Both minor and major depression have high prevalence and are important causes of social burden worldwide; however, there is still no objective indicator to detect minor depression. This study aimed to examine if voice could be used as a biomarker to detect minor and major depression. Ninety-three subjects were classified into three groups: the not depressed group (n = 33), the minor depressive episode group (n = 26), and the major depressive episode group (n = 34), based on current depressive status as a dimension. Twenty-one voice features were extracted from semi-structured interview recordings. A three-group comparison was performed through analysis of variance. Seven voice indicators showed differences between the three groups, even after adjusting for age, BMI, and drugs taken for non-psychiatric disorders. Among the machine learning methods, the best performance was obtained using the multi-layer processing method, and an AUC of 65.9%, sensitivity of 65.6%, and specificity of 66.2% were shown. This study further revealed voice differences in depressive episodes and confirmed that not depressed groups and participants with minor and major depression could be accurately distinguished through machine learning. Although this study is limited by a small sample size, it is the first study on voice change in minor depression and suggests the possibility of detecting minor depression through voice.

Background: Major depressive disorder and bipolar disorder are prevalent and debilitating psychiatric disorders that are difficult to distinguish, as their diagnosis is based on behavioural observations and subjective symptoms. Quantitative protein profile analysis might help to objectively distinguish between these disorders and increase our understanding of their pathophysiology. Thus, this study was conducted to compare the peripheral protein profiles between the two disorders. Methods: Serum samples were collected from 18 subjects with major depressive disorder and 15 subjects with bipolar disorder. After depleting abundant proteins, liquid chromatography-tandem mass spectrometry (LC-MS/MS) and label-free quantification were performed. Data-dependent acquisition data were statistically analysed from the samples of 15 subjects with major depressive disorder and 10 subjects with bipolar disorder who were psychotropic drug-free. Two-sided t-tests were performed for pairwise comparisons of proteomes to detect differentially-expressed proteins (DEPs). Ingenuity Pathway Analysis of canonical pathways, disease and functions, and protein networks based on these DEPs was further conducted. Results: Fourteen DEPs were significant between subjects with major depressive disorder and those with bipolar disorder. Ras-related protein Rab-7a (t = 5.975, p = 4.3 × 10^− 6) and Rho-associated protein kinase 2 (t = 4.782, p = 8.0 × 10^− 5) were significantly overexpressed in subjects with major depressive disorder and Exportin-7 (t = -4.520, p = 1.5 × 10^− 4) was significantly overexpressed in subjects with bipolar disorder after considering multiple comparisons. Bioinformatics analysis showed that cellular functions and inflammation/immune pathways were significantly different. Conclusions: Ras-related protein Rab-7a, Rho-associated protein kinase 2, and Exportin-7 were identified as potential peripheral protein candidates to distinguish major depressive disorder and bipolar disorder. Further large sample studies with longitudinal designs and validation processes are warranted.