Table 2.

Benchmarking analysis of different machine-learning algorithms regarding out-of-sample prediction from gray matter volumes.

	Pearson’s r	Explained Variance Score	Mean Absolute Error	Coefficient of Determination	Mean Squared Error
Ridge Regression	0.2334	0.0599	0.7967	0.0591	0.9421
Random Forest	0.2323	0.0613	0.8016	0.0601	0.9410
Gradient Boosting	0.2310	0.0603	0.8013	0.0591	0.9420
k-Nearest Neighbor	0.1223	0.0019	0.8233	-0.0012	1.0021
Kernel Ridge Regression	0.2256	0.0561	0.8011	0.0550	0.9461
Deep Learning	0.1911	0.0374	0.8080	0.0363	0.9648

(cf. Supplementary Table 11)