Predicting Attentional Vulnerability to Sleep Deprivation: A Multivariate Pattern Analysis of DTI Data

Abstract

Background Large individual differences exist in sleep deprivation (SD) induced sustained attention deterioration. Several brain imaging studies have suggested that the activities within frontal-parietal network, cortico-thalamic connections, and inter-hemispheric connectivity might underlie the neural correlates of vulnerability/resistance to SD. However, those traditional approaches are based on average estimates of differences at the group level. Currently, a neuroimaging marker that can reliably predict this vulnerability at the individual level is lacking. Methods Efficient transfer of information relies on the integrity of white matter (WM) tracts in the human brain, we therefore applied machine learning approach to investigate whether the WM diffusion metrics can predict vulnerability to SD. Forty-nine participants completed the psychomotor vigilance task (PVT) both after resting wakefulness (RW) and after 24 h of sleep deprivation (SD). The number of PVT lapse (reaction time > 500 ms) was calculated for both RW condition and SD condition and participants were categorized as vulnerable (24 participants) or resistant (25 participants) to SD according to the change in the number of PVT lapses between the two conditions. Diffusion tensor imaging were acquired to extract four multitype WM features at a regional level: fractional anisotropy, mean diffusivity, axial diffusivity, and radial diffusivity. A linear support vector machine (LSVM) learning approach using leave-one-out cross-validation (LOOCV) was performed to assess the discriminative power of WM features in SD-vulnerable and SD-resistant participants. Results LSVM analysis achieved a correct classification rate of 83.67% (sensitivity: 87.50%; specificity: 80.00%; and area under the receiver operating characteristic curve: 0.85) for differentiating SD-vulnerable from SD-resistant participants. WM fiber tracts that contributed most to the classification model were primarily commissural pathways (superior longitudinal fasciculus), projection pathways (posterior corona radiata, anterior limb of internal capsule) and association pathways (body and genu of corpus callosum). Furthermore, we found a significantly negative correlation between changes in PVT lapses and the LSVM decision value. Conclusion These findings suggest that WM fibers connecting (1) regions within frontal-parietal attention network, (2) the thalamus to the prefrontal cortex, and (3) the left and right hemispheres contributed the most to classification accuracy.

White matter structural topologic efficiency predicts individual resistance to sleep deprivation

“…Widespread connection differences were found in several large white matter structures and short‐range connections including the brain cortex and the basal ganglia, cingulate, and thalamus regions. Our findings were consistent with emerging evidence of structural network abnormalities in SD‐vulnerable individuals, especially for the white matter connections within the frontal–parietal attention network, and the thalamus to prefrontal cortex 9,42,43 …”

“…Our findings were consistent with emerging evidence of structural network abnormalities in SD-vulnerable individuals, especially for the white matter connections within the frontal-parietal attention network, and the thalamus to prefrontal cortex. 9,42,43 Similar hub distributions were found in both groups. However, hubs in the right orbital superior frontal gyrus and cuneus were only found in the resistant group.…”

Altered isotropic volume fraction in gray matter after sleep deprivation and its association with visuospatial memory: A neurite orientation dispersion and density imaging study

“…Diffusion magnetic resonance imaging (dMRI) is a non-invasive approach that measures the diffusion of water molecules in tissue, providing information about the underlying brain microstructure ( Pierpaoli et al, 1996 ). In recent years, many studies have used dMRI to investigate the effect of SD on brain microstructure ( Rocklage et al, 2009 ; Cui et al, 2015 ; Elvsashagen et al, 2015 ; Zhu et al, 2017 ; Voldsbekk et al, 2021 ; Wang et al, 2022 ). For instance, one diffusion tensor imaging (DTI) study found that SD was associated with impaired white matter (WM) integrity [as reflected by reduced fractional anisotropy (FA)] of the bilateral frontotemporal and parieto-occipital tracts, corpus callosum, thalamus, and brain stem ( Elvsashagen et al, 2015 ).…”

“…For instance, one diffusion tensor imaging (DTI) study found that SD was associated with impaired white matter (WM) integrity [as reflected by reduced fractional anisotropy (FA)] of the bilateral frontotemporal and parieto-occipital tracts, corpus callosum, thalamus, and brain stem ( Elvsashagen et al, 2015 ). In addition, several DTI studies have reported that WM microstructural properties enable the prediction of cognitive vulnerability to SD ( Rocklage et al, 2009 ; Wang et al, 2022 ). Moreover, the individual’s cognitive stability/resistance to SD is associated with the integrity of the WM tract, which connects the frontoparietal attention networks ( Cui et al, 2015 ; Zhu et al, 2017 ).…”

“…NODDI has been used to explore brain microstructural alterations in several physiological and pathological conditions, such as brain development ( Zhao et al, 2021 ), aging ( Merluzzi et al, 2016 ), Parkinsonism ( Mitchell et al, 2019 ), and Wilson disease ( Song et al, 2018 ). Nevertheless, previous DTI and SMT studies have focused solely on WM microstructural changes after SD ( Rocklage et al, 2009 ; Cui et al, 2015 ; Elvsashagen et al, 2015 ; Zhu et al, 2017 ; Voldsbekk et al, 2021 ; Wang et al, 2022 ), and the effect of SD on GM microstructure remains unclear.…”