Skip to main content

Table 1 Predictive performance metrics of five brain age algorithms (brainageR, DeepBrainNet, XGBoost, ENIGMA, pyment) across three motion conditions (no motion, low motion, high motion)

From: Examining the reliability of brain age algorithms under varying degrees of participant motion

Predictive metrics (comparing chronological age and brain age)

Algorithms

 

No motion

Low motion

High motion

brainageR

MAE

4.043

5.316

7.236

 

RMSE

5.128

7.150

9.535

DeepBrainNet

MAE

3.497

3.937

4.019

 

RMSE

4.629

5.121

5.230

XGBoost

MAE

6.927

7.642

9.021

 

RMSE

9.025

9.647

10.757

ENIGMA

MAE

9.967

10.827

11.549

 

RMSE

12.145

12.459

13.535

pyment

MAE

3.139

3.310

3.326

 

RMSE

4.102

4.143

4.073

  1. Performance was evaluated by mean absolute error (MAE) and root mean squared error (RMSE) between algorithm predicted brain age and chronological age