Brain-age prediction using shallow machine learning: Predictive Analytics Competition 2019

TY - JOUR

T1 - Brain-age prediction using shallow machine learning: Predictive Analytics Competition 2019

AU - Lopez Pinaya, Walter

AU - Dafflon, Jessica

AU - Carvalho De Paula Ferreira da Costa, Pedro Ferreira Da Costa

PY - 2020/12/2

Y1 - 2020/12/2

N2 - As we age, our brain structure changes and our cognitive capabilities decline. Although brain ageing is universal, rates of brain ageing differ markedly, which can be associated with pathological mechanism of psychiatric and neurological diseases. Predictive models have been applied to neuroimaging data to learn patterns associated with this variability and develop a neuroimaging biomarker of the brain condition. Aiming to stimulate the development of more accurate brain-age predictors, the Predictive Analytics Competition (PAC) 2019 provided a challenge that included a dataset of 2640 participants.Here, we present our approach which placed between the top 10 of the challenge. We developed an ensemble of shallow machine learning methods (e.g., Support Vector Regression and Decision Tree-based regressors) that combined voxel-based and surface-based morphometric data. We used normalised brain volume maps (i.e., grey matter, white matter, or both) and features of cortical regions and anatomical structures, like cortical thickness, volume, and mean curvature. In order to fine-tune the hyperparameters of the machine learning methods, we combined the use of genetic algorithms and grid search. Our ensemble had a mean absolute error of 3.7597 years on the competition, showing the potential that shallow methods still have in predicting brain-age.

AB - As we age, our brain structure changes and our cognitive capabilities decline. Although brain ageing is universal, rates of brain ageing differ markedly, which can be associated with pathological mechanism of psychiatric and neurological diseases. Predictive models have been applied to neuroimaging data to learn patterns associated with this variability and develop a neuroimaging biomarker of the brain condition. Aiming to stimulate the development of more accurate brain-age predictors, the Predictive Analytics Competition (PAC) 2019 provided a challenge that included a dataset of 2640 participants.Here, we present our approach which placed between the top 10 of the challenge. We developed an ensemble of shallow machine learning methods (e.g., Support Vector Regression and Decision Tree-based regressors) that combined voxel-based and surface-based morphometric data. We used normalised brain volume maps (i.e., grey matter, white matter, or both) and features of cortical regions and anatomical structures, like cortical thickness, volume, and mean curvature. In order to fine-tune the hyperparameters of the machine learning methods, we combined the use of genetic algorithms and grid search. Our ensemble had a mean absolute error of 3.7597 years on the competition, showing the potential that shallow methods still have in predicting brain-age.

U2 - 10.3389/fpsyt.2020.604478

DO - 10.3389/fpsyt.2020.604478

M3 - Article

SN - 1664-1078

VL - 11

JO - Frontiers in Psychology

JF - Frontiers in Psychology

M1 - 604478

ER -