English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Neurological assessment of stroke is crucial to determine the effectiveness of the treatment routine for subsequent disabilities. Clinical assessment is commonly based on clinician's visual/physical evaluation of patient. Interactive robotic devices can provide objective measurements of movement. In this study, we propose a computer-assisted, robot-guided approach that utilises supervised and unsupervised deep learning to identify stroke-associated impairments not captured in traditional metrics. We employed spatiotemporal features of 1189 participants extracted during a robot-assisted reaching task along with an autoencoder-based classifier to distinguish stroke subjects from controls. Moreover, we utilised an unsupervised approach based on joint optimisation of an autoencoder and a self-organising map for representation learning and visualisation of stroke subjects. Our classifier achieved an average AUC of 0.93 outperforming the baselines. It could also identify stroke participants with clinically normal scores from controls with AUC. Our visualisation maps demonstrated the possibility of existence of sub-clusters in each of clinical scoring levels. Our analysis revealed that these sub-clusters differed mainly in the quantity of successful movements. To conclude, robotic technology paired with virtual/augmented reality is a tool for motion quantification. Computer-assisted evaluation of these measurements could identify impairments not captured in clinical measures.

Computer-aided identification of stroke-associated motor impairments using a virtual reality augmented robotic system