Accepted for/Published in: JMIR Mental Health
Date Submitted: Oct 23, 2024
Open Peer Review Period: Oct 22, 2024 - Dec 17, 2024
Date Accepted: Aug 6, 2025
(closed for review but you can still tweet)
Performance of Automatic Speech Analysis in Detecting Depression: Systematic Review and Meta-Analysis
ABSTRACT
Background:
Despite the increased popularity of automatic speech analysis (ASA) for depression assessment, a comprehensive quantitative synthesis of the existing evidence is still lacking.
Objective:
This systematic review and meta-analysis aimed at summarizing the performance of ASA in detecting depression.
Methods:
A systematic search across eight databases was conducted up until July 7, 2023. Eligible studies were appraised for quality using a modified version of the Quality Assessment of Studies of Diagnostic Accuracy-Revised (QUADAS-2).
Results:
A total of 76 studies were included, with the majority exhibiting a high risk of bias in at least one category. A three-level meta-analysis yield pooled highest accuracy, sensitivity, specificity, and precision of 0.81, 0.84, 0.83, and 0.80, respectively, whereas pooled lowest accuracy, sensitivity, specificity, and precision were 0.65, 0.63, 0.58, and 0.64, respectively.
Conclusions:
While ASA shows promise as a tool for detecting depression, further rigorous research is needed before it can be implemented in clinical practice.
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.