Search

The motor features of people with cerebellar ataxia suggest that locomotion is substantially impaired due to incoordination of the head, trunk, and limbs. The purpose of this study was to investigate how well a wearable soft passive exoskeleton worked for motor coordination in these patients. We used an optoelectronic system to examine the gait of nine ataxic people in three different conditions: without an exoskeleton and with two variants of the exoskeleton, one less and the other more flexible. We investigated kinematics using trunk ranges of motion, the displacement of the center of mass in the medio-lateral direction, and the parameters of mechanical energy consumption and recovery. Furthermore, we investigated the lower limb and trunk muscle coactivation. The results revealed a reduction of the medio-lateral sway of the center of mass, a more efficient behavior of the body in the antero-posterior direction, an energy expenditure optimization, a reduction of muscle coactivation and a better coordination between muscle activations. As a result, the findings laid the groundwork for the device to be used in the rehabilitation of individuals with cerebellar ataxia. [ABSTRACT FROM AUTHOR]

The interpretability of gait analysis studies in people with rare diseases, such as those with primary hereditary cerebellar ataxia (pwCA), is frequently limited by the small sample sizes and unbalanced datasets. The purpose of this study was to assess the effectiveness of data balancing and generative artificial intelligence (AI) algorithms in generating synthetic data reflecting the actual gait abnormalities of pwCA. Gait data of 30 pwCA (age: 51.6 ± 12.2 years; 13 females, 17 males) and 100 healthy subjects (age: 57.1 ± 10.4; 60 females, 40 males) were collected at the lumbar level with an inertial measurement unit. Subsampling, oversampling, synthetic minority oversampling, generative adversarial networks, and conditional tabular generative adversarial networks (ctGAN) were applied to generate datasets to be input to a random forest classifier. Consistency and explainability metrics were also calculated to assess the coherence of the generated dataset with known gait abnormalities of pwCA. ctGAN significantly improved the classification performance compared with the original dataset and traditional data augmentation methods. ctGAN are effective methods for balancing tabular datasets from populations with rare diseases, owing to their ability to improve diagnostic models with consistent explainability. [ABSTRACT FROM AUTHOR]