An Automatic Method for Identifying Huntington's Disease using Gait Dynamics

Huntington's Disease (HD) is a genetic disorder that causes the progressive breakdown of nerve cells in the brain, reducing an individual's ability to reason, walk, and speak. Due to its severity, new approaches are important for the development of methods that contribute to the correct classification of this disease. In this paper, we propose an automatic method for diagnosing Huntington's Disease using gait dynamics information. Our approach is divided into a four-stage pipeline: preprocessing, feature extraction, classification, and diagnosis output. We evaluate the performance of our proposed method through well-known classifiers that are commonly used in machine learning problems. A publicly available database on Gait Dynamics in Neuro-Degenerative Disease is used, and the experimental results show that both Support Vector Machines (SVM) and Decision Tree (DT) were able to achieve an average accuracy of 100:0%, representing an improvement in the field.