵向跟踪患者相关的几个问题。这些包括技术的可接受性，特别是易受攻击的群体，可用性，收集数据的准确性，以及跨大型异构环境的可伸缩性/集成。通过采用以患者为中心的敏捷开发，该团队将与社区合作实施基于云的架构，以改进对研究参与者的跟踪，增加数据捕获的便利性，提高患者参与度，并促进护理协调。由此产生的平台将整合大数据分析、实时可扩展数据收集和患者行为的社交媒体分析，以分析弱势非洲裔美国人和西班牙裔患者群体的心血管疾病结局。此外，该团队将实施数据融合技术，以确保所收集数据的不同质量的准确性，并开发机器学习模型，以识别高危患者群体，以减少健康差距。最后，将测量患者参与和健康结果，以评估该系统的有效性和成功。

项目成果

Preventing Cardiovascular Disease Among Urban African Americans With a Mobile Health App (the MOYO App): Protocol for a Usability Study

使用移动健康应用程序（MOYO 应用程序）预防城市非裔美国人的心血管疾病：可用性研究协议

• DOI: 10.2196/16699
• 发表时间: 2020
• 期刊: JMIR Research Protocols
• 影响因子: 1.7
• 作者: Taylor Jr, Herman A;Francis, Sherilyn;Evans, Chad Ray;Harvey, Marques;Newton, Brittney A;Jones, Camara P;Akintobi, Tabia Henry;Clifford, Gari
• 通讯作者: Clifford, Gari

A low-complexity photoplethysmographic systolic peak detector for compressed sensed data

• DOI: 10.1088/1361-6579/ab254b
• 发表时间: 2019-06-01
• 期刊: PHYSIOLOGICAL MEASUREMENT
• 影响因子: 3.2
• 作者: Da Poian, Giulia;Letizia, Nunzio A.;Clifford, Gari D.
• 通讯作者: Clifford, Gari D.

Health Literacy, Health Numeracy, and Trust in Doctor: Effects on Key Patient Health Outcomes

• DOI: 10.1111/joca.12267
• 发表时间: 2019-07-17
• 期刊: JOURNAL OF CONSUMER AFFAIRS
• 影响因子: 2.8
• 作者: Netemeyer, Richard G.;Dobolyi, David G.;Taylor, Herman
• 通讯作者: Taylor, Herman

DeepAISE on FHIR — An Interoperable Real-Time Predictive Analytic Platform for Early Prediction of Sepsis

FHIR 上的 DeepAISE — 用于脓毒症早期预测的可互操作实时预测分析平台

• 发表时间: 2018
• 期刊: AMIA Annual Symposium proceedings
• 作者: Lakshman, Vidyashankar;Amrollahi, Fatemeh;Koppisetty, Veera Supraja;Shashikumar, Supreeth P.;Sharma, Ashish;Nemati, Shamim
• 通讯作者: Nemati, Shamim

Centroid of Age Neighborhoods: A New Approach to Estimate Biological Age

年龄邻域质心：估计生物年龄的新方法

• DOI: 10.1109/jbhi.2019.2930938
• 发表时间: 2020
• 期刊: IEEE Journal of Biomedical and Health Informatics
• 影响因子: 7.7
• 作者: Rahman, Syed Ashiqur;Adjeroh, Donald A.
• 通讯作者: Adjeroh, Donald A.