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/

Zendy Plus

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

Zendy Tools

Zendy Open

This study harnesses state-of-the-art AI technology for detecting mentaldisorders through user-generated textual content. Existing studies typicallyrely on fully supervised machine learning, which presents challenges such asthe labor-intensive manual process of annotating extensive training data foreach research problem and the need to design specialized deep learningarchitectures for each task. We propose a novel method to address thesechallenges by leveraging large language models and continuous multi-promptengineering, which offers two key advantages: (1) developing personalizedprompts that capture each user's unique characteristics and (2) integratingstructured medical knowledge into prompts to provide context for diseasedetection and facilitate predictive modeling. We evaluate our method usingthree widely prevalent mental disorders as research cases. Our methodsignificantly outperforms existing methods, including feature engineering,architecture engineering, and discrete prompt engineering. Meanwhile, ourapproach demonstrates success in few-shot learning, i.e., requiring only aminimal number of training examples. Moreover, our method can be generalized toother rare mental disorder detection tasks with few positive labels. Inaddition to its technical contributions, our method has the potential toenhance the well-being of individuals with mental disorders and offer acost-effective, accessible alternative for stakeholders beyond traditionalmental disorder screening methods.

Few-Shot Learning for Mental Disorder Detection: A Continuous Multi-Prompt Engineering Approach with Medical Knowledge Injection