Dataset Information

Decoding subject-driven cognitive states with whole-brain connectivity patterns.

ABSTRACT: Decoding specific cognitive states from brain activity constitutes a major goal of neuroscience. Previous studies of brain-state classification have focused largely on decoding brief, discrete events and have required the timing of these events to be known. To date, methods for decoding more continuous and purely subject-driven cognitive states have not been available. Here, we demonstrate that free-streaming subject-driven cognitive states can be decoded using a novel whole-brain functional connectivity analysis. Ninety functional regions of interest (ROIs) were defined across 14 large-scale resting-state brain networks to generate a 3960 cell matrix reflecting whole-brain connectivity. We trained a classifier to identify specific patterns of whole-brain connectivity as subjects rested quietly, remembered the events of their day, subtracted numbers, or (silently) sang lyrics. In a leave-one-out cross-validation, the classifier identified these 4 cognitive states with 84% accuracy. More critically, the classifier achieved 85% accuracy when identifying these states in a second, independent cohort of subjects. Classification accuracy remained high with imaging runs as short as 30-60 s. At all temporal intervals assessed, the 90 functionally defined ROIs outperformed a set of 112 commonly used structural ROIs in classifying cognitive states. This approach should enable decoding a myriad of subject-driven cognitive states from brief imaging data samples.

SUBMITTER: Shirer WR

PROVIDER: S-EPMC3236795 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Objectives: Although it is widely observed that chronic insomnia disorder (CID) is associated with cognitive impairment, the neurobiological mechanisms underlying this remain unclear. Prior neuroimaging studies have confirmed that a close correlation exists between functional connectivity and cognitive impairment. Based on this observation, in this study we used resting-state functional magnetic resonance imaging (rs-fMRI) to study the relationship between whole brain functional connectivity and cognitive function in CID. Methods: We included 39 patients with CID and 28 age-, gender-, and education-matched healthy controls (HC). Abnormalities in functional connectivity were identified by comparing the correlation coefficients for each pair of 116 brain regions between CID and HC. Results: Cognitive impairment was associated with reduced subjective insomnia scores after controlling for age, gender, and educational effects. Compared with HC, patients with CID had larger negative correlations within the task-negative network [medial prefrontal cortex (mPFC), precuneus, inferior temporal gyrus, cerebellum, and superior parietal gyrus], and between two intrinsic anti-correlation networks (mPFC and middle temporal gyrus; supplementary motor area and cerebellum). Patients with CID also had decreased positive correlations within the default mode network (DMN), and between the cerebellum and DMN, which mainly comprises the mPFC and posterior cingulated cortex. There were positive correlations of decreased positive connectivity with subjective sleep scores and MMSE scores, and increased negative correlations between the task-negative-network and MMSE scores in CID. Conclusions: Using rs-fMRI, our results support previous observations of cortical disconnection in CID in the prefrontal and DMN networks. Moreover, abnormal correlations within the task-negative network, and between two intrinsically anti-correlation networks, might be important neurobiological indicators of CID and associated cognitive impairment.

Project description:Patients with mild cognitive impairment (MCI) are at high risk for developing Alzheimer's disease (AD), while some of them may remain stable over decades. The underlying mechanism is still not fully understood. In this study, we aimed to explore the connectivity differences between progressive MCI (PMCI) and stable MCI (SMCI) individuals on a whole-brain scale and on a voxel-wise basis, and we also aimed to reveal the differential dynamic alteration patterns between these two disease subtypes. The resting-state functional magnetic resonance images of PMCI and SMCI patients at baseline and year-one were obtained from the Alzheimer's Disease Neuroimaging Initiative dataset, and the progression was determined based on a 3-year follow-up. A whole-brain voxel-wise degree map that was calculated based on graph-theory was constructed for each subject, and then the cross-sectional and longitudinal analyses on the degree maps were performed between PMCI and SMCI patients. In longitudinal analyses, compared with SMCI group, PMCI group showed decreased long-range degree in the left middle occipital/supramarginal gyrus, while the short-range degree was increased in the left supplementary motor area and middle frontal gyrus and decreased in the right middle temporal pole. A significant longitudinal alteration of decreased short-range degree in the right middle occipital was found in PMCI group. Taken together with previous evidence, our current findings may suggest that PMCI, compared with SMCI, might be a "severe" presentation of disease along the AD continuum, and the rapidly reduced degree in the right middle occipital gyrus may have indicative value for the disease progression. Moreover, the cross-sectional comparison results and corresponding receiver-operator characteristic-curves analyses may indicate that the baseline degree difference is not a good predictor of disease progression in MCI patients. Overall, these findings may provide objective evidence and an indicator to characterize the progression-related brain connectivity changes in MCI patients.

Dataset Information

Decoding subject-driven cognitive states with whole-brain connectivity patterns.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets