Pardoel Scott, AlAkhras Ayham, Jafari Ensieh, Kofman Jonathan, Lemaire Edward D, Nantel Julie
Department of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada.
School of Human Kinetics, Faculty of Health Sciences, University of Ottawa, Ottawa, ON K1N 6N5, Canada.
Sensors (Basel). 2024 Dec 23;24(24):8211. doi: 10.3390/s24248211.
Freezing of gait (FOG) is a walking disturbance that can lead to postural instability, falling, and decreased mobility in people with Parkinson's disease. This research used machine learning to predict and detect FOG episodes from plantar-pressure data and compared the performance of decision tree ensemble classifiers when trained on three different datasets. Dataset 1 ( = 11) was collected in a previous study. Dataset 2 ( = 10) included six new participants and four participants from Dataset 1 who were re-tested (approximately 2 years later), and Dataset 3 ( = 21) combined Datasets 1 and 2. The prediction model trained on Dataset 3 had a 2.28% higher sensitivity and 3.09% lower specificity compared to the models trained on Dataset 1. The model trained on Dataset 3 identified 86.84% of the total FOG episodes compared to 74.31% from the model trained on Dataset 1. Also, the model using Dataset 3 identified the FOG episodes 0.3 s earlier than the model developed with Dataset 1. The model trained using Dataset 3 showed improved performance in sensitivity, identification time, and FOG identification. The improvements using the expanded dataset (Dataset 3) in this study compared to the previous model reinforce the validity and generalizability of the original model. The model was able to predict and detect FOG well and is, therefore, ready to be implemented in a FOG prevention device.
冻结步态（FOG）是一种行走障碍，可导致帕金森病患者出现姿势不稳、跌倒及活动能力下降。本研究利用机器学习从足底压力数据预测和检测冻结步态发作，并比较了在三个不同数据集上训练时决策树集成分类器的性能。数据集1（n = 11）是在之前的一项研究中收集的。数据集2（n = 10）包括6名新参与者和4名来自数据集1的参与者（约2年后重新测试），数据集3（n = 21）将数据集1和2合并。与在数据集1上训练的模型相比，在数据集3上训练的预测模型灵敏度高2.28%，特异性低3.09%。在数据集3上训练的模型识别出了86.84%的总冻结步态发作，而在数据集1上训练的模型识别出的比例为74.31%。此外，使用数据集3的模型比使用数据集1开发的模型提前0.3秒识别出冻结步态发作。使用数据集3训练的模型在灵敏度、识别时间和冻结步态识别方面表现出了改进。与之前的模型相比，本研究中使用扩展数据集（数据集3）的改进强化了原始模型的有效性和通用性。该模型能够很好地预测和检测冻结步态，因此，已准备好在冻结步态预防装置中实施。
