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

Dysphonia is one of the early symptoms of Parkinson's disease (PD). Mostexisting methods use feature selection methods to find the optimal subset ofvoice features for all PD patients. Few have considered the heterogeneitybetween patients, which implies the need to provide specific prediction modelsfor different patients. However, building the specific model faces thechallenge of small sample size, which makes it lack generalization ability.Instance transfer is an effective way to solve this problem. Therefore, thispaper proposes a patient-specific game-based transfer (PSGT) method for PDseverity prediction. First, a selection mechanism is used to select PD patientswith similar disease trends to the target patient from the source domain, whichgreatly reduces the risk of negative transfer. Then, the contribution of thetransferred subjects and their instances to the disease estimation of thetarget subject is fairly evaluated by the Shapley value, which improves theinterpretability of the method. Next, the proportion of valid instances in thetransferred subjects is determined, and the instances with higher contributionare transferred to further reduce the difference between the transferredinstance subset and the target subject. Finally, the selected subset ofinstances is added to the training set of the target subject, and the extendeddata is fed into the random forest to improve the performance of the method.Parkinson's telemonitoring dataset is used to evaluate the feasibility andeffectiveness. Experiment results show that the PSGT has better performance inboth prediction error and stability over compared methods.

Patient-Specific Game-Based Transfer Method for Parkinson's Disease Severity Prediction