Borzi Luigi, Varrecchia Marilena, Sibille Stefano, Olmo Gabriella, Artusi Carlo Alberto, Fabbri Margherita, Rizzone Mario Giorgio, Romagnolo Alberto, Zibetti Maurizio, Lopiano Leonardo
Department of Control and Computing EngineeringPolitecnico di Torino 10138 Torino Italy.
Department of Neuroscience "Rita Levi Montalcini,"University of Turin 10124 Torino Italy.
IEEE Open J Eng Med Biol. 2020 May 8;1:140-147. doi: 10.1109/OJEMB.2020.2993463. eCollection 2020.
In this paper we investigated the use of smartphone sensors and Artificial Intelligence techniques for the automatic quantification of the MDS-UPDRS-Part III Leg Agility (LA) task, representative of lower limb bradykinesia. We collected inertial data from 93 PD subjects. Four expert neurologists provided clinical evaluations. We employed a novel Artificial Neural Network approach in order to get a continuous output, going beyond the MDS-UPDRS score discretization. We found a Pearson correlation of 0.92 between algorithm output and average clinical score, compared to an inter-rater agreement index of 0.88. Furthermore, the classification error was less than 0.5 scale point in about 80% cases. We proposed an objective and reliable tool for the automatic quantification of the MDS-UPDRS Leg Agility task. In perspective, this tool is part of a larger monitoring program to be carried out during activities of daily living, and managed by the patients themselves.
在本文中，我们研究了使用智能手机传感器和人工智能技术对MDS-UPDRS第三部分腿部敏捷性（LA）任务进行自动量化，该任务是下肢运动迟缓的代表。我们收集了93名帕金森病患者的惯性数据。四位神经科专家提供了临床评估。我们采用了一种新颖的人工神经网络方法，以获得连续输出，超越MDS-UPDRS评分的离散化。我们发现算法输出与平均临床评分之间的Pearson相关性为0.92，而评分者间一致性指数为0.88。此外，在约80%的病例中，分类误差小于0.5个量表点。我们提出了一种用于自动量化MDS-UPDRS腿部敏捷性任务的客观可靠工具。从长远来看，该工具是在日常生活活动中实施的更大监测计划的一部分，由患者自己管理。
