基于活动分类检测帕金森病患者的左旋多巴诱发异动症

Detection of Levodopa Induced Dyskinesia in Parkinson's Disease patients based on activity classification.

作者信息

Jalloul Nahed, Porée Fabienne, Viardot Geoffrey, L'Hostis Philippe, Carrault Guy

出版信息

Annu Int Conf IEEE Eng Med Biol Soc. 2015;2015:5134-7. doi: 10.1109/EMBC.2015.7319547.

DOI:10.1109/EMBC.2015.7319547

Abstract

In this paper, we present an activity classification-based algorithm for the automatic detection of Levodopa Induced Dyskinesia in Parkinson's Disease (PD) patients. Two PD patients experiencing motor fluctuations related to chronic Levodopa therapy performed a protocol of simple daily life activities on at least two different occasions. A Random Forest classifier was able to classify the performed activities by the patients with an overall accuracy of 86%. Based on the detected activity, a K Nearest Neighbor classifier detected the presence of dyskinesia with accuracy ranging from 75% to 88%.

摘要

在本文中，我们提出了一种基于活动分类的算法，用于自动检测帕金森病（PD）患者的左旋多巴诱导的异动症。两名经历与慢性左旋多巴治疗相关的运动波动的PD患者在至少两个不同场合执行了简单的日常生活活动方案。随机森林分类器能够以86%的总体准确率对患者执行的活动进行分类。基于检测到的活动，K近邻分类器检测异动症的存在，准确率在75%至88%之间。