Dataset Information

Detection of Mild Traumatic Brain Injury by Machine Learning Classification Using Resting State Functional Network Connectivity and Fractional Anisotropy.

ABSTRACT: Traumatic brain injury (TBI) may adversely affect a person's thinking, memory, personality, and behavior. While mild TBI (mTBI) diagnosis is challenging, there is a risk for long-term psychiatric, neurologic, and psychosocial problems in some patients that motivates the search for new and better biomarkers. Recently, diffusion magnetic resonance imaging (dMRI) has shown promise in detecting mTBI, but its validity is still being investigated. Resting state functional network connectivity (rsFNC) is another approach that is emerging as a promising option for the diagnosis of mTBI. The present work investigated the use of rsFNC for mTBI detection compared with dMRI results on the same cohort. Fifty patients with mTBI (25 males) and age-sex matched healthy controls were recruited. Features from dMRI were obtained using all voxels, the enhanced Z-score microstructural assessment for pathology, and the distribution corrected Z-score. Features based on rsFNC were obtained through group independent component analysis and correlation between pairs of resting state networks. A linear support vector machine was used for classification and validated using leave-one-out cross validation. Classification achieved a maximum accuracy of 84.1% for rsFNC and 75.5% for dMRI and 74.5% for both combined. A t test analysis revealed significant increase in rsFNC between cerebellum versus sensorimotor networks and between left angular gyrus versus precuneus in subjects with mTBI. These outcomes suggest that inclusion of both common and unique information is important for classification of mTBI. Results also suggest that rsFNC can yield viable biomarkers that might outperform dMRI and points to connectivity to the cerebellum as an important region for the detection of mTBI.

SUBMITTER: Vergara VM

PROVIDER: S-EPMC5333571 | biostudies-literature | 2017 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Detection of Mild Traumatic Brain Injury by Machine Learning Classification Using Resting State Functional Network Connectivity and Fractional Anisotropy.

Vergara Victor M VM Mayer Andrew R AR Damaraju Eswar E Kiehl Kent A KA Calhoun Vince V

Journal of neurotrauma 20161121 5

Traumatic brain injury (TBI) may adversely affect a person's thinking, memory, personality, and behavior. While mild TBI (mTBI) diagnosis is challenging, there is a risk for long-term psychiatric, neurologic, and psychosocial problems in some patients that motivates the search for new and better biomarkers. Recently, diffusion magnetic resonance imaging (dMRI) has shown promise in detecting mTBI, but its validity is still being investigated. Resting state functional network connectivity (rsFNC) ...[more]

PMID: 27676221

Similar Datasets

Project description:Mild traumatic brain injury (mTBI) is a major public health concern that can result in a broad spectrum of short-term and long-term symptoms. Recently, machine learning (ML) algorithms have been used in neuroscience research for diagnostics and prognostic assessment of brain disorders. The present study aimed to develop an automatic classifier to distinguish patients suffering from chronic mTBI from healthy controls (HCs) utilizing multilevel metrics of resting-state functional magnetic resonance imaging (rs-fMRI). Sixty mTBI patients and forty HCs were enrolled and allocated to training and testing datasets with a ratio of 80:20. Several rs-fMRI metrics including fractional amplitude of low-frequency fluctuation (fALFF), regional homogeneity (ReHo), degree centrality (DC), voxel-mirrored homotopic connectivity (VMHC), functional connectivity strength (FCS), and seed-based FC were generated from two main analytical categories: local measures and network measures. Statistical two-sample t-test was employed comparing between mTBI and HCs groups. Then, for each rs-fMRI metric the features were selected extracting the mean values from the clusters showing significant differences. Finally, the support vector machine (SVM) models based on separate and multilevel metrics were built and the performance of the classifiers were assessed using five-fold cross-validation and via the area under the receiver operating characteristic curve (AUC). Feature importance was estimated using Shapley additive explanation (SHAP) values. Among local measures, the range of AUC was 86.67-100% and the optimal SVM model was obtained based on combined multilevel rs-fMRI metrics and DC as a separate model with AUC of 100%. Among network measures, the range of AUC was 80.42-93.33% and the optimal SVM model was obtained based on the combined multilevel seed-based FC metrics. The SHAP analysis revealed the DC value in the left postcentral and seed-based FC value between the motor ventral network and right superior temporal as the most important local and network features with the greatest contribution to the classification models. Our findings demonstrated that different rs-fMRI metrics can provide complementary information for classifying patients suffering from chronic mTBI. Moreover, we showed that ML approach is a promising tool for detecting patients with mTBI and might serve as potential imaging biomarker to identify patients at individual level.Clinical trial registration[clinicaltrials.gov], identifier [NCT03241732].

Project description:IntroductionThe purpose of this study was to explore the effect of low testosterone level on whole-brain resting state (RS) connectivity in male veterans with symptoms such as sleep disturbance, fatiguability, pain, anxiety, irritability, or aggressiveness persisting after mild traumatic brain injury (mTBI). Follow-up analyses were performed to determine if sleep scores affected the results.Materials and methodsIn our cross-sectional design study, RS magnetic resonance imaging scans on 28 veterans were performed, and testosterone, sleep quality, mood, and post-traumatic stress symptoms were measured. For each participant, we computed the average correlation of each voxel's time-series with the rest of the voxels in the brain, then used AFNI's 3dttest++ on the group data to determine whether the effects of testosterone level on whole-brain connectivity were significant. We then performed follow-up region of interest-based RS analyses of testosterone, with and without sleep quality as a covariate. The study protocol was approved by the National Institute of Health's Combined Neuroscience Institutional Review Board.ResultsSixteen participants reported repeated blast exposure in theater, leading to symptoms; the rest reported exposure to a single blast or a nonblast TBI. Thirty-three percent had testosterone levels <300 ng/dL. Testosterone level was lower in participants who screened positive for post-traumatic stress disorder compared to those who screened negative, but it did not reach statistical significance. Whole-brain connectivity and testosterone level were positively correlated in the left parahippocampal gyrus (LPhG), especially in its connectivity with frontal areas, the lingual gyrus, cingulate, insula, caudate, and right parahippocampal gyrus. Further analysis revealed that the effect of testosterone on LPhG connectivity is only partially mediated by sleep quality. Sleep quality by itself had an effect on connectivity of the thalamus, cerebellum, precuneus, and posterior cingulate.ConclusionLower testosterone levels were correlated with lower connectivity of the LPhG. Weaknesses of this study include a retrospective design based on self-report of mTBI and the lack of a control group without TBI. Without a control group or pre-injury testosterone measures, we were not able to attribute the rate of low testosterone in our participants to TBI per se. Also testosterone levels were checked only once. The high rate of low testosterone level that we found suggests there may be an association between low testosterone level and greater post-traumatic stress disorder symptoms following deployment, but the causality of the relationships between TBI and deployment stress, testosterone level, behavioral symptomatology, and LPhG connectivity remains to be determined. Our study on men with persistent symptoms postdeployment and post-mTBI may help us understand the role of low testosterone and sleep quality in persistent symptoms and may be important in developing therapeutic interventions. Our results highlight the role of the LPhG, as we found that whole-brain connectivity in that region was positively associated with testosterone level, with only a limited portion of that effect attributable to sleep quality.

Project description:Whereas traumatic brain injury (TBI) results in widespread disruption of neural networks, changes in regional resting-state functional connectivity patterns after insult remain unclear. Specifically, little is known about the chronology of emergent connectivity alterations and whether they persist after a critical recovery window. We used resting-state functional magnetic resonance imaging and seed-voxel correlational analyses in both cross-sectional and longitudinal designs to probe intrinsic connectivity patterns involving the posterior cingulate cortex (PCC) and hippocampi, regions shown to be important in the default mode network (DMN) and vulnerable to neuropathology. A total of 22 participants in the chronic stage of moderate-to-severe TBI and 18 healthy controls were included for cross-sectional study. Longitudinal analyses included 13 individuals in the TBI group for whom data approximately 3 months after injury (subacute) were available. Overall, results indicated dissociable connectivity trajectories of the PCC and hippocampi during recovery from TBI, with PCC alterations characterized by early hypersynchrony with the anterior DMN that is gradually reduced, and hippocampal changes marked by increasing synchrony with proximal cortex and subcortex. The PCC also showed increasing antiphase synchrony with posterior attentional regions, and the hippocampi showed decreasing antiphase synchrony with frontal attentional regions. Antiphase synchrony of the hippocampus and dorsolateral prefrontal cortex at the subacute stage of TBI was positively associated with attentional performance on neuropsychological tests at both the subacute and chronic stages. Our findings highlight the heterogeneity of regional whole-brain connectivity changes after TBI, and suggest that residual connectivity alterations exist in the clinically stable phase of TBI. Parallels between the chronicity of the observed effects and findings in neurodegenerative disease are discussed in the context of potential long-term outcomes of TBI.

Dataset Information

Detection of Mild Traumatic Brain Injury by Machine Learning Classification Using Resting State Functional Network Connectivity and Fractional Anisotropy.

Publications

Detection of Mild Traumatic Brain Injury by Machine Learning Classification Using Resting State Functional Network Connectivity and Fractional Anisotropy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets