PDF(Pubmed)
Abstract：
BACKGROUND: Markerless motion capture (MMC) uses video cameras or depth sensors for full body tracking and presents a promising approach for objectively and unobtrusively monitoring functional performance within community settings, to aid clinical decision-making in neurodegenerative diseases such as dementia.
OBJECTIVE: The primary objective of this systematic review was to investigate the application of MMC using full-body tracking, to quantify functional performance in people with dementia, mild cognitive impairment, and Parkinson disease.
METHODS: A systematic search of the Embase, MEDLINE, CINAHL, and Scopus databases was conducted between November 2022 and February 2023, which yielded a total of 1595 results. The inclusion criteria were MMC and full-body tracking. A total of 157 studies were included for full-text screening, out of which 26 eligible studies that met the selection criteria were included in the review. .
RESULTS: Primarily, the selected studies focused on gait analysis (n=24), while other functional tasks, such as sit to stand (n=5) and stepping in place (n=1), were also explored. However, activities of daily living were not evaluated in any of the included studies. MMC models varied across the studies, encompassing depth cameras (n=18) versus standard video cameras (n=5) or mobile phone cameras (n=2) with postprocessing using deep learning models. However, only 6 studies conducted rigorous comparisons with established gold-standard motion capture models.
CONCLUSIONS: Despite its potential as an effective tool for analyzing movement and posture in individuals with dementia, mild cognitive impairment, and Parkinson disease, further research is required to establish the clinical usefulness of MMC in quantifying mobility and functional performance in the real world.
OBJECTIVE: The primary objective of this systematic review was to investigate the application of MMC using full-body tracking, to quantify functional performance in people with dementia, mild cognitive impairment, and Parkinson disease.
METHODS: A systematic search of the Embase, MEDLINE, CINAHL, and Scopus databases was conducted between November 2022 and February 2023, which yielded a total of 1595 results. The inclusion criteria were MMC and full-body tracking. A total of 157 studies were included for full-text screening, out of which 26 eligible studies that met the selection criteria were included in the review. .
RESULTS: Primarily, the selected studies focused on gait analysis (n=24), while other functional tasks, such as sit to stand (n=5) and stepping in place (n=1), were also explored. However, activities of daily living were not evaluated in any of the included studies. MMC models varied across the studies, encompassing depth cameras (n=18) versus standard video cameras (n=5) or mobile phone cameras (n=2) with postprocessing using deep learning models. However, only 6 studies conducted rigorous comparisons with established gold-standard motion capture models.
CONCLUSIONS: Despite its potential as an effective tool for analyzing movement and posture in individuals with dementia, mild cognitive impairment, and Parkinson disease, further research is required to establish the clinical usefulness of MMC in quantifying mobility and functional performance in the real world.
摘要：
背景：无标记运动捕捉（MMC）使用摄像机或深度传感器进行全身跟踪，并提出了一种有希望的方法，可以客观地监控社区环境中的功能表现，帮助临床决策神经退行性疾病，如痴呆。
目的：本系统综述的主要目的是通过全身追踪研究MMC的应用，量化痴呆症患者的功能表现，轻度认知障碍，帕金森病。
方法：对Embase的系统搜索，MEDLINE,CINAHL,和Scopus数据库在2022年11月至2023年2月之间进行，共产生1595个结果。纳入标准为MMC和全身追踪。共纳入157项研究进行全文筛选，其中符合筛选标准的26项符合条件的研究纳入审查..
结果：主要是，选定的研究集中在步态分析(n=24)，而其他功能任务，例如坐下来站立（n=5）和踩踏（n=1），也被探索过。然而,纳入的任何研究均未评估日常生活活动.MMC模型在研究中各不相同，包括深度相机（n=18）与标准摄像机（n=5）或移动电话相机（n=2），并使用深度学习模型进行后处理。然而,只有6项研究与已建立的黄金标准动作捕捉模型进行了严格的比较.
结论：尽管它有潜力成为分析痴呆症患者运动和姿势的有效工具，轻度认知障碍，和帕金森病，需要进一步的研究来确定MMC在量化真实世界中的移动性和功能表现方面的临床应用价值.
目的：本系统综述的主要目的是通过全身追踪研究MMC的应用，量化痴呆症患者的功能表现，轻度认知障碍，帕金森病。
方法：对Embase的系统搜索，MEDLINE,CINAHL,和Scopus数据库在2022年11月至2023年2月之间进行，共产生1595个结果。纳入标准为MMC和全身追踪。共纳入157项研究进行全文筛选，其中符合筛选标准的26项符合条件的研究纳入审查..
结果：主要是，选定的研究集中在步态分析(n=24)，而其他功能任务，例如坐下来站立（n=5）和踩踏（n=1），也被探索过。然而,纳入的任何研究均未评估日常生活活动.MMC模型在研究中各不相同，包括深度相机（n=18）与标准摄像机（n=5）或移动电话相机（n=2），并使用深度学习模型进行后处理。然而,只有6项研究与已建立的黄金标准动作捕捉模型进行了严格的比较.
结论：尽管它有潜力成为分析痴呆症患者运动和姿势的有效工具，轻度认知障碍，和帕金森病，需要进一步的研究来确定MMC在量化真实世界中的移动性和功能表现方面的临床应用价值.
