Skip to main content

Table 2 Basic patient characteristics of the clinical data set (MARS study)

From: Creating sparser prediction models of treatment outcome in depression: a proof-of-concept study using simultaneous feature selection and hyperparameter tuning

 

Training data (N = 817)

Validation data (N = 205)

Overall (N = 1,022)

p

Gender

Female

431 (52.8%)

105 (51.2%)

536 (52.4%)

0.753

Male

386 (47.2%)

100 (48.8%)

486 (47.6%)

 

Age

Mean (SD)

47.4 (14.0)

47.1 (14.4)

47.3 (14.1)

0.790

[Min, Max]

[18.0, 85.0]

[18.0, 87.0]

[18.0, 87.0]

 

Diagnosis (ICD-10)

F32

289 (35.4%)

61 (29.8%)

350 (34.2%)

0.152

F33

528 (64.6%)

144 (70.2%)

672 (65.8%)

 

HDRS-17 baseline sum score

Mean (SD)

24.0 (5.6)

23.4 (5.5)

23.8 (5.6)

0.185

[Min, Max]

[12.0, 40.0]

[10.0, 39.0]

[10.0, 40.0]

 

Missing

11 (1.3%)

4 (2.0%)

15 (1.5%)

 

HDRS-17 response

Yes

454 (55.6%)

110 (53.7%)

564 (55.2%)

0.679

No

363 (44.4%)

95 (46.3%)

458 (44.8%)

 
  1. Two sample t-tests were computed for continuous variables, Chi-squared tests were used for categorical variables to compare training and test data set
  2. HDRS-17, 17-item version of the hamilton rating scale for depression; ICD-10, international classification of diseases [34]