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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Parkinson's disease (PD) is a neuro-degenerative disorder that affectsmovement, speech, and coordination. Timely diagnosis and treatment can improvethe quality of life for PD patients. However, access to clinical diagnosis islimited in low and middle income countries (LMICs). Therefore, development ofautomated screening tools for PD can have a huge social impact, particularly inthe public health sector. In this paper, we present PULSAR, a novel method toscreen for PD from webcam-recorded videos of the finger-tapping task from theMovement Disorder Society - Unified Parkinson's Disease Rating Scale(MDS-UPDRS). PULSAR is trained and evaluated on data collected from 382participants (183 self-reported as PD patients). We used an adaptive graphconvolutional neural network to dynamically learn the spatio temporal graphedges specific to the finger-tapping task. We enhanced this idea with a multistream adaptive convolution model to learn features from different modalitiesof data critical to detect PD, such as relative location of the finger joints,velocity and acceleration of tapping. As the labels of the videos areself-reported, there could be cases of undiagnosed PD in the non-PD labeledsamples. We leveraged the idea of Positive Unlabeled (PU) Learning that doesnot need labeled negative data. Our experiments show clear benefit of modelingthe problem in this way. PULSAR achieved 80.95% accuracy in validation set anda mean accuracy of 71.29% (2.49% standard deviation) in independent test,despite being trained with limited amount of data. This is specially promisingas labeled data is scarce in health care sector. We hope PULSAR will make PDscreening more accessible to everyone. The proposed techniques could beextended for assessment of other movement disorders, such as ataxia, andHuntington's disease.

PULSAR: Graph based Positive Unlabeled Learning with Multi Stream Adaptive Convolutions for Parkinson's Disease Recognition