PROTECT: Predictive approaches in managing long-term conditions: from remote monitoring data to digital biomarkers

在英国，长期疾病的护理费用高达卫生和社会保健总支出的70%，占全科医生预约的50%。制定数据驱动的预防和预测措施将提高护理服务的质量，并降低管理长期疾病的成本。物联网和可穿戴设备等新兴技术为收集运动、日常活动、生命体征和睡眠等连续的家庭监控数据提供了新的机会。这些数据为监测病情进展、进行风险评估和预测不良医疗事件提供了新的可能性。这项研究将开发新的信息工程和机器学习方法，以整合和分析连续的家庭监测数据，并为个性化和预防性护理创造新的数字生物标志物。它将在家庭监测技术和机器学习应用于医疗保健，特别是长期疾病管理方面取得科学进展。它将开发临床应用和护理知情的解决方案，利用远程监控数据提取健康洞察，提供预测分析和医疗保健风险评估。这项研究将有助于实现呼吁中概述的目标，即通过生产适用于一系列长期健康状况的负担得起的解决方案，改变家庭护理和健康状况，实现独立。该研究计划将创建一个数字平台，安全地整合来自家庭观察和测量技术的环境和生理信息。它将应用机器学习模型和解决方案来获得可用于改善医疗保健的数字生物标志物。总体目标是利用该系统从复杂的数据集中提取相关信息，以便进行有效和及时的卫生干预。为了实现这一目标，该团队将构建软件基础设施，使传感器信息能够以安全和隐私意识的方式收集，并通过开发以人为本和临床知情的预测方法，为数字生物标志物的分析创建基本构建块。

The cost of care for long-term conditions is up to 70% of total health and social care expenditure and account for 50% of GP appointments in the UK. Developing data-driven preventative and predictive measures will enhance the quality of care services and reduce the cost of managing long-term conditions. Emerging technologies such as the Internet of Things and wearable devices provide new opportunities to collect continuous in-home monitoring data such as movement, daily activity, vital signs and sleep. This data provides new possibilities to monitor the progression of conditions, do risk assessments and predict adverse healthcare events. This research will develop new information engineering and machine learning methods to integrate and analyse continuous in-home monitoring data and create new digital biomarkers for personalised and preventative care. It will create scientific advances in in-home monitoring technologies and machine learning applied to healthcare and, in particular, managing long-term conditions. It will develop clinically applicable and care informed solutions to utilise remote monitoring data to extract health insights and provide predictive analysis and healthcare risk assessments. The research will contribute to the ambitions outlined in the call to transform care and health at home and enable independence by producing affordable solutions that be applied across a range of long-term health conditions.The research programme will create a digital platform to integrate environmental and physiological information from in-home observation and measurement technologies safely and securely. It will apply machine learning models and solutions to derive digital biomarkers that can be used to improve healthcare. The overarching aim is to use the system to extract relevant information from complex datasets to allows effective and timely health interventions. To achieve this, the team will build the software infrastructure that allows sensor information to be collected in a safe and secure, and privacy-aware way and create the fundamental building blocks for the analysis of digital biomarkers through the development of person-centred and clinically informed predictive approaches.