Deep Learning–Based Prediction of Freezing of Gait in Parkinson's Disease With the Ensemble Channel Selection Approach

• Published in: Brain and behavior Vol. 15; no. 1; pp. e70206 - n/a
• Main Authors: Abbasi, Sara, Rezaee, Khosro
• Format: Journal Article
• Language: English
• Published: United States John Wiley & Sons, Inc 01.01.2025; John Wiley and Sons Inc; Wiley
• Subjects: Accuracy; Aged; Algorithms; Automation; bidirectional long short‐term memory; bottleneck attention module; channel selection; Deep Learning; ensembling; Female; freezing of gait; Gait; Gait - physiology; Gait Disorders, Neurologic - diagnosis; Gait Disorders, Neurologic - etiology; Gait Disorders, Neurologic - physiopathology; Humans; Male; Method; Methods; Middle Aged; Neural networks; Parkinson Disease - complications; Parkinson Disease - diagnosis; Parkinson Disease - physiopathology; Parkinson's disease; Wavelet transforms; channel selection; Parkinson's disease; ensembling; freezing of gait; bidirectional long short‐term memory; bottleneck attention module
• ISSN: 2162-3279; 2162-3279
• DOI: 10.1002/brb3.70206

ABSTRACT Purpose A debilitating and poorly understood symptom of Parkinson's disease (PD) is freezing of gait (FoG), which increases the risk of falling. Clinical evaluations of FoG, relying on patients’ subjective reports and manual examinations by specialists, are unreliable, and most detection methods are influenced by subject‐specific factors. Method To address this, we developed a novel algorithm for detecting FoG events based on movement signals. To enhance efficiency, we propose a novel architecture integrating a bottleneck attention module into a standard bidirectional long short‐term memory network (BiLSTM). This architecture, adaptable to a convolution bottleneck attention–BiLSTM (CBA‐BiLSTM), classifies signals using data from ankle, leg, and trunk sensors. Finding Given three movement directions from three locations, we reduce computational complexity in two phases: selecting optimal channels through ensemble learning followed by feature reduction using attention mapping. In FoG event detection tests, performance improved significantly compared to control groups and existing methods, achieving 99.88% accuracy with only two channels. Conclusion The reduced computational complexity enables real‐time monitoring. Our approach demonstrates substantial improvements in classification results compared to traditional deep learning methods. The figure depicts a pipeline for detecting freezing of gait (FoG) in Parkinson's Disease (PD). Sensor data is collected, pre‐processed (normalization and shuffling), and filtered through channel selection. A CBA‐BiLSTM model classifies FoG events and differentiates PD from non‐PD cases, enabling accurate detection and intervention.