Aouraghe Ibtissame, Alae Ammour, Ghizlane Khaissidi, Mrabti Mostafa, Aboulem Ghita, Faouzi Belahsen
Laboratory LIPI ENS, USMBA Fez, Morocco.
Laboratory ERMSC, FMPF, CHU Hassan II Fez, Morocco.
J Neurosci Methods. 2020 Jun 1;339:108727. doi: 10.1016/j.jneumeth.2020.108727. Epub 2020 Apr 13.
Parkinson's disease (PD) affects millions of people worldwide, and it is predicted that this pathology will gravely increase in the next few years. Unfortunately, there's currently no cure for this disease, indeed an early diagnosis of Parkinson's disease can help to better manage its symptoms and its evolution. One of the most frequent abilities and usually also the first manifestation of Parkinson's disease is alteration of handwriting.
We propose a novel method to detect Parkinson's disease, based on the segmentation of the online handwritten text into lines. Indeed, we propose to compare Parkinson's disease patients and healthy controls, based on the full dynamics of new temporal and spectral features. Three classifiers were used, K-Nearest Neighbors, Support Vector Machine and Decision Trees. The performances of these three classifiers were estimated using a stratified nested 10 cross-validation. All the models in this study have been evaluated using classification accuracy, balanced accuracy, sensitivity, specificity, F-Score and Matthews Correlation Coefficient.
An accuracy of 92.86 % was obtained with Decision Trees classifier in the last line. The new categories of spectral and temporal features gave the best classification performances in comparison to the basic statistical features.
Previous studies have only focused on words or sentences. This is the first study to deal with the analysis of a text composed of several lines.
The last line discriminates at best between Parkinson's disease patients and healthy controls. This obtained result has further strengthened our hypothesis concerning the fatigue occurring while writing in PD patients.
帕金森病（PD）影响着全球数百万人，预计在未来几年这种病症将急剧增加。不幸的是，目前尚无治愈这种疾病的方法，事实上，帕金森病的早期诊断有助于更好地控制其症状及其发展。帕金森病最常见的能力之一，通常也是其首发表现，是笔迹改变。
我们提出了一种基于将在线手写文本分割成行来检测帕金森病的新方法。实际上，我们建议根据新的时间和频谱特征的完整动态，比较帕金森病患者和健康对照。使用了三种分类器：K近邻、支持向量机和决策树。使用分层嵌套10折交叉验证来估计这三种分类器的性能。本研究中的所有模型均使用分类准确率、平衡准确率（balanced accuracy）、灵敏度、特异性、F分数和马修斯相关系数进行评估。
在最后一行中，决策树分类器获得了92.86% 的准确率。与基本统计特征相比，新的频谱和时间特征类别给出了最佳的分类性能。
先前研究仅关注单词或句子。这是第一项处理由多行组成的文本分析的研究。
最后一行能最好地区分帕金森病患者和健康对照。这一结果进一步强化了我们关于帕金森病患者书写时出现疲劳的假设。
