IEEE J Biomed Health Inform. 2019 Mar;23(2):838-847. doi: 10.1109/JBHI.2018.2834317. Epub 2018 May 7.
The aging of the world population is accompanied by a substantial increase in neurodegenerative disorders, such as dementia. Early detection of mild cognitive impairment (MCI), a clinical diagnostic that comes with an increased chance to develop dementias, could be an essential condition for promoting quality of life and independent living, as it would provide a critical window for the implementation of early pharmacological and nonpharmacological interventions. This systematic review aims to investigate the current state of knowledge on the effectiveness of smart home sensors technologies for the early detection of MCI through the monitoring of everyday life activities. This approach offers many advantages, including the continuous measurement of functional abilities in ecological environments. A systematic search of publications in MEDLINE, EMBASE, and CINAHL, before November 2017, was conducted. Seventeen studies were included in this review. Thirteen studies were based on real-life monitoring, with several sensors installed in participants' actual homes, and four studies included scenario-based assessments, in which participants had to complete various tasks in a research lab apartment. In real-life monitoring, the most used indicators of MCI were walking speed and activity/motion in the house. In scenario-based assessment, time of completion, quality of activity completion, number of errors, amount of assistance needed, and task-irrelevant behaviors during the performance of everyday activities predicted MCI in participants. Despite technological limitations and the novelty of the field, smart home technologies represent a promising potential for the early screening of MCI and could support clinicians in geriatric care.
世界人口老龄化伴随着神经退行性疾病（如痴呆症）的大幅增加。轻度认知障碍（MCI）的早期检测，作为一种伴有更高痴呆风险的临床诊断，可以成为提高生活质量和独立生活能力的重要条件，因为它为实施早期药物和非药物干预提供了一个关键窗口。本系统评价旨在研究通过监测日常生活活动来使用智能家居传感器技术早期检测 MCI 的现有知识状态。这种方法具有许多优势，包括在生态环境中持续测量功能能力。在 2017 年 11 月之前，对 MEDLINE、EMBASE 和 CINAHL 中的出版物进行了系统检索。本综述纳入了 17 项研究。13 项研究基于实际生活监测，在参与者的实际家中安装了多个传感器，4 项研究包括基于场景的评估，其中参与者必须在研究实验室公寓中完成各种任务。在实际生活监测中，MCI 最常用的指标是步行速度和房屋内的活动/动作。在基于场景的评估中，完成时间、活动完成质量、错误数量、所需帮助量以及参与者在执行日常活动时的与任务无关的行为，预测了 MCI。尽管存在技术限制和该领域的新颖性，但智能家居技术代表了 MCI 早期筛查的有希望的潜力，并可以为老年护理临床医生提供支持。
