Taguchi T, et al. – Researchers performed this examination to investigate whether vocal acoustic features could allow discrimination between depressive patients and healthy controls. They observed that the mel–frequency cepstrum coefficient 2 (MFCC 2) was significantly different between depressive patients and controls and this feature could be a useful biomarker to identify the major depressive disorder.

Methods

• This study was conducted on thirty-six patients who met the criteria for major depressive disorder and 36 healthy controls with no current or past psychiatric disorders.
• Voices of reading out digits prior and then afterward verbal fluency task were recorded.
• Using OpenSMILE, voices were analyzed.
• The extracted acoustic features, including mel-frequency cepstrum coefficients (MFCCs), were utilized for group comparison and discriminant analysis between patients and controls.

Results

• The analysis in this study showed that the second dimension of MFCC (MFCC 2) was significantly different between groups and allowed the discrimination between patients and controls with a sensitivity of 77.8% and a specificity of 86.1%.
• Data reported that the difference in MFCC 2 between the 2 groups reflected an energy difference of frequency around 2000–3000 Hz.