Quantitative assessment of cerebella ataxia through automated upper limb functional tests

Abstract

Neurological disorders typically exhibit movement disabilities and disorders such as cerebellar ataxia (CA) can cause coordination inaccuracies often manifested as disabilities associated with gait, balance and speech. Since the severity assessment of the disorder is based on the expert clinical opinion, it is likely to be subjective. Automated versions of two upper limb tests: Finger to Nose test (FNT) and Diadochokinesia (DDK) test are investigated in this paper. Inertial Measurement Units (IMU) (BioKin TM) are employed to capture the disability by measuring limb movements. Translational and rotational accelerations considered as kinematic parameters provided the features relevant to characteristic movements intrinsic to the disability. Principal Component Analysis (PCA) and multi-class Linear Discriminant classifier (LDA) were instrumental in dominant features correlating with the clinical scores. The relationship between clinicians assessment and the objective analysis is examined using Pearson Correlation. This study found that although FNT predominantly consist of translational movements, rotation was the dominant feature while for the case of DDK that predominantly consist of rotational movements, acceleration was the dominant feature. The degree of correlation in each test was also enhanced by combining the features in different tests.

Technological Evolution in the Instrumentation of Ataxia Severity Measurement

“…In contrast to other neurological diseases such as Parkinson's disease (PD) or Alzheimer's Disease (AD), the dataset for CA is not publicly available. Across all domains, researchers have engaged conventional ML algorithms such as Random Forest, Linear discriminant and regression analysis (LDRA) [47], [48], Support Vector Machine (SVM), LASSO, Hidden Markov Model [49], Decision Trees, K-Nearest Neighbor [50], Leastsquares support vector machine (LSSVM) [51], 3-nearest neighbour (3-NN), and neural network (NN) [52]. DL limited to the use of Deep Convolutional Neural Networks, Recurrent Neural Networks (RNNs), and Transfer Learning [53].…”

“…Differential diagnosis: 80% accuracy in [91] and 84.6% accuracy in [90]. Severity estimation: 74% in the 3-level CA severity estimation [90] LOWER LIMB ATAXIA Device Illustration Description Feature Clinical Implication IMU kinematic sensor (2019) [34], [47], [48] Heel-shin task in SARA and foot tapping have been employed to evaluate CA. Lower limb domain has been suggested to assess non-ambulant individuals.…”

“…Univariate analysis: Magnitude of the resonant frequencies [48]. Differential diagnosis: ML models yielded 89% [48] and 88.24% [34] accuracy.…”

“…Univariate analysis: Magnitude of the resonant frequencies [48]. Differential diagnosis: ML models yielded 89% [48] and 88.24% [34] accuracy. Severity estimation: 0.72 correlation with SARA acquired through stacking regression models [34] Wireless sensing system (2020) [50] A wireless non-intrusive system to sense lower limb heel-shin via a repetitive task.…”

Quantitative body symmetry assessment during neurological examination

“…These tests are analogous to each other and help to evaluate rapidly alternating performance as well as point-to-point movement. Moreover, they allow to evaluate the slowdown of movements, joint amplitudes, and accuracy [29][30][31]. Examination of all these parameters on different sides of the body allows to estimate the asymmetry.…”