Systematic Evaluation of Machine Learning Algorithms for Neuroanatomically-Based Age Prediction in Youth

Abstract

Application of machine learning algorithms to structural magnetic resonance imaging (sMRI) data has yielded behaviorally meaningful estimates of the biological age of the brain (brain-age). The choice of the machine learning approach in estimating brain-age in children and adolescents is important because age-related brain changes in these age-groups are dynamic. However, the comparative performance of the multiple machine learning algorithms available has not been systematically appraised. To address this gap, the present study evaluated the accuracy (Mean Absolute Error; MAE) and computational efficiency of 21 machine learning algorithms using sMRI data from 2,105 typically developing individuals aged 5 to 22 years from five cohorts. The trained models were then tested in two independent holdout datasets, comprising 4,078 pre-adolescents aged 9-10 years and another sample of 594 individuals aged 5-21 years. The algorithms encompassed parametric and nonparametric, Bayesian, linear and nonlinear, tree-based, and kernel-based models. Sensitivity analyses were performed for parcellation scheme, number of neuroimaging input features, number of cross-validation folds, number of extreme outliers, and sample size. The best performing algorithms were Extreme Gradient Boosting (MAE of 1.49), Random Forest Regression (MAE of 1.58) and Support Vector Regression with Radial Basis Function Kernel (MAE of 1.64) which had acceptable and comparable computational efficiency. Findings of the present study could be used as a guide for optimizing methodology when quantifying age-related changes in youth.