Speech and Voice Quality as Digital Biomarkers in Depression: A Systematic Review

Objective. To review the current evidence on the use of artificial intelligence-driven speech and voice analysis as a biomarker for depression. Methods. PubMed, Scopus, and Cochrane databases were reviewed by two independent investigators for studies investigating the use of artificial intelligence-driven speech and voice quality outcomes as biomarkers for depression according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statements. The methodological quality and risk of bias of each included study were assessed using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. Results. Of the 108 identified records, 12 studies met the inclusion criteria. The studies examined 16 872 participants, including patients with major depressive disorder (n = 1535), bipolar disorder (n = 111), schizophrenia spectrum disorders (n = 35), and anxiety disorders (n = 224). Control groups included a total of 1204 healthy individuals. Speech and voice quality outcomes consistently distinguished depression from controls (AUC = 0.71-0.93), with prosodic, spectral, and perturbation measures showing significant correlations with standardized depression scales. Classification accuracies ranged from 78% to 96.5%. Six studies demonstrated high risk of methodological bias, primarily in patient selection and validation techniques. Voice recording contexts varied between clinical settings and mobile technologies. Conclusion. The findings of this review highlight the potential of voice biomarkers as a novel tool for depression detection and monitoring. While current evidence demonstrates promising classification accuracy, methodological heterogeneity and generalizability concerns must be addressed before widespread clinical adoption.