REMAP Open dataset

Parkinson's disease (PD) is a neurodegenerative disorder characterised by motor symptoms, such as gait dysfunction and postural instability. Technological tools to continuously monitor outcomes could capture the hour-by-hour symptom fluctuations of PD. Development of such tools is hampered by the lack of labelled datasets from home settings. To this end, we propose REMAP, a human rater-labelled dataset of REal-world Mobility Activities in Parkinson's disease including people with and without PD doing sit-to-stand transitions and turns in gait while living in a home setting. These discrete activities are captured from free-living (unobserved, unstructured) and during clinical assessments. The PD participants withheld their dopaminergic medications for a time (causing increased symptoms), so their events are labelled as being “on” or “off” medications. We include skeleton pose camera data. We present this open dataset, where the skeleton pose data is coarsened for anonymisation. We illustrate use-case code measuring sit-to-stand duration, tested on both coarsened and refined data. This is a sister dataset so our controlled dataset (available on application) where there is more refined skeleton pose data and accelerometry.

帕金森病（Parkinson's Disease, PD）是一种以运动症状为典型特征的神经退行性疾病，常见症状包括步态功能障碍与姿势不稳。可用于持续监测病情转归的技术工具，可捕捉帕金森病患者症状随时间的逐时波动情况。此类监测工具的开发，因缺乏居家场景下的标注数据集而受到阻碍。为此，我们提出了REMAP数据集：一款由人工标注者标记的帕金森病真实世界活动数据集，涵盖居家场景下帕金森病患者与健康对照者完成坐站转换与步态转身的活动数据。这些离散的活动数据采集自自由活动状态（即无观察者干预的非结构化场景）与临床评估过程中。参与研究的帕金森病患者曾暂时停用多巴胺能药物（会导致症状加重），因此其活动事件被标记为“服药状态”或“停药状态”。本数据集包含基于摄像头采集的骨骼姿态数据。本次发布的为开源数据集，其中骨骼姿态数据已通过粗化处理完成匿名化。我们提供了用于测量坐站转换时长的示例代码，并分别在粗化处理后与原始精细数据上对代码进行了测试。本数据集为姊妹数据集，我们另有受控数据集可供申请获取，该数据集包含更为精细的骨骼姿态数据与加速度计数据。

搜集汇总

背景与挑战

背景概述

REMAP Open dataset是一个帕金森病相关的人类活动标记数据集，包含家庭环境中PD患者和非PD患者进行坐立转换和转身步态活动的骨骼姿态数据，特别记录了PD患者在用药和停药状态下的活动表现。该数据集经过匿名化处理，并提供了测量活动持续时间的示例代码，旨在支持开发持续监测PD症状波动的技术工具。