Predicting Axial Impairment in Parkinson’s Disease through a Single Inertial Sensor

Abstract

Background: Current telemedicine approaches lack standardised procedures for the remote assessment of axial impairment in Parkinson’s disease (PD). Unobtrusive wearable sensors may be a feasible tool to provide clinicians with practical medical indices reflecting axial dysfunction in PD. This study aims to predict the postural instability/gait difficulty (PIGD) score in PD patients by monitoring gait through a single inertial measurement unit (IMU) and machine-learning algorithms. Methods: Thirty-one PD patients underwent a 7-m timed-up-and-go test while monitored through an IMU placed on the thigh, both under (ON) and not under (OFF) dopaminergic therapy. After pre-processing procedures and feature selection, a support vector regression model was implemented to predict PIGD scores and to investigate the impact of L-Dopa and freezing of gait (FOG) on regression models. Results: Specific time- and frequency-domain features correlated with PIGD scores. After optimizing the dimensionality reduction methods and the model parameters, regression algorithms demonstrated different performance in the PIGD prediction in patients OFF and ON therapy (r = 0.79 and 0.75 and RMSE = 0.19 and 0.20, respectively). Similarly, regression models showed different performances in the PIGD prediction, in patients with FOG, ON and OFF therapy (r = 0.71 and RMSE = 0.27; r = 0.83 and RMSE = 0.22, respectively) and in those without FOG, ON and OFF therapy (r = 0.85 and RMSE = 0.19; r = 0.79 and RMSE = 0.21, respectively). Conclusions: Optimized support vector regression models have high feasibility in predicting PIGD scores in PD. L-Dopa and FOG affect regression model performances. Overall, a single inertial sensor may help to remotely assess axial motor impairment in PD patients.

Context Recognition Algorithms for Energy-Efficient Freezing-of-Gait Detection in Parkinson’s Disease

“…Some of these features represent basic characteristics describing the amplitude of the signal (e.g., median, range, minimum, and maximum values). Other more complex features were previously used for walking (e.g., maximum spectral peak height, frequency of the dominant harmonic, and width of the dominant harmonic) [49] and turning (e.g., jerk, spectral entropy, and power density in the postural band) [47] analysis, while others were used for FoG detection (e.g., increments, principal components, kurtosis, and skewness) [41,50]. This set of features was used to feed two ML classification algorithms, including a logistic regression (LR) model and an RF classifier [51] with 100 estimators.…”

Clinical neurophysiology of Parkinson’s disease and parkinsonism

“…The effects of DBS of different targets can be disappointing and often detrimental, also when targeting cholinergic experimental targets such as the PPN ( Fasano et al, 2015a ). New therapeutic approaches for FOG include closed-loop systems involving wearable sensors for the automatic detection or prediction of FOG, and the real-time administration of sensory stimuli to improve gait ( Suppa et al, 2017b , Borzì et al, 2022 ).…”

Multiscale Entropy Algorithms to Analyze Complexity and Variability of Trunk Accelerations Time Series in Subjects with Parkinson’s Disease

“…Due to the effects of dopamine depletion on motor control, swPD are characterized by increased gait variability [ 5 , 6 , 7 ], which can result in a number of gait abnormalities, including shuffling gait and reduced step length [ 8 , 9 , 10 ]. Altered trunk behavior showed to characterize gait impairment [ 11 , 12 , 13 , 14 , 15 , 16 , 17 ] and to represent a responsive outcome for medications and rehabilitation in swPD [ 17 , 18 , 19 , 20 , 21 , 22 ]. Wearable sensors, such as magneto-inertial measurement units (MIMUs), have been shown to provide trunk acceleration-derived gait indexes that can accurately characterize gait abnormalities, fall risk, and gait variability in swPD [ 14 , 23 , 24 ], and responsive measures to quantify the effectiveness of rehabilitation [ 25 ].…”