Skip to main content

Table 2 Model performance for predicting whole-body composition in the internal dataset

From: CT analysis of thoracolumbar body composition for estimating whole-body composition

 

Multi-slice averaging in the waist

Single-slice L2 lower endplate

Single-slice L3 upper endplate

Multi-slice averaging in T12–L1

Single-slice T12 lower endplate

Single-slice L1 upper endplate

Muscle

R2

0.94

0.92

0.92

0.91

0.90

0.92

RMSE (L)

1.34

1.51

1.53

1.57

1.67

1.46

MAE (L)

1.03

1.07

1.09

1.10

1.20

1.05

Calibration-in-the-large (L)

0.11 (− 0.61, 0.82)

0.09 (− 0.70, 0.89)

0.15 (− 0.66, 0.96)

− 0.02 (− 0.86, 0.83)

0.02 (− 0.89, 0.92)

− 0.10 (− 0.89, 0.69)

Calibration slope

1.00 (0.96, 1.03)

1.00 (0.96, 1.04)

0.99 (0.96, 1.03)

1.00 (0.96, 1.04)

1.00 (0.96, 1.05)

1.01 (0.97, 1.05)

Visceral fat

R2

0.96

0.94

0.94

0.92

0.87

0.91

RMSE (L)

0.38

0.45

0.42

0.49

0.65

0.54

MAE (L)

0.26

0.32

0.30

0.34

0.44

0.38

Calibration-in-the-large (L)

− 0.01 (− 0.11, 0.08)

− 0.10 (− 0.21, 0.02)

− 0.08 (− 0.19, 0.03)

− 0.03 (− 0.16, 0.09)

0.06 (− 0.11, 0.24)

− 0.08 (− 0.22, 0.07)

Calibration slope

1.01 (0.98, 1.04)

1.05 (1.01, 1.09)

1.04 (1.01, 1.08)

1.03 (0.99, 1.06)

1.00 (0.95, 1.05)

1.05 (1.01, 1.09)

Subcutaneous fat

R2

0.89

0.87

0.86

0.90

0.89

0.89

RMSE (L)

1.97

2.07

2.15

1.87

1.94

1.96

MAE (L)

1.45

1.54

1.60

1.42

1.47

1.49

Calibration-in-the-large (L)

0.86 (0.09, 1.62)

0.89 (0.09, 1.70)

0.99 (0.15, 1.83)

0.51 (− 0.23, 1.25)

0.55 (− 0.22, 1.32)

0.54 (− 0.24, 1.32)

Calibration slope

0.95 (0.91, 1.00)

0.95 (0.90, 1.00)

0.94 (0.90, 0.99)

0.97 (0.93, 1.02)

0.97 (0.93, 1.02)

0.97 (0.93, 1.02)

  1. RMSE Root-mean-squared error, MAE Mean absolute error
  2. Data in parentheses indicate 95% confidence intervals