FW-HTF-R: Biometrics and AI to Support Expert Nurse Decision-Making

医护人员通常会快速做出挽救生命的决定。决策失误可能会威胁到患者和工人的福利。高性能，专家护士利用决策策略，如优先考虑重要信息，保持大局观的情况下，并执行有效的临床技能，以提供安全的病人护理。新的或没有经验的护士往往缺乏经验，以支持专家的决策。该项目正在开发传感技术和算法，可用于培训护理学生的实时决策支持。这项技术可以提高这些学生的技能和实时决策能力，特别是在分散注意力和危险的情况下。该项目还为高中生和跨学科的大学课程创建了教学模块，这些课程整合了计算机科学、人因工程和护理等领域。该项目的愿景是增加护理人员的技术，将支持护士在真实的时间决策，而护士积极照顾病人，与其他照顾者的工作，并履行其不同的责任。为了实现这一目标，该项目正在开发实时生物识别技术，可以评估工作人员在复杂、动态的医疗保健工作中的认知状态。该项目还将研究专家护士的行为，学习有效的决策模式，可用于指导新手护士。专家行为的模仿（计算机）学习将用于培训导游。未来，通过将用户感知和决策支持行为与专为医疗工作场所设计的即时可穿戴设备相结合，开发的系统还可以支持快速识别患者风险。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Healthcare workers routinely make fast life-saving decisions. Failures in decision-making can threaten the welfare of the patient and the worker. High-performing, expert nurses utilize decision-making strategies such as prioritizing important information, maintaining a big-picture view of the situation, and executing effective clinical skills to provide safe patient care. New or inexperienced nurses often lack the experiences to support expert decision-making. This project is developing sensing technology and algorithms that can be used in real-time decision-support for training nursing students. The technology could improve the skills and real-time decision making of these students, especially in distracting and risky situations. The project is also creating teaching modules for high school students and inter-disciplinary university courses that integrate fields such as computer science, human factors engineering, and nursing. The project vision is to augment the nursing workforce with technology that will support nurse decision-making in real time while nurses actively care for patients, work with other caregivers, and carry out their diverse responsibilities. To achieve this goal, the project is developing real-time biometrics that can assess the cognitive state of workers during their complex, dynamic healthcare work. The project will also study expert nurse behaviors to learn efficient decision-making patterns that could be used to guide novice nurses. Imitation (computer) learning of expert behavior will be used to train the guides. In the future, the developed system could also support rapid recognition of patient risk by integrating user sensing and decision-support behaviors with just-in-time wearables designed for healthcare workplaces.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.