RAPID: Remote Monitoring of Ebola Patients and Their Treating Physicians

提案#：15-14626PI(S)：Papanikolopoulos，Nikolaos；Lim，Kelvin O.机构：明尼苏达大学双子城分校(UMN)标题：快速：远程监测埃博拉患者及其治疗医生项目建议：该项目融合了成熟的技术，旨在帮助那些在持续的埃博拉疫情中从事直接患者护理的人面临的紧迫挑战。也就是说，使用交互式机器视觉技术和智能编码的防护装备来主动帮助医疗保健提供者(例如，遵守他们所要求的NIH/CDC(疾病控制中心)安全程序-正确穿戴灭菌的防护覆盖物所需的明确运动序列，以及之后安全、循序渐进和受控地移除和随后处置这些现在可能致命的物品)。最近，两名达拉斯地区护士的感染被认为违反了协议，然后疾控中心S的回应突显了这一非常高标准的关键重要性，疾控中心随后实施了增强的伙伴制度，以更好地确保未来的合规。尽管如此，随着时间压力的增加，人工监控有时会失效，特别是当程序变得例行公事的时候。幸运的是，鉴于自动化人类活动和手势识别方面的进步，结合在创建自动化和交互伙伴中吸取的各自经验教训是容易实现的下一步，具有与手术等领域的远程操作辅助方法一起发展的严格程序以及现代图形和人机友好的人机界面的经验。显然，这种新知识服务于有用的目的。更广泛的影响：从长远来看，相对较低的成本应该得到注意。即使是任何环境的便携式扩展都可能成本高得不成比例，甚至是灾难性的，特别是当参与者未能遵守严格的标准时(通常是乏味和不受欢迎的)。在工业(如洁净室、核设施等)、医疗(如手术室)、军事和一些研究领域，记录和注册会议的成本迫使完全遵守所需的安全措施，可能很容易被更好的结果、更少的事故和更低的保险费率所抵消。该项目有助于建立一个大型NSF获奖者联盟，利用计算机科学的最新技术，共同解决具有国家和全球意义的公共卫生问题。UMN小组将协助紧急收集有关埃博拉感染地区使用的防护装备有效性的数据。这项研究将使新的量化危机图得以开发，以接近实时地估计当地传染性埃博拉病毒的传播率，从而加强最近开发的有限疫苗的有效分配，以减缓埃博拉病毒的传播。此外，它还将提供一种机制，通过与区域社交媒体观察的比较来验证和改进疾控中心的业务预测模型。它可能会让我们的第三世界国家进行疾病监测和早期发现。此外，该项目有望推广到其他传染性病毒情况；该研究使人们能够从未来的手持设备中利用社交媒体健康数据。尽管对装备的作用有足够的猜测，但几乎没有数据可以推动协议或装备本身的变化。除了目前的埃博拉问题，拟议的方法和联盟建设努力将支持广泛的公共卫生问题的解决方案。

Proposal #: 15-14626PI(s): Papanikolopoulos, Nikolaos; Lim, Kelvin O.Institution: University of Minnesota-Twin Cities (UMN)Title: RAPID: Remote Monitoring of Ebola Patients and Their Treating Physicians Project Proposed:This project, melding proven technologies, aims to assist in an immediate challenge now facing those engaged in direct patient care in the ongoing Ebola epidemic. Namely, employing interactive machine vision technologies and intelligently encoded protective gear to proactively assist health care providers (e.g., adhering to their required NIH/CDC (Center for Disease Control) Safety Procedures-the explicit movement sequences required for the proper donning of sterilized, protective coverings, and afterwards for the safe, step-wise and controlled removal and subsequent disposition of these now potentially lethal items). The crucial importance of this very high standard was underscored recently by the infection of two Dallas-area nurses where protocols were thought breached, and then by the CDC?s response, which next imposed an enhanced buddy system to better ensure future compliance. Notwithstanding, human monitors can sometimes lapse, especially when procedures become routine, as time pressures mount. Fortunately, incorporating respective lessons learned in the creation of an automated and interactive buddy is a readily achievable next step, given the advances in automated human activity and gesture recognition, with experience of the strict procedures evolved in conjunction with tele-operational assistance methods for domains such as surgery, and with modern graphical and human-friendly man-machine interfaces. Obviously, this new knowledge serves a useful purpose.Broader Impacts:The relatively low cost in the longer term should be noted. Even portable extensions to any environment can be disproportionally costly or even catastrophic, particularly when participants fail to adhere to strict standards (usually tedious and unwelcome). In industry (e.g., clean rooms, nuclear sites, etc.), in medicine (e.g., operating theaters), in the military, and in some research areas, the cost of recording and registering sessions that compel the full compliance to required safety measures might easily be offset by better outcomes, fewer accidents and reduced insurance rates. This project contributes in building a coalition of large NSF awardees to jointly address public health problems of national and global significance using the state of the art in Computer Science. The UMN team will assist in the urgent data collection regarding the effectiveness of the protective gear used in Ebola-infected regions.This research will enable the development of new quantitative crisis maps to approximate local regional rates of infectious Ebola virus spreading in near real time thereby enhancing the effective distribution of limited availability of recently developed vaccines to mitigate the spread of Ebola. Furthermore, it will provide a mechanism for validating and improving operational forecast models of the CDC by comparisons with regional social media observations. It may allow for disease surveillance and early detection among our third world countries. Moreover, this project is expected to be generalizable to other infectious virus conditions; the research enables exploiting social media health data from future hand held devices. Although enough speculation exists about the role of the gear, little data is available to push for changes in the protocols or the gear itself. Beyond the present issue of Ebola, the proposed methodology and the coalition building effort will support solutions in a wide range of public health issues.