Classifying Gait Disorder in Neurodegenerative Disorders Among Older Adults Using Deep Learning

Gait disorders in older adults, particularly those associated with neurodegenerative diseases such as Parkinson's Disease, Huntington's Disease, and Amyotrophic Lateral Sclerosis, present significant diagnostic challenges. This study aimed to classify these gait disorders in individuals aged 50 and above using gait vertical ground reaction force data. A deep learning model was developed, employing Continuous Wavelet Transform for feature extraction, with data augmentation techniques applied to enhance dataset variability and improve model performance. Convolutional Neural Networks were used for classification. The model achieved a validation accuracy of 97.53 %, effectively distinguishing between different neurodegenerative diseases and control subjects. These findings underscore the potential of combining vertical ground reaction force data with advanced deep-learning techniques to accurately classify gait disorders in older adults.