EUVIMEDDescobrir EUVIMED
Systematische ÜbersichtMetaanalyseOpen access

Performance of Automatic Speech Analysis in Detecting Depression: Systematic Review and Meta-Analysis

Leistung der automatischen Sprachanalyse beim Erkennen von Depressionen: systematische Übersicht und Metaanalyse

Patricia Laura Maran iD, María Dolores Braquehais iD, Alexandra Vlaic iD, María Teresa Alonzo-Castillo iD, Júlia Vendrell-Serres iD, Josep Antoni Ramos-Quiroga iD, Amanda Rodríguez-Urrutia iD

JMIR Mental Health · 2025-10-22 · 12 · e67802

DOI: 10.2196/67802 ↗

Auf einen Blick

105 Studien zeigen: Die automatische Sprachanalyse erreichte beim Erkennen von Depressionen eine hohe diagnostische Leistung, blieb als eigenständiges klinisches Tool aber limitiert.

Fragestellung

Wie gut erkennt automatische Sprachanalyse Depressionen?

Methode

Systematische Übersicht und Metaanalyse von Studien zur diagnostischen Genauigkeit; Suche in 8 Datenbanken von Januar 2013 bis 1. April 2025.

Ergebnisse

105 Studien. Gepoolte höchste Werte: Accuracy 0,81 (95 %-KI 0,79–0,83), Sensitivität 0,84 (0,81–0,86), Spezifität 0,83 (0,79–0,86), Präzision 0,81 (0,77–0,84). Niedrigste Werte: 0,66, 0,63, 0,60 und 0,64.

Schlussfolgerung der Autor:innen

ASA zeigt Potenzial für das Erkennen von Depressionen, die Eignung als eigenständiges klinisches Instrument bleibt jedoch begrenzt. Die Autor:innen sehen ASA derzeit als ergänzende Methode.

Kernaussagen

  • 105 Studien zur diagnostischen Genauigkeit von ASA
  • Höchste Werte: Accuracy 0,81; Sensitivität 0,84; Spezifität 0,83
  • Niedrigste Werte deutlich geringer als die höchsten Werte

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Systematische Übersicht in JMIR Mental Health, published online on 2025-10-22. Written by Patricia Laura Maran and 6 co-authors. Institution: Psychiatry, Mental Health and Addictions Group, Vall d'Hebron Research Institute (VHIR), Instituto de Investigación Sanitaria Acreditado Instituto de…. Major MEDLINE topics: Depression, Speech. Cited 14 times so far (Crossref); 176 references. The full text is freely available in PubMed Central.

Auf einen BlickResumoSubjectsDados bibliográficosCiteRelated studies

Abstract (original language)

Background

Despite the high prevalence and significant burden of depression, underdiagnosis remains a persistent challenge. Automatic speech analysis (ASA) has emerged as a promising method for depression assessment. However, a comprehensive quantitative synthesis evaluating its diagnostic accuracy is still lacking.

Objective

This systematic review and meta-analysis aimed to assess the diagnostic performance of ASA in detecting depression, considering both machine learning and deep learning approaches.

Methods

We conducted a systematic search across 8 databases, including MEDLINE, PsycInfo, Embase, CINAHL, IEEE Xplore, ACM Digital Library, Scopus, and Google Scholar from January 2013 to April 1, 2025. We included studies published in English that evaluated the accuracy of ASA for detecting depression, and reported performance metrics such as accuracy, sensitivity, specificity, precision, or confusion matrices. Study quality was assessed using a modified version of the Quality Assessment of Studies of Diagnostic Accuracy-Revised. A 3-level meta-analysis was performed to estimate the pooled highest and lowest accuracy, sensitivity, specificity, and precision. Meta-regressions and subgroup analyses were performed to explore heterogeneity across various factors, including type of publication, artificial intelligence algorithms, speech features, speech-eliciting tasks, ground truth assessment, validation approach, dataset, dataset language, participants’ mean age, and sample size.

Results

Of the 1345 records identified, 105 studies met the inclusion criteria. The pooled mean of the highest accuracy, sensitivity, specificity, and precision were 0.81 (95% CI 0.79 to 0.83), 0.84 (95% CI 0.81 to 0.86), 0.83 (95% CI 0.79 to 0.86), and 0.81 (95% CI 0.77 to 0.84), respectively, whereas the pooled mean of the lowest accuracy, sensitivity, specificity, and precision were 0.66 (95% CI 0.63 to 0.69), 0.63 (95% CI 0.58 to 0.68), 0.60 (95% CI 0.55 to 0.66), and 0.64 (95% CI 0.58 to 0.70), respectively.

Conclusions

ASA shows promise as a method for detecting depression, though its readiness for clinical application as a standalone tool remains limited. At present, it should be regarded as a complementary method, with potential applications across diverse contexts. Further high-quality, peer-reviewed studies are needed to support the development of robust, generalizable models and to advance this emerging field. Trial Registration PROSPERO CRD42023444431; https://www.crd.york.ac.uk/PROSPERO/view/CRD42023444431

Subjects

MeSH terms (MEDLINE)

DepressionSpeechHumansDeep LearningSensitivity and SpecificityMachine Learning

Author keywords

AIartificial intelligenceautomatic speech analysisdepressionmeta-analysismobile phone

Authors and institutions

  • Psychiatry, Mental Health and Addictions Group, Vall d'Hebron Research Institute (VHIR), Instituto de Investigación Sanitaria Acreditado Instituto de Investigación - Hospital Universitario Vall d'Hebron (IR-HUVH), Barce…
  • Department of Psychiatry and Forensic Medicine, Universitat Autònoma de Barcelona, Barcelona, Spain.
  • Biomedical Network Research Centre on Mental Health (CIBERSAM), Barcelona, Spain.
  • Integral Care Programme for Sick Health Professionals, Galatea Clinic, Barcelona, Spain.
  • School of Medicine, Universitat Internacional de Catalunya, Barcelona, Spain.
  • Department of Psychiatry, Vall d'Hebron Hospital Universitari, Barcelona, Spain.

ORCID profiles: Patricia Laura Maran, María Dolores Braquehais, Alexandra Vlaic, María Teresa Alonzo-Castillo, Júlia Vendrell-Serres, Josep Antoni Ramos-Quiroga, Amanda Rodríguez-Urrutia

Cite

APA

Maran, P. L., Braquehais, M. D., Vlaic, A., Alonzo-Castillo, M. T., Vendrell-Serres, J., Ramos-Quiroga, J. A., & Rodríguez-Urrutia, A. (2025). Performance of Automatic Speech Analysis in Detecting Depression: Systematic Review and Meta-Analysis. JMIR Mental Health, 12, e67802. https://doi.org/10.2196/67802

Vancouver

Maran PL, Braquehais MD, Vlaic A, Alonzo-Castillo MT, Vendrell-Serres J, Ramos-Quiroga JA, et al. Performance of Automatic Speech Analysis in Detecting Depression: Systematic Review and Meta-Analysis. JMIR Mental Health. 2025;12:e67802. doi:10.2196/67802

BibTeX
@article{Maran2025,
  author = {Maran, Patricia Laura and Braquehais, María Dolores and Vlaic, Alexandra and Alonzo-Castillo, María Teresa and Vendrell-Serres, Júlia and Ramos-Quiroga, Josep Antoni and Rodríguez-Urrutia, Amanda},
  title = {Performance of Automatic Speech Analysis in Detecting Depression: Systematic Review and Meta-Analysis},
  journal = {JMIR Mental Health},
  year = {2025},
  volume = {12},
  pages = {e67802},
  doi = {10.2196/67802}
}
Start for free →