Filippou V, Redmond A C, Bennion J, Backhouse M R, Wong D
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:4604-4607. doi: 10.1109/EMBC44109.2020.9176201.
Wearable devices offer a possible solution for acquiring objective measurements of physical activity. Most current algorithms are derived using data from healthy volunteers. It is unclear whether such algorithms are suitable in specific clinical scenarios, such as when an individual has altered gait. We hypothesized that algorithms trained on healthy population will result in less accurate results when tested in individuals with altered gait. We further hypothesized that algorithms trained on simulated-pathological gait would prove better at classifying abnormal activity. We studied healthy volunteers to assess whether activity classification accuracy differed for those with healthy and simulated-pathological conditions. Healthy participants (n=30) were recruited from the University of Leeds to perform nine predefined activities under healthy and simulated-pathological conditions. Activities were captured using a wrist-worn MOX accelerometer (Maastricht Instruments, NL). Data were analyzed based on the Activity-Recognition-Chain process. We trained a Neural-Network, Random-Forests, k-Nearest-Neighbors (k-NN), Support-Vector-Machines (SVM) and Naive Bayes models to classify activity. Algorithms were trained four times; once with healthy' data, and once with simulated-pathological data' for each of activity-type and activity-task classification. In activity-type instances, the SVM provided the best results; the accuracy was 98.4% when the algorithm was trained and then tested with unseen data from the same group of healthy individuals. Accuracy dropped to 52.8% when tested on simulated-pathological data. When the model was retrained with simulated-pathological data, prediction accuracy for the corresponding test set was 96.7%. Algorithms developed on healthy data are less accurate for pathological conditions. When evaluating pathological conditions, classifier algorithms developed using data from a target sub-population can restore accuracy to above 95%.
可穿戴设备为获取身体活动的客观测量值提供了一种可能的解决方案。当前大多数算法都是使用来自健康志愿者的数据推导出来的。尚不清楚此类算法在特定临床场景中是否适用，例如当个体步态改变时。我们假设，在健康人群上训练的算法在步态改变的个体中进行测试时，结果准确性会较低。我们进一步假设，在模拟病理性步态上训练的算法在对异常活动进行分类时会表现得更好。我们研究了健康志愿者，以评估健康状况和模拟病理状况下的活动分类准确性是否存在差异。从利兹大学招募了健康参与者（n = 30），让他们在健康和模拟病理条件下进行九项预定义活动。使用腕戴式MOX加速度计（荷兰马斯特里赫特仪器公司）记录活动。基于活动识别链过程对数据进行分析。我们训练了神经网络、随机森林、k近邻（k-NN）、支持向量机（SVM）和朴素贝叶斯模型来对活动进行分类。算法进行了四次训练；针对活动类型和活动任务分类，分别使用“健康”数据训练一次，使用“模拟病理数据”训练一次。在活动类型实例中，SVM提供了最佳结果；当算法使用同一组健康个体的未见数据进行训练然后测试时，准确率为98.4%。在模拟病理数据上进行测试时，准确率降至52.8%。当使用模拟病理数据对模型进行重新训练时，相应测试集的预测准确率为96.7%。基于健康数据开发的算法在病理状况下的准确性较低。在评估病理状况时，使用目标亚群数据开发的分类算法可将准确率恢复到95%以上。
