SBIR Phase I: Lower Extremity Injury Prediction Neuromuscular Algorithm

这个小型企业创新研究(SBIR)第一阶段项目的更广泛的影响/商业潜力是为经历较低远端非接触性损伤的专业和大学运动员提供基于科学的、特定于肌肉的、移动优先的减少伤害方案。这一应用将克服目前可用的固定技术的障碍，使关键的洞察力能够在受伤事件发生之前缓解运动员的痛苦。职业和大学体育运动中60%的伤害与下肢有关，专业组织每年花费1000万美元的恢复和工资沉没成本，从而导致12亿美元的伤害市场。我们将制定解决方案，以实现预防护理的三重目标：1)提高损伤诊断的准确性；2)提高治疗建议的准确性；3)根据环境预测特定的肌肉和关节损伤。该应用程序是一个及时的商业机会，从重复的软件订阅模式开始，该模式将以较低的非接触性下端损伤发生率提供更好的服务。该小型企业创新研究(SBIR)第一阶段项目将神经肌肉活动和计算机视觉的核心模块转化为全面的、以运动员为中心的移动友好解决方案，以减少脚踝扭伤和前交叉韧带撕裂。我们假设，将计算机视觉与神经肌肉活动分析相结合，将产生一个机器学习人类运动指数，该指数具有模拟神经肌肉工作和肌肉疲劳的近似时间的能力。我们已经证明，神经肌肉活动数据的使用说明了下肢内主要稳定器损伤的直接病理基础。我们对300多名运动员进行了测试，收集了3600万个神经肌肉数据样本，发现了与损伤相关的危险因素。通过利用张量流等技术，神经肌肉活动肌肉活动产生了一个丰富的数据集，通过手机上的摄像头识别肌肉和关节效率低下。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势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 1 project is provision of a scientifically-based, muscle-specific, mobile first, injury reduction protocol for professional and collegiate athletes who experience lower distal non-contact injuries. This application will overcome barriers to currently available stationary technologies by enabling key insights to relieve athletes before the incident of injury occurs. 60% of injuries for professional and collegiate sports are related to the lower extremities, costing professional organizations $10 M annually in recovery and salary sunk cost and consequently a $1.2 B injury market. We will develop a solution to the prevention care triple aim of 1) Improving the accuracy of diagnosing injuries; 2) Improving treatment recommendations accuracy; 3) Forecasting specific muscle and joint injuries based on the environment. The application is a timely business opportunity starting with a recurring software subscription model that will provide better service, at a lower occurrence of non-contact lower distal injuries. This Small Business Innovation Research (SBIR) Phase 1 Project will translate the core modules of neuromuscular activity and computer vision into a comprehensive, athlete-centered, mobile friendly solution to reduce ankle sprains and ACL tears. We hypothesize that the use of computer vision in combination with the analysis of neuromuscular activity will result in a machine learning human movement index with the ability to model neuromuscular work and approximate time of muscle fatigue. We have demonstrated that the use of the neuromuscular activity data illuminates a direct line of pathology of injury for the main stabilizers within the lower extremity. Testing over 300 athletes and collecting 36 million neuromuscular data samples, we have discovered risk factors that correlate with injuries. By utilizing technologies such as tensor flow, neuromuscular activity muscle activity produces a rich data set identifying muscle and joint inefficiencies via camera on the mobile phone.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.