Hyperkinetic movement disorder analysis using multidimensional projections

Abstract

Hyperkinetic movement disorders are a group of conditions characterized by involuntary movements such as tremors, sudden/uncontrollable jerks, abnormal postures, and random movements, which may have major impacts on the quality of life of individuals. The diagnosis of these disorders is often dependent on subjective clinical assessments, and there is a need for automatic methods that can support this diagnosis. Established clinical neurophysiological approaches use motion sensors to collect motion data from patients performing postural, action, or resting tasks to analyze and classify the types of disorders that affect patients. However, making sense of the high-dimensional space formed by patients, tasks, sensors, and disorders is challenging and time-consuming. In this paper, we propose a workflow to explore this space to select appropriate subsets of its data, transform it, and analyze it using multidimensional projections. We show how our workflow can lead to insights into the design of automated pipelines that automatically separate individuals with disorders from healthy individuals.