Voice Quality as Digital Biomarker in Bipolar Disorder: A Systematic Review

Voice analysis has emerged as a potential biomarker for mood state detection and monitoring in bipolar disorder (BD). The systematic review aimed to summarize the evidence for voice analysis applications in BD, examining (1) the predictive validity of voice quality outcomes for mood state detection, and (2) the correlation between voice parameters and clinical symptom scales.

A PubMed, Scopus, and Cochrane Library search was carried out by two investigators for publications investigating voice quality in BD according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statements. Studies were assessed using the modified methodological index for non-randomized studies (MINORS).

Of the 400 identified publications, 16 studies met the inclusion accounting for 575 BD patients. Machine learning approaches were implemented in 87.5% of studies, with classification accuracies ranging from 70.9% to 96.9%. Manic state detection showed the strongest predictive validity [area under the curve (AUC) up to 0.89], while depression detection demonstrated moderate performance (AUC: 0.66-0.78). Individual-specific models outperformed population-level approaches (correlation coefficients: 0.78 versus 0.44). Voice quality showed significant correlations with standardized clinical scales, particularly Young Mania Rating Scale and Hamilton Depression Rating Scale (normalized root mean square errors: 1.985 and 3.945, respectively). Prosodic features were examined in 81.25% of studies, with pitch consistently elevated during manic episodes. MINORS varied from 10 to 14, with notable limitations in sample size calculations and blinding procedures.

Voice quality is a promising biomarker in BD, particularly for manic state detection and individualized monitoring. While controlled settings showed strong performance, naturalistic applications yielded more modest results. Future research should focus on standardizing protocols across different environments and conducting large-scale longitudinal studies with robust methodological controls.