Cole Bryan T, Roy Serge H, De Luca Carlo J, Nawab S Hamid
IEEE Trans Neural Syst Rehabil Eng. 2014 Sep;22(5):982-91. doi: 10.1109/TNSRE.2014.2310904. Epub 2014 Mar 19.
We have developed and evaluated several dynamical machine-learning algorithms that were designed to track the presence and severity of tremor and dyskinesia with 1-s resolution by analyzing signals collected from Parkinson's disease (PD) patients wearing small numbers of hybrid sensors with both 3-D accelerometeric and surface-electromyographic modalities. We tested the algorithms on a 44-h signal database built from hybrid sensors worn by eight PD patients and four healthy subjects who carried out unscripted and unconstrained activities of daily living in an apartment-like environment. Comparison of the performance of our machine-learning algorithms against independent clinical annotations of disorder presence and severity demonstrates that, despite their differing approaches to dynamic pattern classification, dynamic neural networks, dynamic support vector machines, and hidden Markov models were equally effective in keeping error rates of the dynamic tracking well below 10%. A common set of experimentally derived signal features were used to train the algorithm without the need for subject-specific learning. We also found that error rates below 10% are achievable even when our algorithms are tested on data from a sensor location that is different from those used in algorithm training.
我们开发并评估了几种动态机器学习算法，这些算法旨在通过分析从佩戴少量兼具三维加速度计和表面肌电图模式的混合传感器的帕金森病（PD）患者收集的信号，以1秒的分辨率跟踪震颤和运动障碍的存在及严重程度。我们在一个44小时的信号数据库上测试了这些算法，该数据库由八名PD患者和四名健康受试者佩戴混合传感器生成，他们在类似公寓的环境中进行了无脚本、无约束的日常生活活动。将我们的机器学习算法的性能与关于疾病存在和严重程度的独立临床注释进行比较表明，尽管它们在动态模式分类上方法不同，但动态神经网络、动态支持向量机和隐马尔可夫模型在将动态跟踪的错误率保持在远低于10%方面同样有效。一组通用的实验得出的信号特征被用于训练算法，而无需特定受试者的学习。我们还发现，即使我们的算法在与算法训练中使用的传感器位置不同的数据上进行测试，错误率也能低于10%。
