Examining machin learning in a digital pyhsical activity intervention to predict and prevent falls in older adults: a mixed methods feasibility study

在数字身体活动干预中检查机器学习以预测和预防老年人跌倒：混合方法可行性研究

• 批准号: 2899352
• 金额: --
• 依托单位: University of Manchester
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2023
• 资助国家: 英国
• 起止时间: 2023 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2899352
• 关键词: Examining; machin; learning; digital; pyhsical

Falls often lead to minor and major injuries and are a risk to morbidity and mortality across all age groups. Factors associated with ageing increase the risk of falls, with at least one third of community-dwelling older people falling and injuring themselves each year (Campbell et al., 1990). This can cause long-term physical and mental health issues. In addition, NHS England has over 250,000 falls related hospital admissions per year, costing an estimated £2 billion annually (Public Health England, 2017). A recent Cochrane review found exercise as a single intervention prevents falls, reducing rates between 23% and 34% (Sherrington et al., 2020). Accessibility and adherence to in-person exercise programmes among older adults can be low and was severely impacted by the COVID-19 pandemic. Hence, digital physical activity interventions are being designed and tested to improve how often and how well older people exercise at home, to improve physical and mental health and prevent falls. A recent scientific review found that artificial intelligence (AI) techniques may improve the prediction of falls among older adults in hospital or simulated settings, but community-based datasets were lacking (O'Connor et al., 2022). These could offer more accurate and up-to-date predictions of older adults at risk of falling and sustaining injuries at home or in a care home. The ACTIVATE project will utilise a novel digital physical activity application called KOKU (https://kokuhealth.com/), provided by a commercial software partner, to measure falls risk and help prevent falls among older adults in the community (Stanmore, 2021). A mixed methods feasibility study will recruit older people to use the KOKU app to collect exercise and falls related data which will be analysed via machine learning techniques. These algorithms will be utilised to create a prediction model of falls risk in older adults in the community. This will inform the co-design of an AI-based digital dashboard with older people to educate them about their falls risk and provide them with evidence-based strategies via the KOKU app to prevent falls. Older people will be at the centre of ACTIVATE, via a patient and public involvement panel, to enhance the conduct, reporting, and impact of the research. Overall, it will improve the prediction of falls risk and the provision of preventative fall strategies by leveraging the KOKU app, AI analytics, and participatory design to help reduce the occurrence of falls among older adults in the community.

跌倒往往导致轻伤和重伤，并对所有年龄段的发病率和死亡率构成风险。与老龄化相关的因素增加了跌倒的风险，每年至少有三分之一居住在社区的老年人摔倒并受伤(Campbell等人，1990年)。这会导致长期的身心健康问题。此外，英国国民健康保险制度每年有超过25万人因跌倒而住院，估计每年花费20亿英镑(公共卫生英格兰，2017)。Cochrane最近的一项研究发现，运动作为一种单一的干预措施可以预防跌倒，使跌倒的发病率降低23%到34%(Sherrington等人，2020年)。老年人对亲自锻炼计划的可及性和坚持性可能较低，并受到新冠肺炎大流行的严重影响。因此，正在设计和测试数字身体活动干预措施，以改善老年人在家中锻炼的频率和效果，以改善身心健康和预防跌倒。最近的一项科学综述发现，人工智能(AI)技术可能会改善医院或模拟环境中老年人跌倒的预测，但缺乏基于社区的数据集(O‘Connor等人，2022年)。这些可以为老年人在家中或疗养院摔倒和受伤的风险提供更准确和最新的预测。Activate项目将利用一种名为KOKU(由商业软件合作伙伴提供的https://kokuhealth.com/)，)的新型数字体力活动应用程序来测量跌倒风险，并帮助预防社区老年人跌倒(Stanmore，2021年)。一项混合方法可行性研究将招募老年人使用Koku应用程序收集与运动和跌倒相关的数据，这些数据将通过机器学习技术进行分析。这些算法将被用来创建社区老年人跌倒风险的预测模型。这将为与老年人共同设计基于人工智能的数字仪表盘提供信息，以教育他们关于跌倒的风险，并通过Koku应用程序为他们提供预防跌倒的循证策略。老年人将通过患者和公众参与小组处于Activate的中心，以加强研究的进行、报告和影响。总体而言，它将通过利用Koku应用程序、人工智能分析和参与式设计来帮助减少社区老年人的跌倒发生率，从而改进跌倒风险的预测和预防性跌倒策略的提供。