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.

Song Y, et al. J Korean Med Sci. 2020 Nov;35(47):e402. https://doi.org/10.3346/jkms.2020.35.e402

Background: Assessing a patient’s suicide risk is challenging for health professionals because it depends on voluntary disclosure by the patient and often has limited resources. The application of novel machine learning approaches to determine suicide risk has clinical utility. Objective: This study aimed to investigate cross-sectional and longitudinal approaches to assess suicidality based on acoustic voice features of psychiatric patients using artificial intelligence. Methods: We collected 348 voice recordings during clinical interviews of 104 patients diagnosed with mood disorders at baseline and 2, 4, 8, and 12 months after recruitment. Suicidality was assessed using the Beck Scale for Suicidal Ideation and suicidal behavior using the Columbia Suicide Severity Rating Scale. The acoustic features of the voice, including temporal, formal, and spectral features, were extracted from the recordings. A between-person classification model that examines the vocal characteristics of individuals cross sectionally to detect individuals at high risk for suicide and a within-person classification model that detects considerable worsening of suicidality based on changes in acoustic features within an individual were developed and compared. Internal validation was performed using 10-fold cross validation of audio data from baseline to 2-month and external validation was performed using data from 2 to 4 months. Results: A combined set of 12 acoustic features and 3 demographic variables (age, sex, and past suicide attempts) were included in the single-layer artificial neural network for the between-person classification model. Furthermore, 13 acoustic features were included in the extreme gradient boosting machine learning algorithm for the within-person model. The between-person classifier was able to detect high suicidality with 69% accuracy (sensitivity 74%, specificity 62%, area under the receiver operating characteristic curve 0.62), whereas the within-person model was able to predict worsening suicidality over 2 months with 79% accuracy (sensitivity 68%, specificity 84%, area under receiver operating characteristic curve 0.67). The second model showed 62% accuracy in predicting increased suicidality in external sets. Conclusions: Within-person analysis using changes in acoustic features within an individual is a promising approach to detect increased suicidality. Automated analysis of voice can be used to support the real-time assessment of suicide risk in primary care or telemedicine.

Previous studies report that income inequality is an important risk factor for depression and suicide, and an increasing income gap appears inevitable. However, little study to date has investigated associations between the attribution of poverty and suicide. Though we previously reported associations between socio-cultural factors, including income, and suicide, we tried to explore more focused associations between income, attribution of poverty (individualistic, societal), permissive attitude toward suicide, and suicidal thought using a structural equation model. A total of 2213 participants from each of three nations (South Korea, Japan, and the United States) completed an online survey. Participants without a history of psychological disorders or suicide attempts completed scales measuring attributions of poverty, attitudes toward suicide, and severity of suicidal thoughts. We established a structural equation model, which exhibited a good fit for all nations, and compared significant path coefficients by country. South Korea had the highest severity of suicidal thought and societal attribution of poverty, followed by Japan and America. In all nations, a permissive attitude was positively related to the severity of suicidal thought and individualistic attribution of poverty was positively related to a permissive attitude toward suicide. Societal attribution of poverty was positively associated with a permissive attitude in Japan and the United States. Income was negatively associated with the severity of suicide in South Korea and the United States. Through an established structural equation model, we found the influence of poverty on suicide and identify the common and distinctive factors associated with suicide in each country.

Objective Suicide is a complex phenomenon; therefore, it should be approached in light of sociocultural perspectives and the general attitude toward suicide. This study aimed to extract factors from the Attitude Toward Suicide Scale (ATTS) and investigate the relationship between attitudes toward suicide and suicidal behavior (i.e., suicidal idea, plan, and attempt) by using a representative sample of Korean adults.Methods Three thousand Koreans aged 19 to 75 years were surveyed cross-sectionally in 2013 and 2018. The data collected were subjected to exploratory factor analysis. Extracted attitude factors were compared using a suicidal behavior continuum. Univariate and multivariate logistic models were constructed to compare the association between attitude factors and suicidal behaviors.Results Among the participants, 477 (15.9%) experienced suicidal idea only, 85 (2.8%) had a suicidal plan without attempt, and 58 (1.9%) attempted suicide. Four meaningful factors were extracted from the factor analysis: “permissiveness,” “unjustified behavior,” “preventability/readiness to help,” and “loneliness.” “Permissiveness,” “unjustified behavior,” and “loneliness” factors showed significant trends across the suicidal behavior continuum. Permissive attitude toward suicide increased the odds of suicidal idea, suicidal plan, and suicide attempt (adjusted odds ratio [aOR]=1.49, 95% confidence interval [CI]=1.25–1.79; aOR=2.79, 95% CI=1.84–4.25; aOR=2.67, 95% CI=1.65–4.33), while attitude toward suicide as unjustified behavior decreased the odds of suicidal ideation and attempt (aOR=0.79, 95% CI=0.67–0.94; aOR=0.64, 95% CI=0.42–0.99).Conclusion A significant association was found between attitude toward suicide and suicidal behaviors. Attitude toward suicide is a modifiable factor that can be used to develop prevention policies.