Validation of Machine Learning-Based Assessment of Major Depressive Disorder from Paralinguistic Speech Characteristics in Routine Care

Table 1

Sample characteristics.

Variable	All participants ()
Age, (SD)	45.6 (10.5)
Sex, female (%)	59.2
School education (%)
<9 years	0.8
9 years	10.0
10 years	27.3
>10 years	61.9
Nationality (%)
German	98.5
Other	1.5
Family status (%)
Single	20.1
Married/living in a partnership	58.3
Separated/divorced	19.3
Widowed	2.3
Current occupation, yes (%)	78.8
HRSD
Baseline, (SD)	9.58 (5.94)
Overall, (SD)	8.89 (6.91)
QIDS-C
Baseline, (SD)	7.09 (4.24)
Overall, (SD)	6.80 (5.12)
PHQ-9
Baseline, (SD)	8.43 (4.42)
Overall, (SD)	7.77 (5.12)

HRSD = Hamilton Rating Scale for Depression; QIDS-C = Quick Inventory of Depressive Symptomatology–Clinician-rated; PHQ-9 = depression module of the Patient Health Questionnaire.