Freezing of gait assessment with inertial measurement units and deep learning: effect of tasks, medication states, and stops

• Published in: Journal of neuroengineering and rehabilitation Vol. 21; no. 1; pp. 24 - 22
• Main Authors: Yang, Po-Kai, Filtjens, Benjamin, Ginis, Pieter, Goris, Maaike, Nieuwboer, Alice, Gilat, Moran, Slaets, Peter, Vanrumste, Bart
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 13.02.2024; BioMed Central; BMC
• Subjects: Aged; Analysis; Care and treatment; Clinical trials; Correlation coefficient; Correlation coefficients; Deep Learning; Demographic aspects; Diagnosis; Dopamine receptors; Drugs; Freezing of gait; Gait; Gait Disorders, Neurologic - diagnosis; Gait Disorders, Neurologic - etiology; Humans; Inertial platforms; Machine learning; Methods; Middle Aged; Movement; Movement disorders; MS-TCN; Neural networks; Neurodegenerative diseases; Parkinson Disease - complications; Parkinson Disease - diagnosis; Parkinson Disease - drug therapy; Parkinson's disease; Pelvis; Questionnaires; Talus; Temporal convolutional neural networks; Tibia; Walking; Belgium; Freezing of gait; MS-TCN; Parkinson’s disease; Temporal convolutional neural networks

Freezing of gait (FOG) is an episodic and highly disabling symptom of Parkinson's Disease (PD). Traditionally, FOG assessment relies on time-consuming visual inspection of camera footage. Therefore, previous studies have proposed portable and automated solutions to annotate FOG. However, automa...