SBIR Phase II: A machine learning-driven telerehabilitation solution designed to promote the personalized recovery of hand and arm functions post stroke

这项小企业创新研究（SBIR）第二阶段项目的更广泛影响/商业潜力是，通过一种用于远程康复的医疗设备，有可能改善因中风而手臂和手部受损的个人的生活质量。在美国，每年约有80万人中风，其中约65%的人患有长期上肢损伤。由于许多障碍，如成本，运输和时间，许多人没有得到足够的治疗恢复。远程康复方法可能会减少这些障碍，允许治疗师和他们的病人进行有意义的远程会话。对于治疗师来说，这可能会通过自动化审查患者进展、调整康复治疗和服务计费的流程来改善财务结果。该项目将推进个性化远程康复系统的开发，特别是针对中风患者的手部和手臂运动恢复。为手指、手和手臂的康复设计的新运动游戏将被开发并添加到当前的游戏库中。机器学习将被添加到系统中，以创建一个通用的、引人入胜的、可定制的解决方案。这种新颖的康复方法将个性化治疗，通过预测分析解决个人用户的需求，可能会更有效。机器学习将推动推荐系统将康复计划与患者康复轨迹同步。这种同步将有助于治疗师提供个性化的治疗练习，并可能增加患者的康复结果。游戏和机器学习算法将与临床医生和中风患者一起进行评估。最后一步将是测试该系统在综合中风中心的可行性。这些个性化虚拟康复、远程临床医生监督和进度跟踪的能力可能提供一种经济有效的方法来改善患者的预后。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 II project is to potentially improve the quality of life for individuals suffering arm and hand impairments from stroke, through a medical device for telerehabilitation. Each year, ~800,000 people have a stroke in the United States, and about 65% of them suffer long-term upper extremity impairments. Due to many barriers such as cost, transportation, and time, many individuals do not obtain enough therapy for recovery. The telerehabilitation approach may reduce some of these barriers, allowing therapists and their patients to have meaningful remote sessions. For therapists, this may improve fiscal outcomes by automating the flow of reviewing patient progress, adjusting their rehabilitation treatments, and billing for services. This project will advance the development of a personalized telerehabilitation system, specifically for hand and arm motor recovery, for individuals suffering from a stroke. New exergames designed for rehabilitation of the fingers, hand, and arm will be developed and added to the current library of games. Machine learning will be added to the system to create a versatile, engaging, and customizable solution. This novel approach to rehabilitation will personalize treatments that may be more effective by addressing individual user needs with predictive analytics. Machine learning will drive the recommendation system to synchronize the rehabilitation plan with the patient recovery trajectory. This synchronization will help the therapist provide personalized therapeutic exercises and possibly increase their patients’ recovery outcomes. The games and machine learning algorithms will be evaluated with clinicians and individuals with stroke. The final step will be to test the feasibility of the system in a comprehensive stroke center. These capabilities of personalized virtual rehabilitation, remote clinician supervision, and progress tracking may offer a cost-effective way to improve patient outcomes.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.