Brain Age Prediction: Cortical and Subcortical Shape Covariation in the Developing Human Brain

Abstract

Cortical development is characterized by distinct spatial and temporal patterns of maturational changes across various cortical shape measures. There is a growing interest in summarizing complex developmental patterns into a single index, which can be used to characterize an individual's brain age. We conducted this study with two primary aims. First, we sought to quantify covariation patterns for a variety of cortical shape measures, including cortical thickness, gray matter volume, surface area, mean curvature, and travel depth, as well as white matter volume, and subcortical gray matter volume. We examined these measures in a sample of 869 participants aged 5-18 from the Healthy Brain Network (HBN) neurodevelopmental cohort using the Joint and Individual Variation Explained (Lock et al., 2013) method. We validated our results in an independent dataset from the Nathan Kline Institute -Rockland Sample (NKI-RS; N=210) and found remarkable consistency for some covariation patterns.Second, we assessed whether covariation patterns in the brain can be used to accurately predict a person's chronological age. Using ridge regression, we showed that covariation patterns can predict chronological age with high accuracy, reflected by our ability to crossvalidate our model in an independent sample with a correlation coefficient of 0.84 between chronologic and predicted age. These covariation patterns also predicted sex with high accuracy (AUC=0.85), and explained a substantial portion of variation in full scale intelligence quotient (R 2 =0.10). In summary, we found significant covariation across different cortical shape measures and subcortical gray matter volumes. In addition, each shape measure exhibited distinct covariations that could not be accounted for by other shape measures. These covariation patterns accurately predicted chronological age, sex and general cognitive ability. In a subset of NKI-RS, test-retest (<1 month apart, N=120) and longitudinal scans (1.22 ± 0.29 years apart, N=77) were available, allowing us to demonstrate high reliability for the prediction models obtained and the ability to detect subtle differences in the longitudinal scan interval among participants (median and median absolute deviation of absolute differences between predicted age difference and real age difference = 0.53 ± 0.47 years, r=0.24, p-value=0.04).

Brain Anatomical Covariation Patterns Linked to Binge Drinking and Age at First Full Drink Prior to 21 Years

“…Other methods, such as structural learning and integrative decomposition of multi-view data (47), common orthogonal basis extraction (48), and group factor analysis (49), may also be used. Our results suggest that an attractive feature of JIVE is the performance robustness, consistent with our prior study of brain age prediction (20).…”

“…In contrast, JIVE summarizes structural covariation patterns across multiple morphological measures into different component scores. Since brain structures with larger loading magnitudes in a JIVE component are generally more correlated than those with smaller loading magnitudes in the same component (20), the JIVE component scores may provide insight into the extent of synchronized development across brain regions and morphological measures at individual levels. Indeed, our prior work has shown that JIVE can be used to integrate multiple morphological measures into joint and specific components that can robustly predict brain age (20).…”

“…Since brain structures with larger loading magnitudes in a JIVE component are generally more correlated than those with smaller loading magnitudes in the same component (20), the JIVE component scores may provide insight into the extent of synchronized development across brain regions and morphological measures at individual levels. Indeed, our prior work has shown that JIVE can be used to integrate multiple morphological measures into joint and specific components that can robustly predict brain age (20). In short, JIVE analysis may help reveal information at the brain network level, not only providing an efficient data reduction, but also indicating potentially interacting neural circuits.…”

Toward Neurosubtypes in Autism

“…These two techniques have yet to be utilized in neurosubtyping but recent neuroimaging studies support their utility in predicting brain age or brain relationship with demographics and behavior (95,96), as well as of extracting a low-dimensional representation of depression-related connectivity (97).…”

Brain age prediction in schizophrenia: does the choice of machine learning algorithm matter?

“…20 Using random forest regression trained on data from 50 healthy individuals, Shahab and colleagues showed that patients with schizophrenia (n=81) had a mean brainPAD of 7.8 years. 21 Other regression algorithms commonly used to estimate brain-age in neuropsychiatric conditions include ordinary least squares (OLS) regression, 22,23 least absolute shrinkage and selection operator regression (Lasso), 24,25 ridge regression, 26,27 and elastic-net regression. 28 At present, it is unclear whether the performance of these machine learning approaches is comparable when estimating brainPAD.…”