SBIR Phase I: Utilization, Condition, and Location Tracking for Clinical Assets

这个小企业创新研究（SBIR）第一阶段项目的更广泛的影响/商业潜力将是通过降低维护临床设备的成本来提高美国医疗保健的质量。美国医院每年在医疗设备生命周期成本上花费930亿美元（仅次于人员成本）。存在严重的效率低下；一家典型的医院有25%的设备库存过剩，导致每年100万美元的不必要资本和运营费用。目前的监控系统使用无线标签来定位设备，但这并不能降低设备维护成本。该提案将开发一种带有传感器和软件的新标签，不仅可以监测设备位置，还可以监测设备的利用率和状况，以优化库存水平。该系统将根据使用情况和状况优化设备维修间隔，而不仅仅是运行时间，从而进一步节省成本。最重要的是，该系统将通过检测需要立即维修的故障来改善患者的治疗效果，例如掉落和机械部件故障。这个小企业创新研究（SBIR）第一阶段项目将推动技术的发展，使医院能够最佳地管理临床设备。该解决方案将小型电池供电的无线标签（带有传感器和机器学习算法）安装在监控设备上。该研究计划将解决以下三个主要技术挑战：适用性、可扩展性和就绪性：1)适用性：测量各种设备类型，分析收集的传感器数据，确定将传感器数据映射到环境的算法，并在真实场景下测试性能；2)可扩展性：开发程序和工具，为医院市场上数千种设备类型/制造/型号创建算法库；3)准备就绪：描述成本-尺寸-电池寿命交易空间，目标是10年的标签寿命，包括探索电池替代品，具有深度睡眠模式的传感器，以及以最大睡眠间隔维持设备环境的自适应算法。该奖项反映了美国国家科学基金会的法定使命，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。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project will be to improve the quality of healthcare in the United States by reducing the costs to maintain clinical equipment. US hospitals spend $93 billion yearly on medical equipment life cycle costs (second only to personnel). Large inefficiencies exist; a typical hospital has 25% over-inventory of equipment, resulting in $1 M annually in unnecessary capital and operational expense. Current monitoring systems use wireless tags to locate equipment but these do not reduce equipment maintenance costs. This proposal will develop a new tag with sensors and software to monitor not only equipment location but also utilization and condition to optimize inventory levels. This system will generate further savings by optimizing equipment service intervals based on usage and condition rather than simply elapsed time. Most importantly, this system will improve patient outcomes by detecting faults requiring immediate service, such as drops and failing mechanical components. This Small Business Innovation Research (SBIR) Phase I project will advance development of technology enabling hospitals to optimally manage clinical equipment. The solution mounts small battery-powered wireless tags (with sensors and machine learning algorithms) on equipment for monitoring. The research plan will address three main technical challenges: applicability, scalability and readiness as follows: 1) Applicability: Measure a wide variety of device types, analyze collected sensor data, identify algorithms mapping sensor data to context, and test performance under real-world scenarios; 2) Scalability: Develop procedures and tools to create an algorithm library for the thousands of device-type/make/models in the hospital market; and 3) Readiness: Characterize the cost-size-battery life trade space, with a goal of tag life of 10 years, including exploring battery alternatives,sensors with deep-sleep modes, and adaptive algorithms maintaining device context with maximum sleep intervals.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.