SBIR Phase II: Quantification of Operative Performance via Simulated Surgery, Capacitive Sensing, and Machine Learning to Improve Surgeon Performance & Medical Device Develop

SBIR 第二阶段：通过模拟手术、电容传感和机器学习量化手术表现，以提高外科医生的表现

• 批准号: 2223976
• 负责人: Hannah Eherenfeldt
• 金额: $ 99.64万
• 依托单位: Resuture Inc.
• 依托单位国家: 美国
• 项目类别: Cooperative Agreement
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-03-01 至 2025-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2223976&HistoricalAwards=false
• 关键词: SBIR; Phase; II; Quantification; Operative

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project is to improve surgical skill acquisition, assessment of surgical performance, and medical device training. The apprenticeship-based model of surgical training has created inefficiencies in the medical device and healthcare industries. This problem is exacerbated by the evolving complexity and specialization of surgical procedures and devices. The proposed technology combines lifelike, physical simulated procedures, novel sensing technologies, and machine-learned data analytics to address a universal market need for data-driven training. The technology developed during this project will result in surgical simulation platforms to improve procedural competency and the ability to practice device deployment outside of the operating room, while providing critical data-driven insight into surgical performance and quantitative evaluation. Ultimately, this solution could reduce patient costs, improve outcomes, and expedite medical device development and adoption. The proposed project will result in the development of a comprehensive system that collects data and evaluates vascular surgical operative performance in both the open and endovascular fields. An open vascular surgery simulation platform previously developed to train surgeons will be expanded to include endovascular procedures and the integration of capacitive sensors to capture a comprehensive set of operative performance data. This project aims to use artificial intelligence to classify key performance metrics from the collected dataset to build a comprehensive model to classify operative performance. A data-driven platform for surgical training and medical device development is not currently commercially available and the industry currently relies on increasingly cost-prohibitive means to provide vital surgical training.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.

该小型企业创新研究（SBIR）II期项目的更广泛影响/商业潜力是改善手术技能获取、手术性能评估和医疗器械培训。基于学徒制的外科培训模式在医疗器械和医疗保健行业造成了效率低下。该问题由于外科手术和装置的不断发展的复杂性和专业化而加剧。该技术结合了逼真的物理模拟程序，新颖的传感技术和机器学习数据分析，以满足数据驱动培训的普遍市场需求。该项目期间开发的技术将产生手术模拟平台，以提高手术能力和在手术室外实践器械部署的能力，同时提供对手术性能和定量评价的关键数据驱动的见解。最终，该解决方案可以降低患者成本，改善结果，并加快医疗设备的开发和采用。拟议项目将开发一个综合系统，收集数据并评价开放和血管内领域的血管外科手术性能。之前为培训外科医生而开发的开放血管手术模拟平台将扩展到包括血管内手术和电容传感器的集成，以捕获一组全面的手术性能数据。该项目旨在使用人工智能对收集的数据集中的关键绩效指标进行分类，以建立一个综合模型来对运营绩效进行分类。一个数据驱动的手术培训和医疗器械开发平台目前还没有商业化，行业目前依赖于越来越多的成本高昂的手段来提供重要的手术培训。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。