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

Abstract

Modelling and predicting individual differences in task-evoked 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 leaner, 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 tfMRI scans, suggesting that it has potential to supplement traditional task localisers.

Act Natural: Functional Connectivity from Naturalistic Stimuli fMRI Outperforms Resting-State in Predicting Brain Activity

“…In efforts to improve the prediction of human behavior and brain activity from functional connectivity, most research to date focuses on model enhancement. This includes exploring different machine-learning algorithms and testing different model parameters (Ngo, Khosla, Jamison, Kuceyeski, & Sabuncu, 2021;Zheng et al, 2021). Here, we take an alternative data-centric approach and focus on enhancing the features rather than the model.…”

An atlas of trait associations with resting-state and task-evoked human brain functional architectures in the UK Biobank

“…Understanding how the brain changes its functionality in response to tasks/stimuli is of great interest and has a wide range of clinical applications 25 . For example, fMRI studies with an emotional task consistently showed abnormalities in the prefrontal cortex-limbic area in patients with anxiety disorders, who tend to overreact to emotional stimuli 26 .…”