FW-HTF-P: Physiological Sensing to Enable Expert Decision-Making in Healthcare

医疗保健决策需要快速综合来自多个来源的信息，失败可能导致患者伤害。专家，高性能的护士可以快速掌握复杂的情况，并执行有效的病人护理所需的技能。然而，新护士往往缺乏经验和随之而来的专业知识，阻碍了他们立即采取适当行动的能力。目前，没有技术援助存在，以支持决策护理决策。该奖项将开发一个专家护士在门诊（门诊）护理反应的模型，并使用该模型来开发实时支持。随着人口老龄化和护理转移到家庭环境，决策支持技术可以对整个人群的健康产生影响。该技术还可以提高服务不足地区的护理质量并改善培训。 此外，这项工作还将通过将技术与决策联系起来的新模式推进本科课程，并通过介绍技术对健康影响的新项目模块改善K-12教育。本研究的目的是透过整合生理感知行为与认知功能与专家行为模式，以提升门诊护理人员的工作表现。首先，该项目将开发专家护士决策和行动的模型。在个人和系统层面的护理专业知识的基本过程将建模与混合方法的方法，包括人种学和眼动跟踪测量。其次，该项目将使用生理传感器（眼动跟踪和脑电图）来监测护士的能力和行为。传感器数据和使用它们的模型将用于确定指导干预的适当时间，这些干预将通过增强现实实时为护士提供决策支持。整个系统将在护理教育和模拟中心与护理学员一起在受控环境中进行评估。 该计划项目的目标是开发必要的基础设施和基础工作，以扩大在人类技术前沿研究提案的完整未来工作水平上研究未来技术、工人和工作的机会。该奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

Decision-making in healthcare requires rapid synthesis of information from multiple sources, and failure can lead to patient harm. Expert, high-performing nurses can quickly grasp complex situations and perform the skills required for effective patient care. New nurses, however, often lack experience and the expertise that comes with it, hindering their ability to take immediate proper action. Currently, no technological aids exist to support decision nursing decision-making. This award will develop a model of expert nurse responses in ambulatory (outpatient) care and use this model to develop real-time support. With an aging population and care moving to home environments, decision-support technology can have an impact on the health across populations. The technology can also elevate the quality of care in underserved regions and improve training. In addition, this work will advance undergraduate curriculum with new models linking technology with decision-making and improve K-12 education through new project modules that introduce the impact of technology on health. The goal of this project is to augment performance of ambulatory care nurses by integrating physiological sensing of behavior and cognitive function with models of expert behaviors. First, the project will develop models for expert nurse decision-making and actions. The fundamental processes of nursing expertise at the individual and system levels will be modeled with a mixed method approach that includes ethnography and eye-tracking measurements. Second, the project will use physiological sensors (eye tracking and EEG) to monitor nurse capability and behavior. The sensor data and models that use them will be used to identify appropriate times for coaching interventions that will provide decision support to nurses in real-time through augmented reality. The entire system will be evaluated in a controlled setting at the Center for Nursing Education and Simulation with nursing trainees. The goal of this planning project is to develop the necessary infrastructure, and foundational work to expand the opportunities for studying future technology, workers, and work at the level of a full Future of Work at the Human-Technology Frontier research proposal.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.