Fisher James M, Hammerla Nils Y, Ploetz Thomas, Andras Peter, Rochester Lynn, Walker Richard W
Department of Medicine, Northumbria Healthcare NHS Foundation Trust, United Kingdom.
School of Computing Science, Newcastle University, United Kingdom.
Parkinsonism Relat Disord. 2016 Dec;33:44-50. doi: 10.1016/j.parkreldis.2016.09.009. Epub 2016 Sep 9.
Current PD assessment methods have inherent limitations. There is need for an objective method to assist clinical decisions and to facilitate evaluation of treatments. Accelerometers, and analysis using artificial neural networks (ANN), have shown potential as a method of motor symptom evaluation. This work describes the development of a novel PD disease state detection system informed by algorithms based on data collected in an unsupervised, home environment. We evaluated whether this approach can reproduce patient-completed symptom diaries and clinical assessment of disease state.
34 participants with PD wore bilateral wrist-worn accelerometers for 4 h in a research facility (phase 1) and for 7 days at home whilst completing symptom diaries (phase 2). An ANN to predict disease state was developed based on home-derived accelerometer data. Using a leave-one-out approach, ANN performance was evaluated against patient-completed symptom diaries and against clinician rating of disease state.
In the clinical setting, specificity for dyskinesia detection was extremely high (0.99); high specificity was also demonstrated for home-derived data (0.93), but with low sensitivity (0.38). In both settings, sensitivity for on/off detection was sub-optimal. ANN-derived values of the proportions of time in each disease state showed strong, significant correlations with patient-completed symptom diaries.
Accurate, real-time evaluation of symptoms in an unsupervised, home environment, with this sensor system, is not yet achievable. In terms of the amounts of time spent in each disease state, ANN-derived results were comparable to those of symptom diaries, suggesting this method may provide a valuable outcome measure for medication trials.
当前帕金森病（PD）的评估方法存在固有局限性。需要一种客观的方法来辅助临床决策并促进对治疗效果的评估。加速度计以及使用人工神经网络（ANN）进行的分析，已显示出作为运动症状评估方法的潜力。这项工作描述了一种新型PD疾病状态检测系统的开发，该系统基于在无监督的家庭环境中收集的数据所形成的算法。我们评估了这种方法是否能够重现患者填写的症状日记以及疾病状态的临床评估。
34名PD患者在研究机构佩戴双侧腕部加速度计4小时（第一阶段），并在家中佩戴7天，同时填写症状日记（第二阶段）。基于在家中采集的加速度计数据开发了一个用于预测疾病状态的人工神经网络。采用留一法，将人工神经网络的性能与患者填写的症状日记以及临床医生对疾病状态的评分进行对比评估。
在临床环境中，异动症检测的特异性极高（0.99）；在家中采集的数据中也显示出高特异性（0.93），但敏感性较低（0.38）。在两种环境下，开/关期检测的敏感性均未达到最佳。人工神经网络得出的每种疾病状态下的时间比例值与患者填写的症状日记显示出强烈且显著的相关性。
使用该传感器系统在无监督的家庭环境中进行症状的准确、实时评估目前尚无法实现。就每种疾病状态下所花费的时间量而言，人工神经网络得出的结果与症状日记的结果相当，这表明该方法可能为药物试验提供有价值的结果指标。
