Resting-state magnetoencephalography source magnitude imaging with deep-learning neural network for classification of symptomatic combat-related mild traumatic brain injury.

Combat-related mild traumatic brain injury (cmTBI) is a leading cause of sustained physical, cognitive, emotional, and behavioral disabilities in Veterans and active-duty military personnel. Accurate diagnosis of cmTBI is challenging since the symptom spectrum is broad and conventional neuroimaging techniques are insensitive to the underlying neuropathology. The present study developed a novel deep-learning neural network method, 3D-MEGNET, and applied it to resting-state magnetoencephalography (rs-MEG) source-magnitude imaging data from 59 symptomatic cmTBI individuals and 42 combat-deployed healthy controls (HCs). Analytic models of individual frequency bands and all bands together were tested. The All-frequency model, which combined delta-theta (1-7 Hz), alpha (8-12 Hz), beta (15-30 Hz), and gamma (30-80 Hz) frequency bands, outperformed models based on individual bands. The optimized 3D-MEGNET method distinguished cmTBI individuals from HCs with excellent sensitivity (99.9 ± 0.38%) and specificity (98.9 ± 1.54%). Receiver-operator-characteristic curve analysis showed that diagnostic accuracy was 0.99. The gamma and delta-theta band models outperformed alpha and beta band models. Among cmTBI individuals, but not controls, hyper delta-theta and gamma-band activity correlated with lower performance on neuropsychological tests, whereas hypo alpha and beta-band activity also correlated with lower neuropsychological test performance. This study provides an integrated framework for condensing large source-imaging variable sets into optimal combinations of regions and frequencies with high diagnostic accuracy and cognitive relevance in cmTBI. The all-frequency model offered more discriminative power than each frequency-band model alone. This approach offers an effective path for optimal characterization of behaviorally relevant neuroimaging features in neurological and psychiatric disorders.

Marked Increases in Resting-State MEG Gamma-Band Activity in Combat-Related Mild Traumatic Brain Injury.

Combat-related mild traumatic brain injury (mTBI) is a leading cause of sustained impairments in military service members and veterans. Recent animal studies show that GABA-ergic parvalbumin-positive interneurons are susceptible to brain injury, with damage causing abnormal increases in spontaneous gamma-band (30-80 Hz) activity. We investigated spontaneous gamma activity in individuals with mTBI using high-resolution resting-state magnetoencephalography source imaging. Participants included 25 symptomatic individuals with chronic combat-related blast mTBI and 35 healthy controls with similar combat experiences. Compared with controls, gamma activity was markedly elevated in mTBI participants throughout frontal, parietal, temporal, and occipital cortices, whereas gamma activity was reduced in ventromedial prefrontal cortex. Across groups, greater gamma activity correlated with poorer performances on tests of executive functioning and visuospatial processing. Many neurocognitive associations, however, were partly driven by the higher incidence of mTBI participants with both higher gamma activity and poorer cognition, suggesting that expansive upregulation of gamma has negative repercussions for cognition particularly in mTBI. This is the first human study to demonstrate abnormal resting-state gamma activity in mTBI. These novel findings suggest the possibility that abnormal gamma activities may be a proxy for GABA-ergic interneuron dysfunction and a promising neuroimaging marker of insidious mild head injuries.

Detection of Chronic Blast-Related Mild Traumatic Brain Injury with Diffusion Tensor Imaging and Support Vector Machines.

Blast-related mild traumatic brain injury (bmTBI) often leads to long-term sequalae, but diagnostic approaches are lacking due to insufficient knowledge about the predominant pathophysiology. This study aimed to build a diagnostic model for future verification by applying machine-learning based support vector machine (SVM) modeling to diffusion tensor imaging (DTI) datasets to elucidate white-matter features that distinguish bmTBI from healthy controls (HC). Twenty subacute/chronic bmTBI and 19 HC combat-deployed personnel underwent DTI. Clinically relevant features for modeling were selected using tract-based analyses that identified group differences throughout white-matter tracts in five DTI metrics to elucidate the pathogenesis of injury. These features were then analyzed using SVM modeling with cross validation. Tract-based analyses revealed abnormally decreased radial diffusivity (RD), increased fractional anisotropy (FA) and axial/radial diffusivity ratio (AD/RD) in the bmTBI group, mostly in anterior tracts (29 features). SVM models showed that FA of the anterior/superior corona radiata and AD/RD of the corpus callosum and anterior limbs of the internal capsule (5 features) best distinguished bmTBI from HCs with 89% accuracy. This is the first application of SVM to identify prominent features of bmTBI solely based on DTI metrics in well-defined tracts, which if successfully validated could promote targeted treatment interventions.

Preinjury alcohol and drug use among persons with spinal cord injury: implications for rehabilitation.

CONTEXT/OBJECTIVE: To describe preinjury alcohol and drug use and opportunities for secondary prevention among persons with recent spinal cord injury (SCI). DESIGN: Survey. SETTING: Acute inpatient rehabilitation program. PARTICIPANTS: Participants were 118 (84.8%) of 139 consecutive admissions who met inclusion criteria and were screened for preinjury alcohol and drug use. INTERVENTIONS: None. OUTCOME MEASURES: Alcohol and drug use, toxicology results, alcohol problems, readiness to change, and treatment preferences. RESULTS: Participants were on average 37 years old, 84% were men, and 85% were white. Fifty-one percent of the sample was considered 'at-risk' drinkers. Significant lifetime alcohol-related problems were reported by 38% of the total sample. Thirty-three percent reported recent illicit drug use and 44% of the 82 cases with toxicology results were positive for illicit drugs. Seventy-one percent of at-risk drinkers reported either considering changes in alcohol use or already taking action. Forty-one percent reported interest in trying substance abuse treatment or Alcoholics Anonymous (AA). Motivation to change alcohol use was significantly and positively associated with self-reported indicators of alcohol problem severity. CONCLUSION: Preinjury alcohol and drug abuse are common among persons with recent SCI. Substance abuse screening is feasible and detects not only salient clinical problems but also significant motivation to change and interest in AA or treatment, all of which represent an important window of opportunity for appropriate brief interventions and referrals. In contrast with the idea that alcoholism is a 'disease of denial', the majority of at-risk drinkers with new onset SCI indicate they are considering making changes.

A typology of alcohol use patterns among persons with recent traumatic brain injury or spinal cord injury: implications for treatment matching.

OBJECTIVE: To describe empirically valid and clinically meaningful types of alcohol use among persons with recent traumatic brain or spinal cord injury. DESIGN: Cross-sectional cohort survey. SETTING: Acute inpatient rehabilitation program in a level I trauma center. PARTICIPANTS: A total of 218 (87%) of 250 consecutive initial admissions who met inclusion criteria and completed interviews. INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: Alcohol and drug use questionnaires, alcohol problem questions, admission toxicology results, readiness to change, and treatment preference questions. RESULTS: Participants were on average 37 years old, 84% were men, and 82% were white. Four types were identified by using k-means cluster analysis based on preinjury alcohol consumption, alcohol problems, and alcohol dependence. Cluster groups differed on extrinsic variables such as drug use, readiness to change, and interest in treatment or in attending Alcoholics Anonymous. The 4 types corresponded to those with a history of (1) alcohol abuse; (2) alcohol dependence; (3) alcohol dependence in remission, partial remission, or relapsed; and (4) normal or nondrinkers. CONCLUSION: More effective care may be possible if clinicians match common patient types to specific interventions such as education, motivational interventions, formal substance abuse treatment, and relapse prevention.

The magnitude and correlates of alcohol and drug use before traumatic brain injury.

OBJECTIVE: To describe preinjury alcohol and drug use and opportunities for secondary prevention among persons with recent traumatic brain injury (TBI). DESIGN: Survey. SETTING: Acute inpatient rehabilitation program. PARTICIPANTS: A total of 142 (91%) of 156 consecutive admissions who met inclusion criteria and were screened. INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURE: Alcohol and drug use questionnaires, alcohol problem questions, toxicology results, readiness to change, and treatment preference questions. RESULTS: Subjects were on average 37 years old, 80% were men, and 80% were white. Fifty-nine percent of the sample was considered "at-risk" drinkers and, as a group, subjects reported a high degree of preinjury alcohol-related problems. Thirty-four percent reported recent illicit drug use, and 42 (37%) of 114 cases with toxicology results were positive for illicit drugs. Motivation to change alcohol use correlated positively with greater self-reported alcohol consumption and problem severity. Most at-risk drinkers wanted to change on their own, whereas a minority were interested in treatment or Alcoholics Anonymous. CONCLUSION: Both alcohol abuse and drug use are common before TBI. Inpatient brain injury rehabilitation represents an important opportunity to identify and intervene in substance abuse problems.

Do preinjury alcohol problems predict poorer rehabilitation progress in persons with spinal cord injury?

OBJECTIVE: To determine whether a history of alcohol-related problems is associated with inpatient rehabilitation progress. DESIGN: Cross-sectional cohort survey. SETTING: Acute inpatient rehabilitation program in a level I trauma center. PARTICIPANTS: Seventy-six of 104 consecutive patients with spinal cord injury (SCI) who met inclusion criteria and had completed interviews and functional outcome data. Participants were on average 38 years old; 84% were white, and 86% were men. Forty-two percent had tetraplegia and 39% had a history of problem drinking. INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: FIM instrument admission, discharge, and efficiency scores as well as rehabilitation length of stay (LOS). RESULTS: The group with a history of problem drinking had significantly lower FIM admission, discharge, and efficiency scores and longer rehabilitation LOS. After controlling for potential confounding factors, a history of problem drinking accounted for a significant proportion of the variance in FIM efficiency scores. CONCLUSIONS: A history of problem drinking may be a risk factor for poorer rehabilitation progress among patients with SCI. They may be more costly to rehabilitate and may be discharged before attaining an adequate level of independence. Despite this, the current rehabilitation prospective payment system does not recognize this common comorbid condition.