Assessment of bradykinesia in Parkinson's disease patients through a multi-parametric system

Abstract

The aim of this paper is to describe and present the results of the automatic detection and assessment of bradykinesia in motor disease patients using wireless, wearable accelerometers. The current work is related to a module of the PERFORM system, a FP7 project from the European Commission, that aims at providing an innovative and reliable tool, able to evaluate, monitor and manage patients suffering from Parkinson's disease. The assessment procedure was carried out through a developed C# library that detects the activities of the patient using an activity recognition algorithm and classifies the data using a Support Vector Machine trained with data coming from previous test phases. The accuracy between the output of the automatic detection and the evaluation of the clinician both expressed with the Unified Parkinson's disease Rating Scale, presents an average value of [68.3 ± 8.9]%. A meta-analysis algorithm is used in order to improve the accuracy to an average value of [74.4 ± 14.9]%. Future work will include a personalized training of the classifiers in order to achieve a higher level of accuracy.

Wearable and wireless accelerometer systems for monitoring Parkinson’s disease patients—A perspective review

“…However, the Kinesia™ device may be prone to having the wire between the command module and sensor becoming dislodged. Wireless accelerometer configurations have been applied for the quantification of Parkinson's disease features within the scope of daily living activities [12][13][14].…”

Assessing Motor Fluctuations in Parkinson’s Disease Patients Based on a Single Inertial Sensor

“…Similarly, Salarian et al [18] employed two triaxial gyroscopes located on each of the forearms to detect and quantify tremor and bradykinesia in 20 PD patients, also obtaining a high correlation with related UPDRS values. Finally, some papers have been presented in the last years as a result of the work done under the European project PERFORM [19,20], where dyskinesia, tremor, and bradykinesia detection were analysed. So far, several limitations are found in former studies.…”

A holistic approach to assess the feasability of telehealth for Parkinson's disease management

“…Finally, Figure 86 shows graphically the quantitative assessment of the system by plotting together the weights of the user needs and the weighted scores of the experts. About the technical performance of the system it shows an accuracy of up to 93.73% of accuracy for the classification of Levodopa Induced Dyskinesias (LID) severity [476], an 86% for the classification of bradykinesia severity [477] and 87% for tremor severity [478]. Also, a specific module was developed for the assessment of gait [5].…”

“…and Pastorino et al (2011) described a methodology to automatically detect the severity of bradykinesia in motor disease patients using wireless, wearable accelerometers. This methodology was tested with cross validation through a sample of 20 Parkinson's disease patients [9], [477]. The assessment of methodology was carried out through some daily living activities which were detected using an activity recognition algorithm.…”

“…Gait assessment [5], [6], [482]. Tremor assessment [478], [483], [484] and bradykinesia assessment [9], [477]. …”