Cortical and subcortical brain networks predict prevailing heart rate.

Resting heart rate may confer risk for cardiovascular disease (CVD) and other adverse cardiovascular events. While the brainstem's autonomic control over heart rate is well established, less is known about the regulatory role of higher level cortical and subcortical brain regions, especially in humans. This study sought to characterize the brain networks that predict variation in prevailing heart rate in otherwise healthy adults. We used machine learning approaches designed for complex, high-dimensional data sets, to predict variation in instantaneous heart period (the inter-heartbeat-interval) from whole-brain hemodynamic signals measured by fMRI. Task-based and resting-state fMRI, as well as peripheral physiological recordings, were taken from two data sets that included extensive repeated measurements within individuals. Our models reliably predicted instantaneous heart period from whole-brain fMRI data both within and across individuals, with prediction accuracies being highest when measured within-participants. We found that a network of cortical and subcortical brain regions, many linked to visceral motor and visceral sensory processes, were reliable predictors of variation in heart period. This adds to evidence on brain-heart interactions and constitutes an incremental step toward developing clinically applicable biomarkers of brain contributions to CVD risk.

Similarity in evoked responses does not imply similarity in macroscopic network states.

It is commonplace in neuroscience to assume that if two tasks activate the same brain areas in the same way, then they are recruiting the same underlying networks. Yet computational theory has shown that the same pattern of activity can emerge from many different underlying network representations. Here we evaluated whether similarity in activation necessarily implies similarity in network architecture by comparing region-wise activation patterns and functional correlation profiles from a large sample of healthy subjects (N = 242). Participants performed two executive control tasks known to recruit nearly identical brain areas, the color-word Stroop task and the Multi-Source Interference Task (MSIT). Using a measure of instantaneous functional correlations, based on edge time series, we estimated the task-related networks that differed between incongruent and congruent conditions. We found that the two tasks were much more different in their network profiles than in their evoked activity patterns at different analytical levels, as well as for a wide range of methodological pipelines. Our results reject the notion that having the same activation patterns means two tasks engage the same underlying representations, suggesting that task representations should be independently evaluated at both node and edge (connectivity) levels.

As a dynamical system, the brain can encode information at the module (e.g., brain regions) or the network level (e.g., connections between brain regions). This means that two tasks can produce the same pattern of activation, but differ in their network profile. Here we tested this using two tasks with largely similar cognitive requirements. Despite producing nearly identical macroscopic activation patterns, the two tasks produced different functional network profiles. These findings confirm prior theoretical work that similarity in task activation does not imply the same similarity in underlying network states.

Cortical and subcortical brain networks predict prevailing heart rate.

Resting heart rate may confer risk for cardiovascular disease (CVD) and other adverse cardiovascular events. While the brainstem's autonomic control over heart rate is well established, less is known about the regulatory role of higher-level cortical and subcortical brain regions, especially in humans. The present study sought to characterize the brain networks that predict variation in prevailing heart rate in otherwise healthy adults. We used machine learning approaches designed for complex, high-dimensional datasets, to predict variation in instantaneous heart period (the inter-heartbeat-interval) from whole brain hemodynamic signals measured by fMRI. Task-based and resting-state fMRI, as well as peripheral physiological recordings, were taken from two datasets that included extensive repeated measurements within individuals. Our models reliably predicted instantaneous heart period from whole brain fMRI data both within and across individuals, with prediction accuracies being highest when measured within-participants. We found that a network of cortical and subcortical brain regions, many linked to psychological stress, were reliable predictors of variation in heart period. This adds to evidence on brain-heart interactions and constitutes an incremental step towards developing clinically-applicable biomarkers of brain contributions to CVD risk.

Integrating multiple brain imaging modalities does not boost prediction of subclinical atherosclerosis in midlife adults.

BACKGROUND: Human neuroimaging evidence suggests that cardiovascular disease (CVD) risk may relate to functional and structural features of the brain. The present study tested whether combining functional and structural (multimodal) brain measures, derived from magnetic resonance imaging (MRI), would yield a multivariate brain biomarker that reliably predicts a subclinical marker of CVD risk, carotid-artery intima-media thickness (CA-IMT). METHODS: Neuroimaging, cardiovascular, and demographic data were assessed in 324 midlife and otherwise healthy adults who were free of (a) clinical CVD and (b) use of medications for chronic illnesses (aged 30-51 years, 49% female). We implemented a prediction stacking algorithm that combined multimodal brain imaging measures and Framingham Risk Scores (FRS) to predict CA-IMT. We included imaging measures that could be easily obtained in clinical settings: resting state functional connectivity and structural morphology measures from T1-weighted images. RESULTS: Our models reliably predicted CA-IMT using FRS, as well as for several individual MRI measures; however, none of the individual MRI measures outperformed FRS. Moreover, stacking functional and structural brain measures with FRS did not boost prediction accuracy above that of FRS alone. CONCLUSIONS: Combining multimodal functional and structural brain measures through a stacking algorithm does not appear to yield a reliable brain biomarker of subclinical CVD, as reflected by CA-IMT.

Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability.

Variation in cognitive ability arises from subtle differences in underlying neural architecture. Understanding and predicting individual variability in cognition from the differences in brain networks requires harnessing the unique variance captured by different neuroimaging modalities. Here we adopted a multi-level machine learning approach that combines diffusion, functional, and structural MRI data from the Human Connectome Project (N = 1050) to provide unitary prediction models of various cognitive abilities: global cognitive function, fluid intelligence, crystallized intelligence, impulsivity, spatial orientation, verbal episodic memory and sustained attention. Out-of-sample predictions of each cognitive score were first generated using a sparsity-constrained principal component regression on individual neuroimaging modalities. These individual predictions were then aggregated and submitted to a LASSO estimator that removed redundant variability across channels. This stacked prediction led to a significant improvement in accuracy, relative to the best single modality predictions (approximately 1% to more than 3% boost in variance explained), across a majority of the cognitive abilities tested. Further analysis found that diffusion and brain surface properties contribute the most to the predictive power. Our findings establish a lower bound to predict individual differences in cognition using multiple neuroimaging measures of brain architecture, both structural and functional, quantify the relative predictive power of the different imaging modalities, and reveal how each modality provides unique and complementary information about individual differences in cognitive function.