Previously submitted to: JMIR Mental Health (no longer under consideration since Jan 08, 2026)
Date Submitted: Jan 8, 2026
Open Peer Review Period: Jan 8, 2026 - Jan 8, 2026
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Robust Acoustic Markers of Suicidal Ideation in College Students: A Multiverse Analysis of Machine Learning Pipelines
ABSTRACT
Background:
Suicide is a major global public health crisis and a leading cause of unnatural death among college students. Current suicide risk assessment mainly relies on self-report questionnaires and structured interviews. These methods are vulnerable to response bias and cannot support continuous monitoring. There is an urgent need for objective and non-invasive markers of suicide risk. Speech provides a promising source of such markers, as acoustic features reflect emotional and cognitive states related to suicidal ideation. Although speech-based machine learning models have shown encouraging predictive performance, most studies rely on single analytical pipelines. Consequently, the robustness and generalizability of reported acoustic markers across analytical choices remain a question for clinical translation.
Objective:
This study aimed to systematically evaluate how analytical variability influences predictive performance and feature stability in acoustic-based suicidal ideation detection. In addition, we sought to identify robust vocal biomarkers that generalize across analytical specifications.
Methods:
A comprehensive multiverse analysis was conducted across 1,764 distinct analytical pipelines using speech data from 96 Chinese university students (48 clinically confirmed cases of suicidal ideation and 48 matched controls). The pipelines varied in preprocessing strategies, acoustic feature sets, dimensionality reduction methods, and machine learning models. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC). Feature importance was aggregated across all pipelines to identify the top 10 core acoustic features. These features were subsequently examined within a new multiverse analysis framework to assess their robustness across analytical specifications.
Results:
Predictive performance was highly sensitive to analytical choices, with AUC values ranging from near chance (0.508) to high discriminative accuracy (0.856). Despite this variability, a core subset of acoustic features—including fundamental frequency (F0), F0 envelope, and Mel-frequency cepstral coefficients (MFCCs)—demonstrated robust and stable associations with suicidal ideation. These features remained statistically significant in 238 of 240 eligible specifications (99.2%).
Conclusions:
Although speech-based computational prediction of suicidal ideation is highly dependent on analytical decisions, the underlying discriminative acoustic signals are remarkably stable. Multiverse analysis offers a transparent and rigorous framework for distinguishing robust vocal biomarkers from pipeline-dependent findings. This approach supports the development of reliable, interpretable, and clinically deployable voice-based mental health screening tools. Clinical Trial: This research was registered prospectively in the Chinese Clinical Trial Registry (http://www.chictr.org.cn) with the registration number ChiCTR2500106625.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© 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.