Review article · 2025 · Open access

Diagnostic accuracy of traditional and deep learning methods for detecting depression based on speech features: a systematic review and meta-analysis

Wei Lu, Xiaowei Tang, Chuan Huang, Man Wei, Chengxin Bai, Xuqing Fan, Dongmei Wu

BMC Psychiatry, 25(1), 1190 · Published 24 November 2025 · DOI 10.1186/s12888-025-07628-z

Free PDFView at the publisherCite this paper

In brief

“Diagnostic accuracy of traditional and deep learning methods for detecting depression based on speech features: a systematic review and meta-analysis” is a 2025 review article by Wei Lu and 6 co-authors, published in BMC Psychiatry. OpenAlex counts 8 citations as of 15 November 2026, which puts it in the top 2% of works published in 2025 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at BMC Psychiatry.

Citations
8
Most cited in
2026 (8)
Field-weighted impact
0.44
References
54
Authors
7

Abstract

BACKGROUND: Depression diagnosis faces challenges of subjectivity and delay. Speech features offer potential objective biomarkers, but a systematic comparison of traditional machine learning (TML) and deep learning (DL) models is lacking. OBJECTIVE: To evaluate and compare the diagnostic accuracy of TML and DL models for depression detection using speech features, and to examine subgroup effects across sample size, validation strategy, language, and diagnostic criteria. METHODS: Following PRISMA guidelines, we systematically searched 9 databases (PubMed, Medline, Embase, PsycINFO, Scopus, IEEE, Cochrane, ACM Digital Library, and Web of Science) from inception to April 2025. Eligible studies included clinically diagnosed patients with depression and healthy controls, assessed using speech-based TML or DL models, and reporting sensitivity, specificity, or the area under the curve (AUC). Risk of bias was evaluated using the diagnostic Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). Random-effects bivariate models pooled diagnostic performance, and heterogeneity, subgroup, and sensitivity analyses were conducted. RESULTS: Twenty-five studies met the inclusion criteria (9 TML, 16 DL). TML models showed pooled sensitivity of 0.82 (95% CI: 0.74-0.88), specificity 0.83 (95% CI: 0.75-0.90), and AUC 0.89 (95% CI: 0.86-0.92). DL models achieved pooled sensitivity of 0.83 (95% CI: 0.77-0.88), specificity 0.86 (95% CI: 0.80-0.90), and AUC 0.91 (95% CI: 0.89-0.93). Subgroup analyses indicated that diagnostic performance varied by sample size, validation strategy, language, and diagnostic criteria. CONCLUSION: Both TML and DL models demonstrate good diagnostic accuracy in speech-based depression detection. ​The marginal but consistent superiority of DL models supports their potential use in secondary care settings for confirmatory diagnosis, while TML remains valuable for primary care screening.​​. CLINICAL TRIAL NUMBER: Not applicable.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Lu, W., Tang, X., Huang, C., Wei, M., Bai, C., Fan, X., & Wu, D. (2025). Diagnostic accuracy of traditional and deep learning methods for detecting depression based on speech features: a systematic review and meta-analysis. BMC Psychiatry, 25(1), 1190. https://doi.org/10.1186/s12888-025-07628-z

MLA 9

Lu, Wei, et al. “Diagnostic accuracy of traditional and deep learning methods for detecting depression based on speech features: a systematic review and meta-analysis.” BMC Psychiatry, vol. 25, no. 1, 2025, p. 1190. https://doi.org/10.1186/s12888-025-07628-z.

Chicago

Lu, Wei, Xiaowei Tang, Chuan Huang, Man Wei, Chengxin Bai, Xuqing Fan, and Dongmei Wu. 2025. “Diagnostic accuracy of traditional and deep learning methods for detecting depression based on speech features: a systematic review and meta-analysis.” BMC Psychiatry 25 (1): 1190. https://doi.org/10.1186/s12888-025-07628-z.

Harvard

Lu, W. et al. (2025) ‘Diagnostic accuracy of traditional and deep learning methods for detecting depression based on speech features: a systematic review and meta-analysis’, BMC Psychiatry, 25(1), p. 1190. doi:10.1186/s12888-025-07628-z.

IEEE

W. Lu et al., “Diagnostic accuracy of traditional and deep learning methods for detecting depression based on speech features: a systematic review and meta-analysis,” BMC Psychiatry, vol. 25, no. 1, p. 1190, 2025, doi: 10.1186/s12888-025-07628-z.

BibTeX

@article{lu2025diagnostic,
  title     = {{Diagnostic accuracy of traditional and deep learning methods for detecting depression based on speech features: a systematic review and meta-analysis}},
  author    = {Lu, Wei and Tang, Xiaowei and Huang, Chuan and Wei, Man and Bai, Chengxin and Fan, Xuqing and Wu, Dongmei},
  journal   = {BMC Psychiatry},
  year      = {2025},
  volume    = {25},
  number    = {1},
  pages     = {1190},
  doi       = {10.1186/s12888-025-07628-z},
  url       = {https://doi.org/10.1186/s12888-025-07628-z}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition

  • depression detection
  • speech features
  • deep learning
  • traditional machine learning
  • diagnostic accuracy
  • speech biomarkers
  • automated mental health screening
  • primary care screening

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Lu, W., Tang, X., Huang, C., Wei, M., Bai, C., Fan, X., & Wu, D. (2025). Diagnostic accuracy of traditional and deep learning methods for detecting depression based on speech features: a systematic review and meta-analysis. BMC Psychiatry, 25(1), 1190. https://doi.org/10.1186/s12888-025-07628-z

How many times has this paper been cited?

8 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at BMC Psychiatry.

Who wrote this paper?

Wei Lu, Xiaowei Tang, Chuan Huang, Man Wei, Chengxin Bai, Xuqing Fan, Dongmei Wu.

What is the DOI of this paper?

10.1186/s12888-025-07628-z. The permanent link is https://doi.org/10.1186/s12888-025-07628-z.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.