A large normative connectome for exploring the tractographic correlates of focal brain interventions.

Diffusion-weighted MRI (dMRI) is a widely used neuroimaging modality that permits the in vivo exploration of white matter connections in the human brain. Normative structural connectomics - the application of large-scale, group-derived dMRI datasets to out-of-sample cohorts - have increasingly been leveraged to study the network correlates of focal brain interventions, insults, and other regions-of-interest (ROIs). Here, we provide a normative, whole-brain connectome in MNI space that enables researchers to interrogate fiber streamlines that are likely perturbed by given ROIs, even in the absence of subject-specific dMRI data. Assembled from multi-shell dMRI data of 985 healthy Human Connectome Project subjects using generalized Q-sampling imaging and multispectral normalization techniques, this connectome comprises ~12 million unique streamlines, the largest to date. It has already been utilized in at least 18 peer-reviewed publications, most frequently in the context of neuromodulatory interventions like deep brain stimulation and focused ultrasound. Now publicly available, this connectome will constitute a useful tool for understanding the wider impact of focal brain perturbations on white matter architecture going forward.

Ipsilateral and axial tremor response to focused ultrasound thalamotomy for essential tremor: clinical outcomes and probabilistic mapping.

BACKGROUND: MR-guided focused ultrasound (MRgFUS) thalamotomy has been shown to be a safe and effective treatment for essential tremor (ET). OBJECTIVE: To investigate the effects of MRgFUS in patients with ET with an emphasis on ipsilateral-hand and axial tremor subscores. METHODS: Tremor scores and adverse effects of 100 patients treated between 2012 and 2018 were assessed at 1 week, 3, 12, and 24 months. A subgroup analysis of ipsilateral-hand tremor responders (defined as patients with ≥30% improvement at any time point) and non-responders was performed. Correlations and predictive factors for improvement were analysed. Weighted probabilistic maps of improvement were generated. RESULTS: Significant improvement in axial, contralateral-hand and total tremor scores was observed at all study visits from baseline (p<0.0001). There was no significant improvement in ipsilateral subscores. A subset of patients (n=20) exhibited group-level ipsilateral-hand improvement that remained significant through all follow-ups (p<0.001). Multivariate regression analysis revealed that higher baseline scores predict better improvement in ipsilateral-hand and axial tremor. Probabilistic maps demonstrated that the lesion hotspot for axial improvement was situated more medially than that for contralateral improvement. CONCLUSION: MRgFUS significantly improved axial, contralateral-hand and total tremor scores. In a subset of patients, a consistent group-level treatment effect was observed for ipsilateral-hand tremor. While ipsilateral improvement seemed to be less directly related to lesion location, a spatial relationship between lesion location and axial and contralateral improvement was observed that proved consistent with the somatotopic organisation of the ventral intermediate nucleus. TRIAL REGISTRATION NUMBERS: NCT01932463, NCT01827904, and NCT02252380.

Dysgeusia induced and resolved by focused ultrasound thalamotomy: case report.

Dysgeusia, or distorted taste, has recently been acknowledged as a complication of thalamic ablation or thalamic deep brain stimulation as a treatment of tremor. In a unique patient, left-sided MR-guided focused ultrasound thalamotomy improved right-sided essential tremor but also induced severe dysgeusia. Although dysgeusia persisted and caused substantial weight loss, tremor slowly relapsed. Therefore, 19 months after the first procedure, the patient underwent a second focused ultrasound thalamotomy procedure, which again improved tremor but also completely resolved the dysgeusia. On the basis of normative and patient-specific whole-brain tractography, the authors determined the relationship between the thalamotomy lesions and the medial border of the medial lemniscus-a surrogate for the solitariothalamic gustatory fibers-after the first and second focused ultrasound thalamotomy procedures. Both tractography methods suggested partial and complete disruption of the solitariothalamic gustatory fibers after the first and second thalamotomy procedures, respectively. The tractography findings in this unique patient demonstrate that incomplete and complete disruption of a neural pathway can induce and resolve symptoms, respectively, and serve as the rationale for ablative procedures for neurological and psychiatric disorders.

Predicting optimal deep brain stimulation parameters for Parkinson's disease using functional MRI and machine learning.

Commonly used for Parkinson's disease (PD), deep brain stimulation (DBS) produces marked clinical benefits when optimized. However, assessing the large number of possible stimulation settings (i.e., programming) requires numerous clinic visits. Here, we examine whether functional magnetic resonance imaging (fMRI) can be used to predict optimal stimulation settings for individual patients. We analyze 3 T fMRI data prospectively acquired as part of an observational trial in 67 PD patients using optimal and non-optimal stimulation settings. Clinically optimal stimulation produces a characteristic fMRI brain response pattern marked by preferential engagement of the motor circuit. Then, we build a machine learning model predicting optimal vs. non-optimal settings using the fMRI patterns of 39 PD patients with a priori clinically optimized DBS (88% accuracy). The model predicts optimal stimulation settings in unseen datasets: a priori clinically optimized and stimulation-naïve PD patients. We propose that fMRI brain responses to DBS stimulation in PD patients could represent an objective biomarker of clinical response. Upon further validation with additional studies, these findings may open the door to functional imaging-assisted DBS programming.

Use of Functional MRI to Assess Effects of Deep Brain Stimulation Frequency Changes on Brain Activation in Parkinson Disease.

BACKGROUND: Models have been developed for predicting ideal contact and amplitude for subthalamic nucleus (STN) deep brain stimulation (DBS) for Parkinson disease (PD). Pulse-width is generally varied to modulate the size of the energy field produced. Effects of varying frequency in humans have not been systematically evaluated. OBJECTIVE: To examine how altered frequencies affect blood oxygen level-dependent activation in PD. METHODS: PD subjects with optimized DBS programming underwent functional magnetic resonance imaging (fMRI). Frequency was altered and fMRI scans/Unified Parkinson Disease Rating Scale motor subunit (UPDRS-III) scores were obtained. Analysis using DBS-OFF data was used to determine which regions were activated during DBS-ON. Peak activity utilizing T-values was obtained and compared. RESULTS: At clinically optimized settings (n = 14 subjects), thalamic, globus pallidum externa (GPe), and posterior cerebellum activation were present. Activation levels significantly decreased in the thalamus, anterior cerebellum, and the GPe when frequency was decreased (P < .001). Primary somatosensory cortex activation levels significantly decreased when frequency was increased by 30 Hz, but not 60 Hz. Sex, age, disease/DBS duration, and bilaterality did not significantly affect the data. Retrospective analysis of fMRI activation patterns predicted optimal frequency in 11/14 subjects. CONCLUSION: We show the first data with fMRI of STN DBS-ON while synchronizing cycling with magnetic resonance scanning. At clinically optimized settings, an fMRI signature of thalamic, GPe, and posterior cerebellum activation was seen. Reducing frequency significantly decreased thalamic, GPe, and anterior cerebellum activation. Current standard-of-care programming can take up to 6 mo using UPDRS-III testing alone. We provide preliminary evidence that using fMRI signature of frequency may have clinical utility and feasibility.

Probabilistic Mapping of Deep Brain Stimulation: Insights from 15 Years of Therapy.

Deep brain stimulation (DBS) depends on precise delivery of electrical current to target tissues. However, the specific brain structures responsible for best outcome are still debated. We applied probabilistic stimulation mapping to a retrospective, multidisorder DBS dataset assembled over 15 years at our institution (ntotal = 482 patients; nParkinson disease = 303; ndystonia = 64; ntremor = 39; ntreatment-resistant depression/anorexia nervosa = 76) to identify the neuroanatomical substrates of optimal clinical response. Using high-resolution structural magnetic resonance imaging and activation volume modeling, probabilistic stimulation maps (PSMs) that delineated areas of above-mean and below-mean response for each patient cohort were generated and defined in terms of their relationships with surrounding anatomical structures. Our results show that overlap between PSMs and individual patients' activation volumes can serve as a guide to predict clinical outcomes, but that this is not the sole determinant of response. In the future, individualized models that incorporate advancements in mapping techniques with patient-specific clinical variables will likely contribute to the optimization of DBS target selection and improved outcomes for patients. ANN NEUROL 2021;89:426-443.

Mapping the network underpinnings of central poststroke pain and analgesic neuromodulation.

Central poststroke pain (CPSP) is a debilitating and often treatment-refractory condition that affects numerous stroke patients. The location of lesions most likely to cause pain and the identity of the functional brain networks that they impinge upon remain incompletely understood. We aimed to (1) elucidate which lesion locations are most frequently accompanied by pain; (2) explore CPSP-associated functional networks; and (3) examine how neuromodulation interacts with these networks. This multisite study investigated 17 CPSP patients who received deep brain stimulation (DBS; n = 12) or motor cortex stimulation (MCS; n = 5). Pain-causing lesions were manually segmented and normalized to standard space. To identify areas linked to high risk of pain, the locations of CPSP lesions and 220 control lesions were compared using voxelwise odds ratio mapping. The functional connectivity of pain-causing lesions was obtained using a large (n = 1000) normative resting-state functional MRI connectome and compared to that of control lesions and therapeutic DBS activation volumes. Brain regions most associated with CPSP risk (highest value = 63 times) were located along the ascending somatosensory pathways. These areas and the majority of individual CPSP lesions were functionally connected to anterior/middle cingulate cortex, insula, thalamus, and inferior parietal lobule (PBonferroni < 0.05). The extent of connectivity to the thalamus, inferior parietal lobule, and precuneus also differed between CPSP and control lesions (PBonferroni < 0.05). Posterior insula and thalamus shared connectivity with both CPSP lesions and pain-alleviating DBS activation volumes (PBonferroni < 0.05). These findings further clarify the topography and functional connectivity of pain-causing brain lesions, and provide new insights into the network-level mechanism of CPSP neuromodulation.

Use of Functional Magnetic Resonance Imaging to Assess How Motor Phenotypes of Parkinson's Disease Respond to Deep Brain Stimulation.

BACKGROUND: Deep brain stimulation (DBS) is a well-accepted treatment of Parkinson's disease (PD). Motor phenotypes include tremor-dominant (TD), akinesia-rigidity (AR), and postural instability gait disorder (PIGD). The mechanism of action in how DBS modulates motor symptom relief remains unknown. OBJECTIVE: Blood oxygen level-dependent (BOLD) functional magnetic resonance imaging (fMRI) was used to determine whether the functional activity varies in response to DBS depending on PD phenotypes. MATERIALS AND METHODS: Subjects underwent an fMRI scan with DBS cycling ON and OFF. The effects of DBS cycling on BOLD activation in each phenotype were documented through voxel-wise analysis. For each region of interest, ANOVAs were performed using T-values and covariate analyses were conducted. Further, a correlation analysis was performed comparing stimulation settings to T-values. Lastly, T-values of subjects with motor improvement were compared to those who worsened. RESULTS: As a group, BOLD activation with DBS-ON resulted in activation in the motor thalamus (p < 0.01) and globus pallidus externa (p < 0.01). AR patients had more activation in the supplementary motor area (SMA) compared to PIGD (p < 0.01) and TD cohorts (p < 0.01). Further, the AR cohort had more activation in primary motor cortex (MI) compared to the TD cohort (p = 0.02). Implanted nuclei (p = 0.01) and phenotype (p = <0.01) affected activity in MI and phenotype alone affected SMA activity (p = <0.01). A positive correlation was seen between thalamic activation and pulse-width (p = 0.03) and between caudate and total electrical energy delivered (p = 0.04). CONCLUSIONS: These data suggest that DBS modulates network activity differently based on patient motor phenotype. Improved understanding of these differences may further our knowledge about the mechanisms of DBS action on PD motor symptoms and to optimize treatment.

Author Correction: Noninvasive sub-organ ultrasound stimulation for targeted neuromodulation.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Probing the circuitry of panic with deep brain stimulation: Connectomic analysis and review of the literature.

BACKGROUND: Panic attacks affect a sizeable proportion of the population. The neurocircuitry of panic remains incompletely understood. OBJECTIVE: To investigate the neuroanatomical underpinnings of panic attacks induced by deep brain stimulation (DBS) through (1) connectomic analysis of an obsessive-compulsive disorder patient who experienced panic attacks during inferior thalamic peduncle DBS; (2) appraisal of existing clinical reports on DBS-induced panic attacks. METHODS: Panicogenic, ventral contact stimulation was compared with benign stimulation at other contacts using volume of tissue activated (VTA) modelling. Networks associated with the panicogenic zone were investigated using state-of-the-art normative connectivity mapping. In addition, a literature search for prior reports of DBS-induced panic attacks was conducted. RESULTS: Panicogenic VTAs impinged primarily on the tuberal hypothalamus. Compared to non-panicogenic VTAs, panicogenic loci were significantly functionally coupled to limbic and brainstem structures, including periaqueductal grey and amygdala. Previous studies found stimulation of these areas can also provoke panic attacks. CONCLUSIONS: DBS in the region of the tuberal hypothalamus elicited panic attacks in a single obsessive-compulsive disorder patient and recruited a network of structures previously implicated in panic pathophysiology, reinforcing the importance of the hypothalamus as a hub of panicogenic circuitry.

Functional MRI Signature of Chronic Pain Relief From Deep Brain Stimulation in Parkinson Disease Patients.

BACKGROUND: Chronic pain occurs in 83% of Parkinson disease (PD) patients and deep brain stimulation (DBS) has shown to result in pain relief in a subset of patients, though the mechanism is unclear. OBJECTIVE: To compare functional magnetic resonance imaging (MRI) data in PD patients with chronic pain without DBS, those whose pain was relieved (PR) with DBS and those whose pain was not relieved (PNR) with DBS. METHODS: Functional MRI (fMRI) with blood oxygen level-dependent activation data was obtained in 15 patients in control, PR, and PNR patients. fMRI was obtained in the presence and absence of a mechanical stimuli with DBS ON and DBS OFF. Voxel-wise analysis using pain OFF data was used to determine which regions were altered during pain ON periods. RESULTS: At the time of MRI, pain was scored a 5.4 ± 1.2 out of 10 in the control, 4.25 ± 1.18 in PNR, and 0.8 ± 0.67 in PR cohorts. Group analysis of control and PNR groups showed primary somatosensory (SI) deactivation, whereas PR patients showed thalamic deactivation and SI activation. DBS resulted in more decreased activity in PR than PNR (P < .05) and more activity in anterior cingulate cortex (ACC) in PNR patients (P < .05). CONCLUSION: Patients in the control and PNR groups showed SI deactivation at baseline in contrast to the PR patients who showed SI activation. With DBS ON, the PR cohort had less activity in SI, whereas the PNR had more anterior cingulate cortex activity. We provide pilot data that patients whose pain responds to DBS may have a different fMRI signature than those who do not, and PR and PNR cohorts produced different brain responses when DBS is employed.

Noninvasive sub-organ ultrasound stimulation for targeted neuromodulation.

Tools for noninvasively modulating neural signaling in peripheral organs will advance the study of nerves and their effect on homeostasis and disease. Herein, we demonstrate a noninvasive method to modulate specific signaling pathways within organs using ultrasound (U/S). U/S is first applied to spleen to modulate the cholinergic anti-inflammatory pathway (CAP), and US stimulation is shown to reduce cytokine response to endotoxin to the same levels as implant-based vagus nerve stimulation (VNS). Next, hepatic U/S stimulation is shown to modulate pathways that regulate blood glucose and is as effective as VNS in suppressing the hyperglycemic effect of endotoxin exposure. This response to hepatic U/S is only found when targeting specific sub-organ locations known to contain glucose sensory neurons, and both molecular (i.e. neurotransmitter concentration and cFOS expression) and neuroimaging results indicate US induced signaling to metabolism-related hypothalamic sub-nuclei. These data demonstrate that U/S stimulation within organs provides a new method for site-selective neuromodulation to regulate specific physiological functions.

Longitudinal Resting State Functional Connectivity Predicts Clinical Outcome in Mild Traumatic Brain Injury.

Mild traumatic brain injury (mTBI) affects about 42 million people worldwide. It is often associated with headache, cognitive deficits, and balance difficulties but rarely shows any abnormalities on conventional computed tomography (CT) or magnetic resonance imaging (MRI). Although in most mTBI patients the symptoms resolve within 3 months, 10-15% of patients continue to exhibit symptoms beyond a year. Also, it is known that there exists a vulnerable period post-injury, when a second injury may exacerbate clinical prognosis. Identifying this vulnerable period may be critical for patient outcome, but very little is known about the neural underpinnings of mTBI and its recovery. In this work, we used advanced functional neuroimaging to study longitudinal changes in functional organization of the brain during the 3-month recovery period post-mTBI. Fractional amplitude of low frequency fluctuations (fALFF) measured from resting state functional MRI (rs-fMRI) was found to be associated with symptom severity score (SSS, r = -0.28, p = 0.002). Decreased fALFF was observed in specific functional networks for patients with higher SSS, and fALFF returned to higher values when the patient recovered (lower SSS). In addition, functional connectivity of the same networks was found to be associated with concurrent SSS, and connectivity immediately after injury (<10 days) was capable of predicting SSS at a later time-point (3 weeks to 3 months, p < 0.05). Specific networks including motor, default-mode, and visual networks were found to be associated with SSS (p < 0.001), and connectivity between these networks predicted 3-month clinical outcome (motor and visual: p < 0.001, default-mode: p < 0.006). Our results suggest that functional connectivity in these networks comprise potential biomarkers for predicting mTBI recovery profiles and clinical outcome.

Multiband fMRI as a plausible, time-saving technique for resting-state data acquisition: Study on functional connectivity mapping using graph theoretical measures.

BACKGROUND AND OBJECTIVES: Ensuring patient comfort and compliance by emphasizing reduced time frame for image acquisition, without compromising image quality is the key aspect with functional MRI examination. Multiband resting state fMRI (MB-rsfMRI) is a fairly new technique that potentially shortens MR image acquisition time by providing increased number of time points. The study aims to compare signal characteristics as well as the functional connectivity using conventional resting-state fMRI (rsfMRI) with that of MB-rsfMRI technique. MATERIALS AND METHODS: 9 healthy volunteers have prospectively undergone conventional resting-state fMRI and Multiband rsfMRI scanning technique in a 3T GE scanner (Discovery MR750w™). We compared the temporal SNR (tSNR) of conventional rs-fMRI with that of MB-rsfMRI. We looked at the language network connectivity and small world network characteristics from graph theoretical measures to compare the two techniques. RESULTS: We computed the tSNR of conventional resting-state fMRI (rsfMRI) and MB-rsfMRI technique. A strong positive correlation was seen between graph theoretical measures from MB-rsfMRI and conventional rsfMRI (Pearson Correlation, r = 0.99). Both techniques showed similar small world network characteristics in healthy controls. CONCLUSION: The present study demonstrates negligible differences between the conventional-rsfMRI and MB-rsfMRI acquisitions on the computed graph theoretic measures. Accordingly current analysis proves that MB-rs-fMRI may be used as a time reducing acquisition technique that enables mapping of functional connectivity with similar outcome as conventional rs-fMRI in healthy subjects.

Recursive feature elimination for biomarker discovery in resting-state functional connectivity.

Biomarker discovery involves finding correlations between features and clinical symptoms to aid clinical decision. This task is especially difficult in resting state functional magnetic resonance imaging (rs-fMRI) data due to low SNR, high-dimensionality of images, inter-subject and intra-subject variability and small numbers of subjects compared to the number of derived features. Traditional univariate analysis suffers from the problem of multiple comparisons. Here, we adopt an alternative data-driven method for identifying population differences in functional connectivity. We propose a machine-learning approach to down-select functional connectivity features associated with symptom severity in mild traumatic brain injury (mTBI). Using this approach, we identified functional regions with altered connectivity in mTBI. including the executive control, visual and precuneus networks. We compared functional connections at multiple resolutions to determine which scale would be more sensitive to changes related to patient recovery. These modular network-level features can be used as diagnostic tools for predicting disease severity and recovery profiles.

Reproducibility and Temporal Structure in Weekly Resting-State fMRI over a Period of 3.5 Years.

Resting-state functional MRI (rs-fMRI) permits study of the brain's functional networks without requiring participants to perform tasks. Robust changes in such resting state networks (RSNs) have been observed in neurologic disorders, and rs-fMRI outcome measures are candidate biomarkers for monitoring clinical trials, including trials of extended therapeutic interventions for rehabilitation of patients with chronic conditions. In this study, we aim to present a unique longitudinal dataset reporting on a healthy adult subject scanned weekly over 3.5 years and identify rs-fMRI outcome measures appropriate for clinical trials. Accordingly, we assessed the reproducibility, and characterized the temporal structure of, rs-fMRI outcome measures derived using independent component analysis (ICA). Data was compared to a 21-person dataset acquired on the same scanner in order to confirm that the values of the single-subject RSN measures were within the expected range as assessed from the multi-participant dataset. Fourteen RSNs were identified, and the inter-session reproducibility of outcome measures-network spatial map, temporal signal fluctuation magnitude, and between-network connectivity (BNC)-was high, with executive RSNs showing the highest reproducibility. Analysis of the weekly outcome measures also showed that many rs-fMRI outcome measures had a significant linear trend, annual periodicity, and persistence. Such temporal structure was most prominent in spatial map similarity, and least prominent in BNC. High reproducibility supports the candidacy of rs-fMRI outcome measures as biomarkers, but the presence of significant temporal structure needs to be taken into account when such outcome measures are considered as biomarkers for rehabilitation-style therapeutic interventions in chronic conditions.

Disruption of functional organization within the primary motor cortex in children with autism.

Accumulating evidence suggests that motor impairments are prevalent in autism spectrum disorder (ASD), relate to the social and communicative deficits at the core of the diagnosis and may reflect abnormal connectivity within brain networks underlying motor control and learning. Parcellation of resting-state functional connectivity data using spectral clustering approaches has been shown to be an effective means of visualizing functional organization within the brain but has most commonly been applied to explorations of normal brain function. This article presents a parcellation of a key area of the motor network, the primary motor cortex (M1), a key area of the motor control network, in adults, typically developing (TD) children and children with ASD and introduces methods for selecting the number of parcels, matching parcels across groups and testing group differences. The parcellation is based solely on patterns of connectivity between individual M1 voxels and all voxels outside of M1, and within all groups, a gross dorsomedial to ventrolateral organization emerged within M1 which was left-right symmetric. Although this gross organizational scheme was present in both groups of children, statistically significant group differences in the size and segregation of M1 parcels within regions of the motor homunculus corresponding to the upper and lower limbs were observed. Qualitative comparison of the M1 parcellation for children with ASD with that of younger and older TD children suggests that these organizational differences, with a lack of differentiation between lower limb/trunk regions and upper limb/hand regions, may be due, at least in part, to a delay in functional specialization within the motor cortex.

Extensive neurological recovery from a complete spinal cord injury: a case report and hypothesis on the role of cortical plasticity.

Neurological recovery in patients with severe spinal cord injury (SCI) is extremely rare. We have identified a patient with chronic cervical traumatic SCI, who suffered a complete loss of motor and sensory function below the injury for 6 weeks after the injury, but experienced a progressive neurological recovery that continued for 17 years. The extent of the patient's recovery from the severe trauma-induced paralysis is rare and remarkable. A detailed study of this patient using diffusion tensor imaging (DTI), magnetization transfer imaging (MTI), and resting state fMRI (rs-fMRI) revealed structural and functional changes in the central nervous system that may be associated with the neurological recovery. Sixty-two percent cervical cord white matter atrophy was observed. DTI-derived quantities, more sensitive to axons, demonstrated focal changes, while MTI-derived quantity, more sensitive to myelin, showed a diffuse change. No significant cortical structural changes were observed, while rs-fMRI revealed increased brain functional connectivity between sensorimotor and visual networks. The study provides comprehensive description of the structural and functional changes in the patient using advanced MR imaging technique. This multimodal MR imaging study also shows the potential of rs-fMRI to measure the extent of cortical plasticity.

Analysis of group ICA-based connectivity measures from fMRI: application to Alzheimer's disease.

Functional magnetic resonance imaging (fMRI) is a powerful tool for the in vivo study of the pathophysiology of brain disorders and disease. In this manuscript, we propose an analysis stream for fMRI functional connectivity data and apply it to a novel study of Alzheimer's disease. In the first stage, spatial independent component analysis is applied to group fMRI data to obtain common brain networks (spatial maps) and subject-specific mixing matrices (time courses). In the second stage, functional principal component analysis is utilized to decompose the mixing matrices into population-level eigenvectors and subject-specific loadings. Inference is performed using permutation-based exact logistic regression for matched pairs data. The method is applied to a novel fMRI study of Alzheimer's disease risk under a verbal paired associates task. We found empirical evidence of alternative ICA-based metrics of connectivity when comparing subjects evidencing mild cognitive impairment relative to carefully matched controls.

Automated diagnoses of attention deficit hyperactive disorder using magnetic resonance imaging.

Successful automated diagnoses of attention deficit hyperactive disorder (ADHD) using imaging and functional biomarkers would have fundamental consequences on the public health impact of the disease. In this work, we show results on the predictability of ADHD using imaging biomarkers and discuss the scientific and diagnostic impacts of the research. We created a prediction model using the landmark ADHD 200 data set focusing on resting state functional connectivity (rs-fc) and structural brain imaging. We predicted ADHD status and subtype, obtained by behavioral examination, using imaging data, intelligence quotients and other covariates. The novel contributions of this manuscript include a thorough exploration of prediction and image feature extraction methodology on this form of data, including the use of singular value decompositions (SVDs), CUR decompositions, random forest, gradient boosting, bagging, voxel-based morphometry, and support vector machines as well as important insights into the value, and potentially lack thereof, of imaging biomarkers of disease. The key results include the CUR-based decomposition of the rs-fc-fMRI along with gradient boosting and the prediction algorithm based on a motor network parcellation and random forest algorithm. We conjecture that the CUR decomposition is largely diagnosing common population directions of head motion. Of note, a byproduct of this research is a potential automated method for detecting subtle in-scanner motion. The final prediction algorithm, a weighted combination of several algorithms, had an external test set specificity of 94% with sensitivity of 21%. The most promising imaging biomarker was a correlation graph from a motor network parcellation. In summary, we have undertaken a large-scale statistical exploratory prediction exercise on the unique ADHD 200 data set. The exercise produced several potential leads for future scientific exploration of the neurological basis of ADHD.