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

Speech patterns have been identified as potential diagnostic markers forneuropsychiatric conditions. However, most studies only compare a singleclinical group to healthy controls, whereas clinical practice often requiresdifferentiating between multiple potential diagnoses (multiclass settings). Toaddress this, we assembled a dataset of repeated recordings from 420participants (67 with major depressive disorder, 106 with schizophrenia and 46with autism, as well as matched controls), and tested the performance of arange of conventional machine learning models and advanced Transformer modelson both binary and multiclass classification, based on voice and text features.  While binary models performed comparably to previous research (F1 scoresbetween 0.54-0.75 for autism spectrum disorder, ASD; 0.67-0.92 for majordepressive disorder, MDD; and 0.71-0.83 for schizophrenia); whendifferentiating between multiple diagnostic groups performance decreasedmarkedly (F1 scores between 0.35-0.44 for ASD, 0.57-0.75 for MDD, 0.15-0.66 forschizophrenia, and 0.38-0.52 macro F1). Combining voice and text-based modelsyielded increased performance, suggesting that they capture complementarydiagnostic information.  Our results indicate that models trained on binary classification may learnto rely on markers of generic differences between clinical and non-clinicalpopulations, or markers of clinical features that overlap across conditions,rather than identifying markers specific to individual conditions. We providerecommendations for future research in the field, suggesting increased focus ondeveloping larger transdiagnostic datasets that include more fine-grainedclinical features, and that can support the development of models that bettercapture the complexity of neuropsychiatric conditions and naturalisticdiagnostic assessment.

Automated speech- and text-based classification of neuropsychiatric conditions in a multidiagnostic setting