PDF(Pubmed)
Abstract：
BACKGROUND: Dyskinesias and freezing of gait are episodic disorders in Parkinson\'s disease, characterized by a fluctuating and unpredictable nature. This cross-sectional study aims to objectively monitor Parkinsonian patients experiencing dyskinesias and/or freezing of gait during activities of daily living and assess possible changes in spatiotemporal gait parameters.
METHODS: Seventy-one patients with Parkinson\'s disease (40 with dyskinesias and 33 with freezing of gait) were continuously monitored at home for a minimum of 5 days using a single wearable sensor. Dedicated machine-learning algorithms were used to categorize patients based on the occurrence of dyskinesias and freezing of gait. Additionally, specific spatiotemporal gait parameters were compared among patients with and without dyskinesias and/or freezing of gait.
RESULTS: The wearable sensor algorithms accurately classified patients with and without dyskinesias as well as those with and without freezing of gait based on the recorded dyskinesias and freezing of gait episodes. Standard spatiotemporal gait parameters did not differ significantly between patients with and without dyskinesias or freezing of gait. Both the time spent with dyskinesias and the number of freezing of gait episodes positively correlated with the disease severity and medication dosage.
CONCLUSIONS: A single inertial wearable sensor shows promise in monitoring complex, episodic movement patterns, such as dyskinesias and freezing of gait, during daily activities. This approach may help implement targeted therapeutic and preventive strategies for Parkinson\'s disease.
METHODS: Seventy-one patients with Parkinson\'s disease (40 with dyskinesias and 33 with freezing of gait) were continuously monitored at home for a minimum of 5 days using a single wearable sensor. Dedicated machine-learning algorithms were used to categorize patients based on the occurrence of dyskinesias and freezing of gait. Additionally, specific spatiotemporal gait parameters were compared among patients with and without dyskinesias and/or freezing of gait.
RESULTS: The wearable sensor algorithms accurately classified patients with and without dyskinesias as well as those with and without freezing of gait based on the recorded dyskinesias and freezing of gait episodes. Standard spatiotemporal gait parameters did not differ significantly between patients with and without dyskinesias or freezing of gait. Both the time spent with dyskinesias and the number of freezing of gait episodes positively correlated with the disease severity and medication dosage.
CONCLUSIONS: A single inertial wearable sensor shows promise in monitoring complex, episodic movement patterns, such as dyskinesias and freezing of gait, during daily activities. This approach may help implement targeted therapeutic and preventive strategies for Parkinson\'s disease.
摘要：
背景：运动障碍和步态冻结是帕金森病的偶发性障碍，以波动和不可预测的性质为特征。这项横断面研究旨在客观地监测在日常生活活动中经历运动障碍和/或步态冻结的帕金森病患者，并评估时空步态参数的可能变化。
方法：71名帕金森病患者（40名运动障碍患者和33名步态冻结患者）在家中使用单一可穿戴传感器连续监测至少5天。使用专用机器学习算法根据运动障碍和步态冻结的发生对患者进行分类。此外,在有和没有运动障碍和/或步态冻结的患者中比较了特定的时空步态参数.
结果：可穿戴传感器算法根据记录的运动障碍和冻结步态发作，准确地对有和没有运动障碍的患者以及有和没有冻结步态的患者进行分类。有和没有运动障碍或步态冻结的患者之间的标准时空步态参数没有显着差异。运动障碍的时间和步态发作的冻结次数均与疾病严重程度和药物剂量呈正相关。
结论：单个惯性可穿戴传感器在监测复杂系统方面显示出希望，情节运动模式，比如运动障碍和步态冻结，在日常活动中。这种方法可能有助于对帕金森病实施有针对性的治疗和预防策略。
方法：71名帕金森病患者（40名运动障碍患者和33名步态冻结患者）在家中使用单一可穿戴传感器连续监测至少5天。使用专用机器学习算法根据运动障碍和步态冻结的发生对患者进行分类。此外,在有和没有运动障碍和/或步态冻结的患者中比较了特定的时空步态参数.
结果：可穿戴传感器算法根据记录的运动障碍和冻结步态发作，准确地对有和没有运动障碍的患者以及有和没有冻结步态的患者进行分类。有和没有运动障碍或步态冻结的患者之间的标准时空步态参数没有显着差异。运动障碍的时间和步态发作的冻结次数均与疾病严重程度和药物剂量呈正相关。
结论：单个惯性可穿戴传感器在监测复杂系统方面显示出希望，情节运动模式，比如运动障碍和步态冻结，在日常活动中。这种方法可能有助于对帕金森病实施有针对性的治疗和预防策略。
