SBIR Phase II: Development of a Safety System for Individuals with Alzheimer's Disease and Related Dementias

这个小企业创新研究（SBIR）第二阶段项目的更广泛影响/商业潜力是一个基于视频的安全系统，用于提高痴呆症护理的质量和降低成本。阿尔茨海默病（AD）在美国影响了540万人，其中65岁以上的9人中有1人，85岁以上的3人中有1人，占所有痴呆症患者的三分之二。它是美国最昂贵的疾病（直接成本为2360亿美元，间接成本为2210亿美元）。美国患阿尔茨海默病的人数每15年翻一番。阿尔茨海默病的药物失败率是最高的，目前为99.6%。跌倒事故占所有AD相关住院的26%，是一个主要问题和主要费用来源，平均每年跌倒4次，4次重复跌倒中有3次。不幸的是，为跌倒开发的安全产品是为有认知能力的成年人开发的，而不是专门为AD患者设计的。该系统将改变记忆护理机构的护理和操作质量，提高患者和家属的生活质量，并有助于医学界更好地了解痴呆症。拟议的项目通过检测安全关键事件来解决阿尔茨海默氏症护理中的这一关键空白，基于摄像机视频，事件可以由人工助手实时和事后审查。它有望实现推动科学和技术进步的两个主要目标：(1)通过学习足够丰富的数据集，展示我们的机器学习算法自动执行安全关键任务的能力。这些扩展了现有的跌倒检测方法，包括：(a)跌倒预测；(b)漫游检测；(c)褥疮检测；(2)使公司能够证明所提出的系统可以在100家记忆护理机构中以多达1000名患者的规模运行的完全可操作的HIL范式下运行。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 a video-based safety system for improving the quality and reducing the cost of dementia care. Alzheimer's Disease (AD) affects 5.4M in the US, including 1 in 9 over 65 and 1 in 3 over 85, and represents two thirds of all those affected by dementia. It is the single most expensive disease in the US ($236B direct; $221B indirect costs). The size of the US population with AD doubles every 15 years. The drug failure rate for AD is among the highest, currently 99.6. Fall accidents account for 26% of all AD related hospitalizations and are a major concern and key cost contributor, with an average fall rate of 4 falls per year and 3 in 4 repeated falls. Unfortunately, safety products developed for falls were developed for cognitively aware adults and not designed specifically for individuals with AD. The proposed system will change the quality of care and operations in memory care facilities, increase quality of life for patients and families, and help the medical profession gain a better understanding of dementia. The proposed project addresses this critical gap in Alzheimer's care by detecting safety critical events, based on camera video where events can be reviewed by a human assistant in real-time and after the fact. It is expected to achieve two main objectives that advance science and technology: (1) Demonstrating the ability for our machine learning algorithms to automatically perform safety critical tasks, by learning over a sufficiently rich set of data. These extend existing methods for fall detection to include (a) fall prediction; (b) wandering detection; (c) bed sores detections; (2) enabling the Company to demonstrate that the system proposed can run with a fully operational HIL paradigm running at scale with up to 1000 patients in 100 memory care facilities.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.