Dopaminergic-induced dyskinesia assessment based on a single belt-worn accelerometer

Abstract

Background: After several years of treatment, patients with Parkinson's disease (PD) tend to have, as a side effect of the medication, dyskinesias. Close monitoring may benefit patients by enabling doctors to tailor a personalised medication regimen.Moreover, dyskinesia monitoring can help neurologists make more informed decisions in patient's care.Objective: To design and validate an algorithm able to be embedded into a system that PD patients could wear during their activities of daily living with the purpose of registering the occurrence of dyskinesia in real conditions. Materials and methods:Data from an accelerometer positioned in the waist are collected at the patient's home and are annotated by experienced clinicians. Data collection is divided into two parts: a main database gathered from 92 patients used to partially train and to evaluate the algorithms based on a leave-one-out approach and, on the other hand, a second database from 10 patients which have been used to also train a part of the detection algorithm. Results:Results show that, depending on the severity and location of dyskinesia, specificities and sensitivities higher than 90% are achieved using a leave-one-out methodology. Although mild dyskinesias presented on the limbs are detected with 95% specificity and 39% sensitivity, the most important types of dyskinesia (any strong dyskinesia and trunk mild dyskinesia) are assessed with 95% specificity and 93% sensitivity. Conclusion:The presented algorithmic method and wearable device have been successfully validated in monitoring the occurrence of strong dyskinesias and mild trunk dyskinesias during activities of daily living.

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

“…Notably, the algorithmic basis for the detection of bradykinesia in [53] and this work, with some modifications, is based on a previous work by the authors [52]. On the other hand the algorithmic basis of the dyskinesia block is based on another previous work [33]. The way to combine these algorithms and the database where they are validated are completely new.…”

“…More concretely, these works mainly rely on the use of inertial sensors, although there are other less extended alternatives, as the use of sEMG [25,26,27,28] or another physiological measure [29]. The majority of these research studies have employed wearable sensors to study specific PD symptoms such as FOG [30,31,32], dyskinesia [33,34,35,36] and bradykinesia [18,19,22,37,38,39]; thus, the aim was detecting the presence or severity of a certain symptom. However, the main objective of our work is the detection of ON/OFF motor states of patients, which is mainly related to a dopaminergic deficit and is not related to the presence of a unique symptom.…”

A Waist-Worn Inertial Measurement Unit for Long-Term Monitoring of Parkinson’s Disease Patients

“…These algorithms have been previously presented by the authors in other works [3,41,60,61,62,63]. With these classifiers, along with the gait analysis algorithm, an identification of the PD motor state can be performed.…”

“…In our previous works [3,41,61,65], sampling frequency was 40 Hz. This frequency was selected due to two reasons: the first one, it has been shown that 40 Hz is enough to measure human movement [49]; second, due to the maximum frequency of interest within the PD movements, which is 20 Hz for walking activities [61]. Regarding the filter, a 2nd order Butterworth low-pass filter has been employed to remove the noise of the signal.…”

“…The extracted features are, firstly, temporal characteristics such as mean, standard deviation, range, signal magnitude area, signal correlations, distribution analysis like skewness, kurtosis; and secondly frequency features are used, such as energy and spectral density in specific bands. From these features the bradykinetic gait [41,64] and dyskinesia indexes are extracted [61], as well as if the person is walking based on an SVM model [41,64,66], and the FoG detection output [60]. The calculated index for dyskinesia and bradykinesia, however, might be dismissed given that the person might not suffer neither dyskinesia nor bradykinesia in a certain moment of the day.…”