Accurate predictions of individual differences in task-evoked brain activity from resting-state fMRI using a sparse ensemble learner.

• We propose an approach to accurately predict individual variability of task-evoked brain activity. • Prediction accuracy is on par with the repeat task-fMRI (tfMRI) scans, both on the Human Connectome Project and the UK Biobank datasets. • The shape and overall intensity of individual tfMRI activations can be modelled separately and explicitly. • Training on residuals improves prediction of individual-unique features in tfMRI activations. Modelling and predicting individual differences in task-fMRI activity can have a wide range of applications from basic to clinical neuroscience. It has been shown that models based on resting-state activity can have high predictive accuracy. Here we propose several improvements to such models. Using a sparse ensemble learner, we show that (i) features extracted using Stochastic Probabilistic Functional Modes (sPROFUMO) outperform the previously proposed dual-regression approach, (ii) that the shape and overall intensity of individualised task activations can be modelled separately and explicitly, (iii) training the model on predicting residual differences in brain activity further boosts individualised predictions. These results hold for both surface-based analyses of the Human Connectome Project data as well as volumetric analyses of UK-biobank data. Overall, our model achieves state of the art prediction accuracy on par with the test-retest reliability of task-fMRI scans, suggesting that it has potential to supplement traditional task localisers. [ABSTRACT FROM AUTHOR]