Cross-sectional and longitudinal associations between anxiety and acoustic-prosodic markers in adolescents
Bibliographic record
Abstract
BACKGROUND: Adolescence marks a critical period for the onset of anxiety disorders, yet they frequently remain undiagnosed due to barriers such as reluctance to self-disclose symptoms. Objective screening methods that bypass self-report may improve early detection. Speech-derived acoustic markers have emerged as a promising avenue for identifying anxiety disorders. This study investigates associations between acoustic properties of speech, anxiety severity, and anxiety diagnoses in adolescents, evaluated cross-sectionally and longitudinally. METHODS: Speech samples from 581 adolescents were collected during the Trier Social Stress Test. Acoustic features were extracted using OpenSMILE and analyzed for cross-sectional associations with anxiety severity (Spearman's correlations) and longitudinal predictions of future anxiety (linear regressions). Random forest (RF) classifiers with 10-fold cross-validation were used to classify anxious and healthy individuals using acoustic features. Analyses were stratified by sex. RESULTS: RFs achieved the highest performance for the longitudinal classification of social anxiety disorder (SAD), with an AUC-ROC of 85% (males) and 74% (females). Adding acoustic features to baseline measures increased the variance explained in anxiety by 5.4% (males) and 10.9% (females). In males, higher anxiety was cross-sectionally correlated with reduced pitch slope, narrower pitch range, lower F1 frequency, and greater MFCC1 variability. Females with higher anxiety showed reduced variability in pitch slope. Correlations did not survive multiple testing correction. CONCLUSIONS: Acoustic speech markers elicited in socially evaluative contexts can accurately recognize SAD in male adolescents three years in advance. Performance is moderate for females and other anxiety disorders, underscoring the need for sex-specific approaches to diagnostic tool development.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".