Statistical machine learning to identify traumatic brain injury (TBI) from structural disconnections of white matter networks

The recent two decades of traumatic brain injury: a bibliometric analysis and systematic review

BACKGROUND

Traumatic brain injury (TBI) is a serious public health burden worldwide, with a mortality rate of 20-30%; however, reducing the incidence and mortality rates of TBI remains a major challenge. This study provides a multidimensional analysis to explore the potential breakthroughs in TBI over the past two decades.

MATERIALS AND METHODS

The authors used bibliometric and Latent Dirichlet Allocation (LDA) analyses to analyze publications focusing on TBI published between 2003 and 2022 from the Web of Science Core Collection (WOSCC) database to identify core journals and collaborations among countries/regions, institutions, authors, and research trends.

RESULTS

Over the past 20 years, 41 545 articles on TBI from 3043 journals were included, with 12 916 authors from 20 449 institutions across 145 countries/regions. The annual number of publications has increased 10-fold compared to previous publications. This study revealed that high-income countries, especially the United States, have a significant influence. Collaboration was limited to several countries/regions. The LDA results indicated that the hotspots included four main areas: 'Clinical finding', 'Molecular mechanism', 'Epidemiology', and 'Prognosis'. Epidemiological research has consistently increased in recent years. Through epidemiological topic analysis, the main etiology of TBI has shifted from traffic accidents to falls in a demographically aging society.

CONCLUSION

Over the past two decades, TBI research has developed rapidly, and its epidemiology has received increasing attention. Reducing the incidence of TBI from a preventive perspective is emerging as a trend to alleviate the future social burden; therefore, epidemiological research might bring breakthroughs in TBI.

Identification and Connectomic Profiling of Concussion Using Bayesian Machine Learning

Accurate early diagnosis of concussion is useful to prevent sequelae and improve neurocognitive outcomes. Early after head impact, concussion diagnosis may be doubtful in persons whose neurological, neuroradiological, and/or neurocognitive examinations are equivocal. Such individuals can benefit from novel accurate assessments that complement clinical diagnostics. We introduce a Bayesian machine learning classifier to identify concussion through cortico-cortical connectome mapping from magnetic resonance imaging in persons with quasi-normal cognition and without neuroradiological findings. Classifier features are generated from connectivity matrices specifying the mean fractional anisotropy of white matter connections linking brain structures. Each connection's saliency to classification was quantified by training individual classifier instantiations using a single feature type. The classifier was tested on a discovery sample of 92 healthy controls (HCs; 26 females, age μ ± σ: 39.8 ± 15.5 years) and 471 adult mTBI patients (158 females, age μ ± σ: 38.4 ± 5.9 years). Results were replicated in an independent validation sample of 256 HCs (149 females, age μ ± σ: 55.3 ± 12.1 years) and 126 patients with concussion (46 females, age μ ± σ: 39.0 ± 17.7 years). Classifier accuracy exceeds 99% in both samples, suggesting robust generalizability to new samples. Notably, 13 bilateral cortico-cortical connection pairs predict diagnostic status with accuracy exceeding 99% in both discovery and validation samples. Many such connection pairs are between prefrontal cortex structures, fronto-limbic and fronto-subcortical structures, and occipito-temporal structures in the ventral ("what") visual stream. This and related connectivity form a highly salient network of brain connections that is particularly vulnerable to concussion. Because these connections are important in mediating cognitive control, memory, and attention, our findings explain the high frequency of cognitive disturbances after concussion. Our classifier was trained and validated on concussed participants with cognitive profiles very similar to those of HCs. This suggests that the classifier can complement current diagnostics by providing independent information in clinical contexts where patients have quasi-normal cognition but where concussion diagnosis stands to benefit from additional evidence.

Connectome-based schizophrenia prediction using structural connectivity - Deep Graph Neural Network(sc-DGNN)

BACKGROUND

Connectome is understanding the complex organization of the human brain's structural and functional connectivity is essential for gaining insights into cognitive processes and disorders.

OBJECTIVE

To improve the prediction accuracy of brain disorder issues, the current study investigates dysconnected subnetworks and graph structures associated with schizophrenia.

METHOD

By using the proposed structural connectivity-deep graph neural network (sc-DGNN) model and compared with machine learning (ML) and deep learning (DL) models.This work attempts to focus on eighty-eight subjects of diffusion magnetic resonance imaging (dMRI), three classical ML, and five DL models.

RESULT

The structural connectivity-deep graph neural network (sc-DGNN) model is proposed to effectively predict dysconnectedness associated with schizophrenia and exhibits superior performance compared to traditional ML and DL (GNNs) methods in terms of accuracy, sensitivity, specificity, precision, F1-score, and Area under receiver operating characteristic (AUC).

CONCLUSION

The classification task on schizophrenia using structural connectivity matrices and experimental results showed that linear discriminant analysis (LDA) performed 72% accuracy rate in ML models and sc-DGNN performed at a 93% accuracy rate in DL models to distinguish between schizophrenia and healthy patients.

Clinical performance of a multiparametric MRI-based post concussive syndrome index

Introduction

Diffusion Tensor Imaging (DTI) has revealed measurable changes in the brains of patients with persistent post-concussive syndrome (PCS). Because of inconsistent results in univariate DTI metrics among patients with mild traumatic brain injury (mTBI), there is currently no single objective and reliable MRI index for clinical decision-making in patients with PCS.

Purpose

This study aimed to evaluate the performance of a newly developed PCS Index (PCSI) derived from machine learning of multiparametric magnetic resonance imaging (MRI) data to classify and differentiate subjects with mTBI and PCS history from those without a history of mTBI.

Materials and methods

Data were retrospectively extracted from 139 patients aged between 18 and 60 years with PCS who underwent MRI examinations at 2 weeks to 1-year post-mTBI, as well as from 336 subjects without a history of head trauma. The performance of the PCS Index was assessed by comparing 69 patients with a clinical diagnosis of PCS with 264 control subjects. The PCSI values for patients with PCS were compared based on the mechanism of injury, time interval from injury to MRI examination, sex, history of prior concussion, loss of consciousness, and reported symptoms.

Results

Injured patients had a mean PCSI value of 0.57, compared to the control group, which had a mean PCSI value of 0.12 (p = 8.42e-23) with accuracy of 88%, sensitivity of 64%, and specificity of 95%, respectively. No statistically significant differences were found in the PCSI values when comparing the mechanism of injury, sex, or loss of consciousness.

Conclusion

The PCSI for individuals aged between 18 and 60 years was able to accurately identify patients with post-concussive injuries from 2 weeks to 1-year post-mTBI and differentiate them from the controls. The results of this study suggest that multiparametric MRI-based PCSI has great potential as an objective clinical tool to support the diagnosis, treatment, and follow-up care of patients with post-concussive syndrome. Further research is required to investigate the replicability of this method using other types of clinical MRI scanners.

Integrating unsupervised and supervised learning techniques to predict traumatic brain injury: A population-based study

This work aimed to identify pre-existing health conditions of patients with traumatic brain injury (TBI) and develop predictive models for the first TBI event and its external causes by employing a combination of unsupervised and supervised learning algorithms. We acquired up to five years of pre-injury diagnoses for 488,107 patients with TBI and 488,107 matched control patients who entered the emergency department or acute care hospitals between April 1st, 2002, and March 31st, 2020. Diagnoses were obtained from the Ontario Health Insurance Plan (OHIP) database which contains province-wide claims data by physicians in Ontario, Canada for inpatient and outpatient services. A screening process was conducted on the OHIP diagnostic codes to limit the subsequent analysis to codes that were predictive of TBI, which concluded that 314 codes were significantly associated with TBI. The Latent Dirichlet Allocation (LDA) model was applied to the diagnostic codes and generated an optimal number of 19 topics that concur with published literature but also suggest other unexplored areas. Estimated word-topic probabilities from the LDA model helped us detect pre-morbid conditions among patients with TBI by uncovering the underlying patterns of diagnoses, meanwhile estimated document-topic probabilities were utilized in variable creation as form of a dimension reduction. We created 19 topic scores for each patient in the cohort which were utilized along with socio-demographic factors for Random Forest binary classifier models. Test set performances evaluated using area under the receiver operating characteristic curve (AUC) were: TBI event (AUC = 0.85), external cause of injury: falls (AUC = 0.85), struck by/against (AUC = 0.83), cyclist collision (AUC = 0.76), motor vehicle collision (AUC = 0.83). Our analysis successfully demonstrated the feasibility of using machine learning to predict TBI due to various external causes and identified the most important factors that contribute to this prediction.

Safety and efficacy of simple training protocol in patients after mild traumatic brain injury

AIMS

Mild Traumatic Brain Injury (mTBI) is the most common type of craniocerebral injury. Proper management appears to be a key factor in preventing post-concussion syndrome. The aim of this prospective study was to evaluate the effect and safety of selected training protocol in patients after mTBI.

METHODS

This was a prospective study that included 25 patients with mTBI and 25 matched healthy controls. Assessments were performed in two sessions and included a post-concussion symptoms questionnaire, battery of neurocognitive tests, and magnetic resonance with tractography. Participants were divided into two groups: a passive subgroup with no specific recommendations and an active subgroup with simple physical and cognitive training.

RESULTS

The training program with slightly higher initial physical and cognitive loads was well tolerated and was harmless according to the noninferiority test. The tractography showed overall temporal posttraumatic changes in the brain. The predictive model was able to distinguish between patients and controls in the first (AUC=0.807) and second (AUC=0.652) sessions. In general, tractography had an overall predictive dominance of measures.

CONCLUSION

The results from our study objectively point to the safety of our chosen training protocol, simultaneously with the signs of slight benefits in specific cognitive domains. The study also showed the capability of machine learning and predictive models in mTBI patient recognition.

Enhanced Performance by Interpretable Low-Frequency Electroencephalogram Oscillations in the Machine Learning-Based Diagnosis of Post-traumatic Stress Disorder

Electroencephalography (EEG)-based diagnosis of psychiatric diseases using machine-learning approaches has made possible the objective diagnosis of various psychiatric diseases. The objective of this study was to improve the performance of a resting-state EEG-based computer-aided diagnosis (CAD) system to diagnose post-traumatic stress disorder (PTSD), by optimizing the frequency bands used to extract EEG features. We used eyes-closed resting-state EEG data recorded from 77 PTSD patients and 58 healthy controls (HC). Source-level power spectrum densities (PSDs) of the resting-state EEG data were extracted from 6 frequency bands (delta, theta, alpha, low-beta, high-beta, and gamma), and the PSD features of each frequency band and their combinations were independently used to discriminate PTSD and HC. The classification performance was evaluated using support vector machine with leave-one-out cross validation. The PSD features extracted from slower-frequency bands (delta and theta) showed significantly higher classification performance than those of relatively higher-frequency bands. The best classification performance was achieved when using delta PSD features (86.61%), which was significantly higher than that reported in a recent study by about 13%. The PSD features selected to obtain better classification performances could be explained from a neurophysiological point of view, demonstrating the promising potential to develop a clinically reliable EEG-based CAD system for PTSD diagnosis.

Mixture Model Framework for Traumatic Brain Injury Prognosis Using Heterogeneous Clinical and Outcome Data

Prognoses of Traumatic Brain Injury (TBI) outcomes are neither easily nor accurately determined from clinical indicators. This is due in part to the heterogeneity of damage inflicted to the brain, ultimately resulting in diverse and complex outcomes. Using a data-driven approach on many distinct data elements may be necessary to describe this large set of outcomes and thereby robustly depict the nuanced differences among TBI patients' recovery. In this work, we develop a method for modeling large heterogeneous data types relevant to TBI. Our approach is geared toward the probabilistic representation of mixed continuous and discrete variables with missing values. The model is trained on a dataset encompassing a variety of data types, including demographics, blood-based biomarkers, and imaging findings. In addition, it includes a set of clinical outcome assessments at 3, 6, and 12 months post-injury. The model is used to stratify patients into distinct groups in an unsupervised learning setting. We use the model to infer outcomes using input data, and show that the collection of input data reduces uncertainty of outcomes over a baseline approach. In addition, we quantify the performance of a likelihood scoring technique that can be used to self-evaluate the extrapolation risk of prognosis on unseen patients.

Post-concussive mTBI in Student Athletes: MRI Features and Machine Learning

Purpose: To determine and characterize the radiomics features from structural MRI (MPRAGE) and Diffusion Tensor Imaging (DTI) associated with the presence of mild traumatic brain injuries on student athletes with post-concussive syndrome (PCS).

Material and Methods: 122 student athletes (65 M, 57 F), median (IQR) age 18.8 (15–20) years, with a mixed level of play and sports activities, with a known history of concussion and clinical PCS, and 27 (15 M, 12 F), median (IQR) age 20 (19, 21) years, concussion free athlete subjects were MRI imaged in a clinical MR machine. MPRAGE and DTI-FA and DTI-ADC images were used to extract radiomic features from white and gray matter regions within the entire brain (2 ROI) and the eight main lobes of the brain (16 ROI) for a total of 18 analyzed regions. Radiomic features were divided into five different data sets used to train and cross-validate five different filter-based Support Vector Machines. The top selected features of the top model were described. Furthermore, the test predictions of the top four models were ensembled into a single average prediction. The average prediction was evaluated for the association to the number of concussions and time from injury.

Results: Ninety-one PCS subjects passed inclusion criteria (91 Cases, 27 controls). The average prediction of the top four models had a sensitivity of 0.80, 95% CI: [0.71, 0.88] and specificity of 0.74 95%CI [0.54, 0.89] for distinguishing subjects from controls. The white matter features were strongly associated with mTBI, while the whole-brain analysis of gray matter showed the worst association. The predictive index was significantly associated with the number of concussions (p < 0.0001) and associated with the time from injury (p < 0.01).

Conclusion: MRI Radiomic features are associated with a history of mTBI and they were successfully used to build a predictive machine learning model for mTBI for subjects with PCS associated with a history of one or more concussions.

Structural brain connectivity correlates with outcome in mild traumatic brain injury

We investigated the topology of structural brain connectivity networks and its association to outcome following mild traumatic brain injury, a major cause of permanent disability. Eighty-five patients with mild traumatic brain injury underwent MRI twice, about three weeks and eight months after injury, and 30 age-matched orthopedic trauma control subjects were scanned. Outcome was assessed with Extended Glasgow Outcome Scale on average eight months after injury. We performed constrained spherical deconvolution based probabilistic streamlines tractography on diffusion MRI data and parcellated cortical and subcortical gray matter into 84 regions based on T1-weighted data to reconstruct structural brain connectivity networks weighted by the number of streamlines. Graph theoretical methods were employed to measure network properties in both patients and controls, and correlations between these properties and outcome were calculated. We found no global differences in the network properties between patients with mild traumatic brain injury and orthopedic control subjects at either stage. However, we found significantly increased betweenness centrality of the right pars opercularis in the chronic stage compared to control subjects. Furthermore, both global and local network properties correlated significantly with outcome. Higher normalized global efficiency, degree, and strength as well as lower small-worldness were associated with better outcome. Correlations between the outcome and the local network properties were the most prominent in the left putamen and the left postcentral gyrus. Our results indicate that both global and local network properties provide valuable information about the outcome already in the acute/subacute stage, and therefore, are promising biomarkers for prognostic purposes in mild traumatic brain injury.

Combining Multiple Indices of Diffusion Tensor Imaging Can Better Differentiate Patients with Traumatic Brain Injury from Healthy Subjects

AIM

Diffuse axonal injury (DAI) is one of the most common pathological features of traumatic brain injury (TBI). Diffusion tensor imaging (DTI) indices can be used to identify and quantify white matter microstructural changes following DAI. Recently, many studies have used DTI with various machine learning approaches to predict white matter microstructural changes following TBI. The current study sought to examine whether our classification approach using multiple DTI indices in conjunction with machine learning is a useful tool for diagnosing/classifying TBI patients and healthy controls.

METHODS

Participants were adult patients with chronic TBI (n = 26) with DAI pathology, and age- and sex-matched healthy controls (n = 26). DTI images were obtained from all participants. Tract-based spatial statistics analyses were applied to DTI images. Classification models were built using principal component analysis and support vector machines. Receiver operator characteristic curve analysis and area under the curve were used to assess the classification performance of the different classifiers.

RESULTS

Tract-based spatial statistics revealed significantly decreased fractional anisotropy, as well as increased mean diffusivity, axial diffusivity, and radial diffusivity in patients with TBI compared with healthy controls (all p-values < 0.01). The principal component analysis and support vector machine-based machine learning classification using combined DTI indices classified patients with TBI and healthy controls with an accuracy of 90.5% with an area under the curve of 93 ± 0.09.

CONCLUSION

These results highlight the potential of our approach combining multiple DTI measures to identify patients with TBI.

Integrative Neuroinformatics for Precision Prognostication and Personalized Therapeutics in Moderate and Severe Traumatic Brain Injury

Despite changes in guideline-based management of moderate/severe traumatic brain injury (TBI) over the preceding decades, little impact on mortality and morbidity have been seen. This argues against the "one-treatment fits all" approach to such management strategies. With this, some preliminary advances in the area of personalized medicine in TBI care have displayed promising results. However, to continue transitioning toward individually-tailored care, we require integration of complex "-omics" data sets. The past few decades have seen dramatic increases in the volume of complex multi-modal data in moderate and severe TBI care. Such data includes serial high-fidelity multi-modal characterization of the cerebral physiome, serum/cerebrospinal fluid proteomics, admission genetic profiles, and serial advanced neuroimaging modalities. Integrating these complex and serially obtained data sets, with patient baseline demographics, treatment information and clinical outcomes over time, can be a daunting task for the treating clinician. Within this review, we highlight the current status of such multi-modal omics data sets in moderate/severe TBI, current limitations to the utilization of such data, and a potential path forward through employing integrative neuroinformatic approaches, which are applied in other neuropathologies. Such advances are positioned to facilitate the transition to precision prognostication and inform a top-down approach to the development of personalized therapeutics in moderate/severe TBI.

Recurrent neural network-based acute concussion classifier using raw resting state EEG data

Concussion is a global health concern. Despite its high prevalence, a sound understanding of the mechanisms underlying this type of diffuse brain injury remains elusive. It is, however, well established that concussions cause significant functional deficits; that children and youths are disproportionately affected and have longer recovery time than adults; and that individuals suffering from a concussion are more prone to experience additional concussions, with each successive injury increasing the risk of long term neurological and mental health complications. Currently, the most significant challenge in concussion management is the lack of objective, clinically- accepted, brain-based approaches for determining whether an athlete has suffered a concussion. Here, we report on our efforts to address this challenge. Specifically, we introduce a deep learning long short-term memory (LSTM)-based recurrent neural network that is able to distinguish between non-concussed and acute post-concussed adolescent athletes using only short (i.e. 90 s long) samples of resting state EEG data as input. The athletes were neither required to perform a specific task nor expected to respond to a stimulus during data collection. The acquired EEG data were neither filtered, cleaned of artefacts, nor subjected to explicit feature extraction. The LSTM network was trained and validated using data from 27 male, adolescent athletes with sports related concussion, benchmarked against 35 non-concussed adolescent athletes. During rigorous testing, the classifier consistently identified concussions with an accuracy of > 90% and achieved an ensemble median Area Under the Receiver Operating Characteristic Curve (ROC/AUC) equal to 0.971. This is the first instance of a high-performing classifier that relies only on easy-to-acquire resting state, raw EEG data. Our concussion classifier represents a promising first step towards the development of an easy-to-use, objective, brain-based, automatic classification of concussion at an individual level.

Topological Aberrance of Structural Brain Network Provides Quantitative Substrates of Post-Traumatic Brain Injury Attention Deficits in Children

Background: Traumatic brain injury (TBI)-induced attention deficits are among the most common long-term cognitive consequences in children. Most of the existing studies attempting to understand the neuropathological underpinnings of cognitive and behavioral impairments in TBI have utilized heterogeneous samples and resulted in inconsistent findings. The current research proposed to investigate topological properties of the structural brain network in children with TBI and their relationship with post-TBI attention problems in a more homogeneous subgroup of children who had severe post-TBI attention deficits (TBI-A). Materials and Methods: A total of 31 children with TBI-A and 35 group-matched controls were involved in the study. Diffusion tensor imaging-based probabilistic tractography and graph theoretical techniques were used to construct the structural brain network in each subject. Network topological properties were calculated in both global level and regional (nodal) level. Between-group comparisons among the topological network measures and analyses for searching brain-behavioral were all corrected for multiple comparisons using Bonferroni method. Results: Compared with controls, the TBI-A group showed significantly higher nodal local efficiency and nodal clustering coefficient in left inferior frontal gyrus and right transverse temporal gyrus, whereas significantly lower nodal clustering coefficient in left supramarginal gyrus and lower nodal local efficiency in left parahippocampal gyrus. The temporal lobe topological alterations were significantly associated with the post-TBI inattentive and hyperactive symptoms in the TBI-A group. Conclusion: The results suggest that TBI-related structural re-modularity in the white matter subnetworks associated with temporal lobe may play a critical role in the onset of severe post-TBI attention deficits in children. These findings provide valuable input for understanding the neurobiological substrates of post-TBI attention deficits, and have the potential to serve as quantitatively measurable criteria guiding the development of more timely and tailored strategies for diagnoses and treatments to the affected individuals. Impact statement This study provides a new insight into the neurobiological substrates associated with post-traumatic brain injury attention deficits (TBI-A) in children, by evaluating topological alterations of the structural brain network. The results demonstrated that relative to group-matched controls, the children with TBI-A had significantly altered nodal local efficiency and nodal clustering coefficient in temporal lobe, which strongly linked to elevated inattentive and hyperactive symptoms in the TBI-A group. These findings suggested that white matter structural re-modularity in subnetworks associated with temporal lobe may serve as quantitatively measurable biomarkers for early prediction and diagnosis of post-TBI attention deficits in children.

A Machine Learning Enhanced Mechanistic Simulation Framework for Functional Deficit Prediction in TBI

Resting state functional magnetic resonance imaging (rsfMRI), and the underlying brain networks identified with it, have recently appeared as a promising avenue for the evaluation of functional deficits without the need for active patient participation. We hypothesize here that such alteration can be inferred from tissue damage within the network. From an engineering perspective, the numerical prediction of tissue mechanical damage following an impact remains computationally expensive. To this end, we propose a numerical framework aimed at predicting resting state network disruption for an arbitrary head impact, as described by the head velocity, location and angle of impact, and impactor shape. The proposed method uses a library of precalculated cases leveraged by a machine learning layer for efficient and quick prediction. The accuracy of the machine learning layer is illustrated with a dummy fall case, where the machine learning prediction is shown to closely match the full simulation results. The resulting framework is finally tested against the rsfMRI data of nine TBI patients scanned within 24 h of injury, for which paramedical information was used to reconstruct in silico the accident. While more clinical data are required for full validation, this approach opens the door to (i) on-the-fly prediction of rsfMRI alterations, readily measurable on clinical premises from paramedical data, and (ii) reverse-engineered accident reconstruction through rsfMRI measurements.

Molecular and Diffusion Tensor Imaging Biomarkers of Traumatic Brain Injury: Principles for Investigation and Integration

The last 20 years have seen the advent of new technologies that enhance the diagnosis and prognosis of traumatic brain injury (TBI). There is recognition that TBI affects the brain beyond initial injury, in some cases inciting a progressive neuropathology that leads to chronic impairments. Medical researchers are now searching for biomarkers to detect and monitor this condition. Perhaps the most promising developments are in the biomolecular and neuroimaging domains. Molecular assays can identify proteins indicative of neuronal injury and/or degeneration. Diffusion imaging now allows sensitive evaluations of the brain's cellular microstructure. As the pace of discovery accelerates, it is important to survey the research landscape and identify promising avenues of investigation. In this review, we discuss the potential of molecular and diffusion tensor imaging (DTI) biomarkers in TBI research. Integration of these technologies could advance models of disease prognosis, ultimately improving care. To date, however, few studies have explored relationships between molecular and DTI variables in patients with TBI. Here, we provide a short primer on each technology, review the latest research, and discuss how these biomarkers may be incorporated in future studies.

Post-traumatic Headache and Mild Traumatic Brain Injury: Brain Networks and Connectivity

PURPOSE OF REVIEW

Post-traumatic headache (PTH) consequent to mild traumatic brain injury (mTBI) is a complex, multidimensional, chronic neurological disorder. The purpose of this review is to evaluate the current neuroimaging studies on mTBI and PTH with a specific focus on brain networks and connectivity patterns.

RECENT FINDINGS

We present findings on PTH incidence and prevalence, as well as the latest neuroimaging research findings on mTBI and PTH. Additionally, we propose a new strategy in studying PTH following mTBI. The diversity and heterogeneity of pathophysiological mechanisms underlying mild traumatic brain injury pose unique challenges on how we interpret neuroimaging findings in PTH. Evaluating alterations in the intrinsic brain network connectivity patterns using novel imaging and analytical techniques may provide additional insights into PTH disease state and therefore inform effective treatment strategies.

Predicting Post-Concussion Symptom Recovery in Adolescents Using a Novel Artificial Intelligence

This pilot study explores the possibility of predicting post-concussion symptom recovery at one week post-injury using only objective diffusion tensor imaging (DTI) data inputs to a novel artificial intelligence (AI) system composed of Genetic Fuzzy Trees (GFT). Forty-three adolescents age 11 to 16 years with either mild traumatic brain injury or traumatic orthopedic injury were enrolled on presentation to the emergency department. Participants received a DTI scan three days post-injury, and their symptoms were assessed by the Post-Concussion Symptom Scale (PCSS) at 6 h and one week post-injury. The GFT system was trained using one-week total PCSS scores, 48 volumetric magnetic resonance imaging inputs, and 192 DTI inputs per participant over 225 training runs. Each training run contained a randomly selected 80% of the total sample followed by a 20% validation run. Over a different randomly selected sample distribution, GFT was also compared with six common classification methods. The cascading GFT structure controlled an effectively infinite solution space that classified participants as recovered or not recovered significantly better than chance. It demonstrated 100% and 62% classification accuracy in training and validation, respectively, better than any of the six comparison methods. Recovery sensitivity and specificity were 59% and 65% in the GFT validation set, respectively. These results provide initial evidence for the effectiveness of a GFT system to make clinical predictions of trauma symptom recovery using objective brain measures. Although clinical and research applications will necessitate additional optimization of the system, these results highlight the future promise of AI in acute care.

Predicting PTSD severity using longitudinal magnetoencephalography with a multi-step learning framework

Objective The present study explores the effectiveness of incorporating temporal information in predicting Post-Traumatic Stress Disorder (PTSD) severity using magnetoencephalography (MEG) imaging data. The main objective was to assess the relationship between longitudinal MEG functional connectome data, measured across a variety of neural oscillatory frequencies and collected at two-timepoints (Phase I & II), against PTSD severity captured at the later time point. Approach We used an in-house developed informatics solution, featuring a two-step process featuring pre-learn feature selection (CV-SVR-rRF-FS, cross-validation with support vector regression and recursive random forest feature selection) and deep learning (long-short term memory recurrent neural network, LSTM-RNN) techniques. Main results The pre-learn step selected a small number of functional connections (or edges) from Phase I MEG data associated with Phase II PTSD severity, indexed using the PTSD CheckList (PCL) score. This strategy identified the functional edges affected by traumatic exposure and indexed disease severity, either permanently or evolving dynamically over time, for optimal predictive performance. Using the selected functional edges, LSTM modelling was used to incorporate the Phase II MEG data into longitudinal regression models. Single timepoint (Phase I and Phase II MEG data) SVR models were generated for comparison. Assessed with holdout test data, alpha and high gamma bands showed enhanced predictive performance with the longitudinal models comparing to the Phase I single timepoint models. The best predictive performance was observed for lower frequency ranges compared to the higher frequencies (low gamma), for both model types. Significance This study identified the neural oscillatory signatures that benefited from additional temporal information when estimating the outcome of PTSD severity using MEG functional connectome data. Crucially, this approach can similarly be applied to any other mental health challenge, using this effective informatics foundation for longitudinal tracking of pathological brain states and predicting outcome with a MEG-based neurophysiology imaging system.

Traumatic Brain Injury Severity in a Network Perspective: A Diffusion MRI Based Connectome Study

Traumatic brain injury (TBI) is often characterized by alterations in brain connectivity. We explored connectivity alterations from a network perspective, using graph theory, and examined whether injury severity affected structural connectivity and modulated the association between brain connectivity and cognitive deficits post-TBI. We performed diffusion imaging network analysis on chronic TBI patients, with different injury severities and healthy subjects. From both global and local perspectives, we found an effect of injury severity on network strength. In addition, regions which were considered as hubs differed between groups. Further exploration of graph measures in the determined hub regions showed that efficiency of six regions differed between groups. An association between reduced efficiency in the precuneus and nonverbal abstract reasoning deficits (calculated using actual pre-injury scores) was found in the controls but was lost in TBI patients. Our results suggest that disconnection of network hubs led to a less efficient network, which in turn may have contributed to the cognitive impairments manifested in TBI patients. We conclude that injury severity modulates the disruption of network organization, reflecting a "dose response" relationship and emphasize the role of efficiency as an important diagnostic tool to detect subtle brain injury specifically in mild TBI patients.

Classifying post-traumatic stress disorder using the magnetoencephalographic connectome and machine learning

Given the subjective nature of conventional diagnostic methods for post-traumatic stress disorder (PTSD), an objectively measurable biomarker is highly desirable; especially to clinicians and researchers. Macroscopic neural circuits measured using magnetoencephalography (MEG) has previously been shown to be indicative of the PTSD phenotype and severity. In the present study, we employed a machine learning-based classification framework using MEG neural synchrony to distinguish combat-related PTSD from trauma-exposed controls. Support vector machine (SVM) was used as the core classification algorithm. A recursive random forest feature selection step was directly incorporated in the nested SVM cross validation process (CV-SVM-rRF-FS) for identifying the most important features for PTSD classification. For the five frequency bands tested, the CV-SVM-rRF-FS analysis selected the minimum numbers of edges per frequency that could serve as a PTSD signature and be used as the basis for SVM modelling. Many of the selected edges have been reported previously to be core in PTSD pathophysiology, with frequency-specific patterns also observed. Furthermore, the independent partial least squares discriminant analysis suggested low bias in the machine learning process. The final SVM models built with selected features showed excellent PTSD classification performance (area-under-curve value up to 0.9). Testament to its robustness when distinguishing individuals from a heavily traumatised control group, these developments for a classification model for PTSD also provide a comprehensive machine learning-based computational framework for classifying other mental health challenges using MEG connectome profiles.

Early computed tomography for acute post-traumatic diffuse axonal injury: a systematic review

Purpose

Diffuse axonal injury (DAI) is the rupture of multiple axons due to acceleration and deceleration forces during a closed head injury. Most traumatic brain injuries (TBI) have some degree of DAI, especially severe TBI. Computed tomography (CT) remains the first imaging test performed in the acute phase of TBI, but has low sensitivity for detecting DAI, since DAI is a cellular lesion. The aim of this study is to search in the literature for CT signs, in the first 24 h after TBI, that may help to differentiate patients in groups with a better versus worst prognosis.

Methods

We searched for primary scientific articles in the PubMed database, in English, indexed since January 1st, 2000.

Results

Five articles were selected for review. In the DAI group, traffic accidents accounted 70% of the cases, 79% were male, and the mean age was 41 years. There was an association between DAI and intraventricular hemorrhage (IVH) and traumatic subarachnoid hemorrhage (tSAH); an association between the IVH grade and number of corpus callosum lesions; and an association between blood in the interpeduncular cisterns (IPC) and brainstem lesions.

Conclusion

In closed TBI with no tSAH, severe DAI is unlikely. Similarly, in the absence of IVH, any DAI is unlikely. If there is IVH, patients generally are clinically worse; and the more ventricles affected, the worse the prognosis.

Integrating machining learning and multimodal neuroimaging to detect schizophrenia at the level of the individual

Schizophrenia is a severe psychiatric disorder associated with both structural and functional brain abnormalities. In the past few years, there has been growing interest in the application of machine learning techniques to neuroimaging data for the diagnostic and prognostic assessment of this disorder. However, the vast majority of studies published so far have used either structural or functional neuroimaging data, without accounting for the multimodal nature of the disorder. Structural MRI and resting‐state functional MRI data were acquired from a total of 295 patients with schizophrenia and 452 healthy controls at five research centers. We extracted features from the data including gray matter volume, white matter volume, amplitude of low‐frequency fluctuation, regional homogeneity and two connectome‐wide based metrics: structural covariance matrices and functional connectivity matrices. A support vector machine classifier was trained on each dataset separately to distinguish the subjects at individual level using each of the single feature as well as their combination, and 10‐fold cross‐validation was used to assess the performance of the model. Functional data allow higher accuracy of classification than structural data (mean 82.75% vs. 75.84%). Within each modality, the combination of images and matrices improves performance, resulting in mean accuracies of 81.63% for structural data and 87.59% for functional data. The use of all combined structural and functional measures allows the highest accuracy of classification (90.83%). We conclude that combining multimodal measures within a single model is a promising direction for developing biologically informed diagnostic tools in schizophrenia.

MTBI Identification From Diffusion MR Images Using Bag of Adversarial Visual Features

In this paper, we propose bag of adversarial features (BAFs) for identifying mild traumatic brain injury (MTBI) patients from their diffusion magnetic resonance images (MRIs) (obtained within one month of injury) by incorporating unsupervised feature learning techniques. MTBI is a growing public health problem with an estimated incidence of over 1.7 million people annually in USA. Diagnosis is based on clinical history and symptoms, and accurate, concrete measures of injury are lacking. Unlike most of the previous works, which use hand-crafted features extracted from different parts of brain for MTBI classification, we employ feature learning algorithms to learn more discriminative representation for this task. A major challenge in this field thus far is the relatively small number of subjects available for training. This makes it difficult to use an end-to-end convolutional neural network to directly classify a subject from MRIs. To overcome this challenge, we first apply an adversarial auto-encoder (with convolutional structure) to learn patch-level features, from overlapping image patches extracted from different brain regions. We then aggregate these features through a bag-of-words approach. We perform an extensive experimental study on a dataset of 227 subjects (including 109 MTBI patients, and 118 age and sex-matched healthy controls) and compare the bag-of-deep-features with several previous approaches. Our experimental results show that the BAF significantly outperforms earlier works relying on the mean values of MR metrics in selected brain regions.

Fingerprinting Orientation Distribution Functions in diffusion MRI detects smaller crossing angles

Diffusion tractography is routinely used to study white matter architecture and brain connectivity in vivo. A key step for successful tractography of neuronal tracts is the correct identification of tract directions in each voxel. Here we propose a fingerprinting-based methodology to identify these fiber directions in Orientation Distribution Functions, dubbed ODF-Fingerprinting (ODF-FP). In ODF-FP, fiber configurations are selected based on the similarity between measured ODFs and elements in a pre-computed library. In noisy ODFs, the library matching algorithm penalizes the more complex fiber configurations. ODF simulations and analysis of bootstrapped partial and whole-brain in vivo datasets show that the ODF-FP approach improves the detection of fiber pairs with small crossing angles while maintaining fiber direction precision, which leads to better tractography results. Rather than focusing on the ODF maxima, the ODF-FP approach uses the whole ODF shape to infer fiber directions to improve the detection of fiber bundles with small crossing angle. The resulting fiber directions aid tractography algorithms in accurately displaying neuronal tracts and calculating brain connectivity.

The structural connectome in traumatic brain injury: A meta-analysis of graph metrics

Although recent structural connectivity studies of traumatic brain injury (TBI) have used graph theory to evaluate alterations in global integration and functional segregation, pooled analysis is needed to examine the robust patterns of change in graph metrics across studies. Following a systematic search, 15 studies met the inclusion criteria for review. Of these, ten studies were included in a random-effects meta-analysis of global graph metrics, and subgroup analyses examined the confounding effects of severity and time since injury. The meta-analysis revealed significantly higher values of normalised clustering coefficient (gö=ö1.445, CI=[0.512, 2.378], pö=ö0.002) and longer characteristic path length (gö=ö0.514, CI=[0.190, 0.838], pö=ö0.002) in TBI patients compared with healthy controls. Our findings suggest that the TBI structural network has shifted away from the balanced small-world network towards a regular lattice. Therefore, these graph metrics may be useful markers of neurocognitive dysfunction in TBI. We conclude that the pattern of change revealed by our analysis should be used to guide hypothesis-driven research into the role of graph metrics as diagnostic and prognostic biomarkers.

Current trends in biomarker discovery and analysis tools for traumatic brain injury

Traumatic brain injury (TBI) affects 1.7 million people in the United States each year, causing lifelong functional deficits in cognition and behavior. The complex pathophysiology of neural injury is a primary barrier to developing sensitive and specific diagnostic tools, which consequentially has a detrimental effect on treatment regimens. Biomarkers of other diseases (e.g. cancer) have provided critical insight into disease emergence and progression that lend to developing powerful clinical tools for intervention. Therefore, the biomarker discovery field has recently focused on TBI and made substantial advancements to characterize markers with promise of transforming TBI patient diagnostics and care. This review focuses on these key advances in neural injury biomarkers discovery, including novel approaches spanning from omics-based approaches to imaging and machine learning as well as the evolution of established techniques.

Neuroimaging of Traumatic Brain Injury

The purpose of this article is to review conventional and advanced neuroimaging techniques performed in the setting of traumatic brain injury (TBI). The primary goal for the treatment of patients with suspected TBI is to prevent secondary injury. In the setting of a moderate to severe TBI, the most appropriate initial neuroimaging examination is a noncontrast head computed tomography (CT), which can reveal life-threatening injuries and direct emergent neurosurgical intervention. We will focus much of the article on advanced neuroimaging techniques including perfusion imaging and diffusion tensor imaging and discuss their potentials and challenges. We believe that advanced neuroimaging techniques may improve the accuracy of diagnosis of TBI and improve management of TBI.

Low Rank plus Sparse decomposition of ODFs for improved detection of group-level differences and variable correlations in white matter

A novel approach is presented for group statistical analysis of diffusion weighted MRI datasets through voxelwise Orientation Distribution Functions (ODF). Recent advances in MRI acquisition make it possible to use high quality diffusion weighted protocols (multi-shell, large number of gradient directions) for routine in vivo study of white matter architecture. The dimensionality of these data sets is however often reduced to simplify statistical analysis. While these approaches may detect large group differences, they do not fully capitalize on all acquired image volumes. Incorporation of all available diffusion information in the analysis however risks biasing the outcome by outliers. Here we propose a statistical analysis method operating on the ODF, either the diffusion ODF or fiber ODF. To avoid outlier bias and reliably detect voxelwise group differences and correlations with demographic or behavioral variables, we apply the Low-Rank plus Sparse (L+S) matrix decomposition on the voxelwise ODFs which separates the sparse individual variability in the sparse matrix S whilst recovering the essential ODF features in the low-rank matrix L. We demonstrate the performance of this ODF L+S approach by replicating the established negative association between global white matter integrity and physical obesity in the Human Connectome dataset. The volume of positive findings p<0.01,227cm3, agrees with and expands on the volume found by TBSS (17 cm3), Connectivity based fixel enhancement (15 cm3) and Connectometry (212 cm3). In the same dataset we further localize the correlations of brain structure with neurocognitive measures such as fluid intelligence and episodic memory. The presented ODF L+S approach will aid in the full utilization of all acquired diffusion weightings leading to the detection of smaller group differences in clinically relevant settings as well as in neuroscience applications.

Ordinal Pattern: A New Descriptor for Brain Connectivity Networks

Brain connectivity networks based on magnetic resonance imaging (MRI) or functional MRI (fMRI) data provide a straightforward way to quantify the structural or functional systems of the brain. Currently, there are several network descriptors developed for representing and analyzing brain connectivity networks. However, most of them are designed for unweighted networks, regardless of the valuable weight information of edges, or do not take advantage of the ordinal relationship of weighted edges (even though they are designed for weighted networks). In this paper, we propose a new network descriptor (i.e., ordinal pattern that contains a sequence of weighted edges) for brain connectivity network analysis. Compared with previous network properties, the proposed ordinal patterns cannot only take advantage of the weight information of edges but also explicitly model the ordinal relationship of weighted edges in brain connectivity networks. We further develop an ordinal pattern-based learning framework for brain disease diagnosis using resting-state fMRI data. Specifically, we first construct a set of brain functional connectivity networks, where each network is corresponding to a particular subject. We then develop an algorithm to identify ordinal patterns that frequently appear in brain connectivity networks of patients and normal controls. We further perform discriminative ordinal pattern selection and extract feature representations for subjects based on the selected ordinal patterns, followed by a learning model for automated brain disease diagnosis. Experimental results on both Alzheimer's Disease Neuroimaging Initiative and attention deficit hyperactivity disorder-200 data sets demonstrate that our method outperforms the several state-of-the-art approaches in the tasks of disease classification and clinical score regression.

Impaired rich club and increased local connectivity in children with traumatic brain injury: Local support for the rich?

Recent evidence has shown the presence of a "rich club" in the brain, which constitutes a core network of highly interconnected and spatially distributed brain regions, important for high-order cognitive processes. This study aimed to map the rich club organization in 17 young patients with moderate to severe TBI (15.71 ± 1.75 years) in the chronic stage of recovery and 17 age- and gender-matched controls. Probabilistic tractography was performed on diffusion weighted imaging data to construct the edges of the structural connectomes using number of streamlines as edge weight. In addition, the whole-brain network was divided into a rich club network, a local network and a feeder network connecting the latter two. Functional outcome was measured with a parent questionnaire for executive functioning. Our results revealed a significantly decreased rich club organization (p values < .05) and impaired executive functioning (p < .001) in young patients with TBI compared with controls. Specifically, we observed reduced density values in all three subnetworks (p values < .005) and a reduced mean strength in the rich club network (p = .013) together with an increased mean strength in the local network (p = .002) in patients with TBI. This study provides new insights into the nature of TBI-induced brain network alterations and supports the hypothesis that the local subnetwork tries to compensate for the biologically costly subnetwork of rich club nodes after TBI.

Accelerated Changes in Cortical Thickness Measurements with Age in Military Service Members with Traumatic Brain Injury

Finding objective and quantifiable imaging markers of mild traumatic brain injury (TBI) has proven challenging, especially in the military population. Changes in cortical thickness after injury have been reported in animals and in humans, but it is unclear how these alterations manifest in the chronic phase, and it is difficult to characterize accurately with imaging. We used cortical thickness measures derived from Advanced Normalization Tools (ANTs) to predict a continuous demographic variable: age. We trained four different regression models (linear regression, support vector regression, Gaussian process regression, and random forests) to predict age from healthy control brains from publicly available datasets (n = 762). We then used these models to predict brain age in military Service Members with TBI (n = 92) and military Service Members without TBI (n = 34). Our results show that all four models overpredicted age in Service Members with TBI, and the predicted age difference was significantly greater compared with military controls. These data extend previous civilian findings and show that cortical thickness measures may reveal an association of accelerated changes over time with military TBI.

White matter changes in patients with mild traumatic brain injury: MRI perspective

This review focuses on white matter (WM) changes in mild traumatic brain injury (mTBI) as assessed by multimodal MRI. All the peer reviewed publications on WM changes in mTBI from January 2011 through September 2016 are included in this review. This review is organized as follows: introduction to mTBI, the basics of multimodal MRI techniques that are potentially useful for probing the WM integrity, summary and critical evaluation of the published literature on the application of multimodal MRI techniques to assess the changes of WM in mTBI, and correlation of MRI measures with behavioral deficits. The MRI–pathology correlation studies based on preclinical models of mTBI are also reviewed. Finally, the author's perspective of future research directions is described.

Repetitive transcranial magnetic stimulation for the treatment of post-stroke depression: A systematic review and meta-analysis of randomized controlled clinical trials

BACKGROUND

Every year, more than fifteen million people worldwide experience a stroke, nearly 30% of stroke survivors are likely to experience post-stroke depression (PSD). Repetitive transcranial magnetic stimulation (rTMS) is one of the emerging techniques which assist in targeting rehabilitation after stroke. Although deterioration of PSD greatly affects the recovery and quality of life of stroke sufferers, the effect of rTMS therapy has not been systematically studied.

OBJECTIVE

A systematic review and meta-analysis was conducted to determine the effect of rTMS on PSD.

METHODS

We carried out a systematic review and meta-analysis of randomized controlled trials (RCTs) of rTMS for the treatment of PSD. Primary outcome was severity of depression measured by the Hamilton Depression Rating Scale (HAMD). Secondary outcomes were response rates, remission rates, stroke severity and ability to perform daily activities.

RESULTS

22 RCTs studies (n=1764 patients) were included. The results demonstrated that rTMS was beneficial on PSD using three scales: HAMD (MD=-6.09, 95% CI: -7.74, -4.45, P<0.001); response rates (OR=3.46, 95% CI: 2.52, 4.76, P<0.00001); remission rates (OR 0.99, 95% CI: 0.56, 1.75, P<0.00001); National Institutes of Health Stroke Scale (NIHSS) (MD=-2.74, 95% CI: -3.33, -2.15, P<0.001); Activities of daily living (ADL) (SMD=-1.20, 95% CI: 0.68, 1.72, P<0.001); Montgomery-Asberg Depression Scale (MARDE) (MD=-6.21; 95% CI: -9.34, -3.08; P=0.0001); CONCLUSION: In present meta-analysis, the positive findings suggest rTMS has beneficial effects on PSD. However, those findings should be treated with caution because of heterogeneity and potential biases.

Systems Biology, Neuroimaging, Neuropsychology, Neuroconnectivity and Traumatic Brain Injury

The patient who sustains a traumatic brain injury (TBI) typically undergoes neuroimaging studies, usually in the form of computed tomography (CT) and magnetic resonance imaging (MRI). In most cases the neuroimaging findings are clinically assessed with descriptive statements that provide qualitative information about the presence/absence of visually identifiable abnormalities; though little if any of the potential information in a scan is analyzed in any quantitative manner, except in research settings. Fortunately, major advances have been made, especially during the last decade, in regards to image quantification techniques, especially those that involve automated image analysis methods. This review argues that a systems biology approach to understanding quantitative neuroimaging findings in TBI provides an appropriate framework for better utilizing the information derived from quantitative neuroimaging and its relation with neuropsychological outcome. Different image analysis methods are reviewed in an attempt to integrate quantitative neuroimaging methods with neuropsychological outcome measures and to illustrate how different neuroimaging techniques tap different aspects of TBI-related neuropathology. Likewise, how different neuropathologies may relate to neuropsychological outcome is explored by examining how damage influences brain connectivity and neural networks. Emphasis is placed on the dynamic changes that occur following TBI and how best to capture those pathologies via different neuroimaging methods. However, traditional clinical neuropsychological techniques are not well suited for interpretation based on contemporary and advanced neuroimaging methods and network analyses. Significant improvements need to be made in the cognitive and behavioral assessment of the brain injured individual to better interface with advances in neuroimaging-based network analyses. By viewing both neuroimaging and neuropsychological processes within a systems biology perspective could represent a significant advancement for the field.