Balance Deficits due to Cerebellar Ataxia: A Machine Learning and Cloud-Based Approach

Abstract

Cerebellar ataxia (CA) refers to the disordered movement that occurs when the cerebellum is injured or affected by disease. It manifests as uncoordinated movement of the limbs, speech, and balance. This study is aimed at the formation of a simple, objective framework for the quantitative assessment of CA based on motion data. We adopted the Recurrence Quantification Analysis concept in identifying features of significance for the diagnosis. Eighty-six subjects were observed undertaking three standard neurological tests (Romberg s, Heel-shin and Truncal ataxia) to capture 213 time series inertial measurements each. The feature selection was based on engaging six different common techniques to distinguish feature subset for diagnosis and severity assessment separately. The Gaussian Naive Bayes classifier performed best in diagnosing CA with an average double cross-validation accuracy, sensitivity, and specificity of 88.24%, 85.89%, and 92.31%, respectively. Regarding severity assessment, the voting regression model exhibited a significant correlation (0.72 Pearson) with the clinical scores in the case of the Romberg s test. The Heel-shin and Truncal tests were considered for diagnosis and assessment of severity concerning subjects who were unable to stand. The underlying approach proposes a reliable, comprehensive framework for the assessment of postural stability due to cerebellar dysfunction using a single inertial measurement unit.