Table 2 Model performance of the regression analysis for the discovery model and its application to the validation, Cam-CAN and patient groups

From: The BMIgap tool to quantify transdiagnostic brain signatures of current and future weight

Study group

n

BMIgap uncorrected (kg m−2)

BMIgap (kg m−2)

MAE (kg m−2)

R2

r

P

HCdiscovery

770

−0.01 (3.4)

0 (1.78)

2.75

0.28

0.53

2.1975 × 10−56

HCvalidation

734

1.73 (2.2)

0.23 (1.68)

2.29

0.26

0.51

1.3696 × 10−15

HCCam-CAN

536

0.82 (0.56)

0.25 (3.26)

2.96

0.10

0.32

7.7240 × 10−14

Schizophrenia

146

1.83 (3.0)

1.05 (1.53)

2.85

0.25

0.50

1.2242 × 10−10

CHR

213

1.70 (3.26)

0.51 (1.68)

3.07

0.16

0.40

2.2209 × 10−7

ROD

200

−0.03 (3.48)

−0.82 (1.64)

2.73

0.10

0.32

3.7118 × 10−5

  1. P values in bold indicate statistical significance (α = 0.05).
  2. BMIgap is shown as the mean ± s.d. (uncorrected and corrected for BMI). Model performance metrics include the MAE, the coefficient of determination (R2) and Pearson correlation coefficients (r, two-sided) between predicted and observed BMI.
Back to article page