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

Alzheimer's disease (AD) is a common form of dementia that severely impactspatient health. As AD impairs the patient's language understanding andexpression ability, the speech of AD patients can serve as an indicator of thisdisease. This study investigates various methods for detecting AD usingpatients' speech and transcripts data from the DementiaBank Pitt database. Theproposed approach involves pre-trained language models and Graph Neural Network(GNN) that constructs a graph from the speech transcript, and extracts featuresusing GNN for AD detection. Data augmentation techniques, including synonymreplacement, GPT-based augmenter, and so on, were used to address the smalldataset size. Audio data was also introduced, and WavLM model was used toextract audio features. These features were then fused with text features usingvarious methods. Finally, a contrastive learning approach was attempted byconverting speech transcripts back to audio and using it for contrastivelearning with the original audio. We conducted intensive experiments andanalysis on the above methods. Our findings shed light on the challenges andpotential solutions in AD detection using speech and audio data.

Exploring Multimodal Approaches for Alzheimer's Disease Detection Using Patient Speech Transcript and Audio Data