Background: In many developed countries, mental health disorders have become a problem, and the economic loss due to treatment costs and interference with work is immeasurable. Therefore, a simple technique must be developed to determine individuals’ depressive state and stress levels. Voice analysis using smartphones is not only noninvasive, it does not require a dedicated device; thus, it can be performed conveniently and remotely. Consequently, we developed a method to assess individuals’ mental health levels using emotional components contained in the human voice.
Methods: We proposed two indices of mental health: a short-term index (vitality) and mental activity calculated from long-term trends in vitality. We used the voices of healthy individuals (men: n = 10, Mage = 42.7 ± 6.0 years; women: n = 4, Mage = 35.0 ± 14.4 years) and patients with major depression (men: n = 19, Mage = 43.7 ± 11.0 years; women: n = 11, Mage = 53.9 ± 8.2 years). For patients, simultaneously with voice collection, specialists assessed current depression severity using the Hamilton Rating Scale for Depression (HAM-D).
Results: A significant negative correlation existed between the vitality extracted from voice and HAM-D score (r = -0.33, p < .05). We could discriminate the voice data of healthy individuals and patients with depression (judged as moderate or severe by the specialists) with high accuracy using vitality (p = .0085, the area under the curve (AUC) of the receiver operating characteristic curve = 0.87). However, there was no significant difference between the vitality of the healthy individuals and the patients judged to be the “no depression group with almost no depressive symptoms,” even if they were outpatients with depression (p > .1, AUC = 0.64).
Conclusions: We developed a method to estimate stress through emotion instead of analyzing stress directly from voice data. By daily monitoring of vitality using smartphones, we can encourage hospital visits for people before they become depressed or during the early stages of depression. This may lead to reduced economic loss due to treatment costs and interference with work.