Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: Jun 28, 2026
Date Accepted: Sep 25, 2026

The final, peer-reviewed published version of this preprint can be found here:

Cross-Domain Transfer of Depression Voice Biomarkers Depends on the Outcome Instrument: Leakage-Controlled Cross-Sectional Evaluation Study

Wiley R, Schwoebel J, Caccia M, Shor J, Garcia AM, Fisher SD, Frasch MG

Cross-Domain Transfer of Depression Voice Biomarkers Depends on the Outcome Instrument: Leakage-Controlled Cross-Sectional Evaluation Study

J Med Internet Res 2026;28:e105737

DOI: 10.2196/105737

PMID: 43038548

Cross-Domain Transfer of Depression Voice Biomarkers Depends on the Outcome Instrument: Leakage-Controlled Cross-Sectional Evaluation Study

  • Rachel Wiley; 
  • James Schwoebel; 
  • Matias Caccia; 
  • Joel Shor; 
  • Adolfo M. Garcia; 
  • Sheehan D. Fisher; 
  • Martin Gerbert Frasch

ABSTRACT

Background:

Voice-based depression screening is commercializing rapidly, yet whether voice biomarkers generalize across clinical settings is largely untested. Generalization is usually framed as a question about populations, but it is also a question about the outcome instrument a model is scored against. Reported accuracy varies with the diagnostic criteria a study adopts, but in the published literature this is confounded with everything else that differs between studies.

Objective:

We tested whether depression voice biomarkers transfer between perinatal and general-psychiatric speech in both directions under strict leakage control, and whether transfer depends on which screening instrument defines the outcome.

Methods:

In a cross-sectional US-nationwide online study, 446 sessions from 390 pregnant participants at 22±1 weeks’ gestation (analytical sample N=316) each provided four voice recordings. The screening instruments included the eight-item Patient Health Questionnaire (PHQ-8) and a modified nine-item Edinburgh Postnatal Depression Scale (mEPDS-9). We extracted 375 acoustic descriptors and 330-dimensional Population Dynamics Foundation Model (PDFM) community-health embeddings. Discrimination (area under the curve, AUC) was assessed under leakage-controlled cross-validation, with feature and classifier selection inside training folds only, gated by a permutation negative-control harness, across a pre-specified grid of 4 speech tasks × 4 outcome definitions. The prenatal-trained model was applied to two general-psychiatric corpora (DAIC-WOZ, N=189; E-DAIC, N=219) under pure held-out inference, and an open-source model (DAM) trained on ∼35,000 individuals was applied to all three cohorts without refitting, with Benjamini–Hochberg multiplicity control.

Results:

Within the prenatal cohort, the pre-registered outcome was at chance (AUC 0.494, 95% CI 0.431–0.560), and no cell of the 16-cell grid survived adjustment under either modeling paradigm. The prenatal-trained model also did not transfer to either general-psychiatric corpus (AUC 0.505, 0.478). Transfer in the reverse direction, however, depended on the screening instrument. DAM reached AUC 0.706–0.708 on general-psychiatric speech. In the same pregnant participants, it performed at chance against the PHQ-8 (AUC 0.510, 95% CI 0.411–0.609) but discriminated against the mEPDS-9 (AUC 0.645, 95% CI 0.541–0.744), a paired difference of 0.135 (95% CI 0.019–0.248; unadjusted post hoc p=0.021). An exploratory item-level analysis suggests a mechanism: DAM tracked affective-distress items (crying r=0.26, sadness 0.21, overwhelmed 0.20) but not the somatic PHQ-8 items; only crying survived adjustment across 17 tests. Transfer also varied by elicitation task (pregnancy narrative 0.653, 95% CI 0.550–0.753; open-ended speech 0.597, 0.486–0.699; scripted reading 0.544, 0.434–0.651), although these were not compared formally.

Conclusions:

Cross-domain comparison in this analysis is a compound shift: population, elicitation task and outcome instrument differ together, and only the instrument could be varied on its own. Whether a depression voice biomarker transfers may depend not only on the population, but on whether the outcome instrument captures what the model can detect: in the same pregnant participants, a general-population speech model discriminated better against the mEPDS-9 than against the PHQ-8. Validation should state the population, the elicitation task, and the outcome instrument together; a tool validated against one instrument should not be assumed to work against another. Clinical Trial: Preregistered on the Open Science Framework. [https://osf.io/grft3]


 Citation

Please cite as:

Wiley R, Schwoebel J, Caccia M, Shor J, Garcia AM, Fisher SD, Frasch MG

Cross-Domain Transfer of Depression Voice Biomarkers Depends on the Outcome Instrument: Leakage-Controlled Cross-Sectional Evaluation Study

J Med Internet Res 2026;28:e105737

DOI: 10.2196/105737

PMID: 43038548

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.