eduzhai > Applied Sciences > Engineering >

Vision-based Estimation of MDS-UPDRS Gait Scores for Assessing Parkinsons Disease Motor Severity

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 11 pages

Abstract: Parkinson s disease (PD) is a progressive neurological disorder primarilyaffecting motor function resulting in tremor at rest, rigidity, bradykinesia,and postural instability. The physical severity of PD impairments can bequantified through the Movement Disorder Society Unified Parkinson s DiseaseRating Scale (MDS-UPDRS), a widely used clinical rating scale. Accurate andquantitative assessment of disease progression is critical to developing atreatment that slows or stops further advancement of the disease. Prior workhas mainly focused on dopamine transport neuroimaging for diagnosis or costlyand intrusive wearables evaluating motor impairments. For the first time, wepropose a computer vision-based model that observes non-intrusive videorecordings of individuals, extracts their 3D body skeletons, tracks themthrough time, and classifies the movements according to the MDS-UPDRS gaitscores. Experimental results show that our proposed method performssignificantly better than chance and competing methods with an F1-score of 0.83and a balanced accuracy of 81 . This is the first benchmark for classifying PDpatients based on MDS-UPDRS gait severity and could be an objective biomarkerfor disease severity. Our work demonstrates how computer-assisted technologiescan be used to non-intrusively monitor patients and their motor impairments.The code is available atthis https URL.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×