Chong, Catherine D.

White matter hyperintensities (WMHs) are common MRI findings and established markers of cerebral small-vessel disease associated with stroke, cognitive decline, and vascular risk factors. Several studies have suggested that individuals with migraine, particularly migraine with aura (MA), may have an increased burden of WMHs compared with individuals without migraine. Early population-based studies and meta-analyses reported a higher prevalence of WMHs in migraine, whereas more recent large neuroimaging cohorts have reported conflicting findings or no association. Differences in study design, migraine ascertainment, MRI acquisition parameters, WMH quantification methods, and adjustment for vascular risk factors complicate interpretation of the existing literature. An updated systematic review focusing on methodologically comparable population-based cohorts is therefore warranted. The primary objective of this systematic review and meta-analysis is to determine whether adults with migraine have a higher prevalence or burden of WMHs on MRI than non-migraine controls. Secondary objectives include evaluating associations according to migraine subtype (MA vs. migraine without aura and episodic vs. chronic migraine), sex, WMH location, age, and MRI acquisition or WMH quantification methods, as well as examining longitudinal WMH progression where available. We will include population-based cross-sectional or longitudinal cohort studies of adults undergoing brain MRI with sequences suitable for WMH detection. Migraine exposure may be defined using International Classification of Headache Disorders criteria, structured interviews, validated questionnaires, physician diagnosis, or ICD codes. Controls must originate from the same source population. Searches will be conducted in PubMed/MEDLINE, EMBASE, Web of Science, and Scopus. Study selection, data extraction, and risk-of-bias assessment will be performed independently by two reviewers using Covidence, and risk of bias will be evaluated using the ROBINS-E tool. Because WMH burden is reported using heterogeneous metrics across studies, the primary synthesis will use a precision-weighted direction-of-effect approach, in which each study contributes the direction of the association, weighted by statistical precision. Where sufficiently comparable outcomes are available, random-effects meta-analysis will be performed. Sensitivity analyses will explore the influence of diagnostic criteria, MRI field strength, and confounder adjustment. This review will provide an updated and methodologically rigorous synthesis of the evidence on the association between migraine and WMHs.

Abstract To enhance the prediction of traumatic brain injury (mTBI) outcomes, we propose a deep learning approach that integrates brain computed tomography (CT) scans with corresponding synthetic T1-weighted magnetic resonance imaging (T1-MRI). Our method significantly outperforms the prediction using CT scans alone. TRACK-TBI Pilot dataset, which includes imaging and clinical outcome data from patients with TBI, is studied. The hypothesis is brain CT and T1-MRI complement each other and together will improve TBI prognosis compared to using either CT or T1-MRI alone. Since CT and T1-MRI may not be available for the same individual, we employed a specialized version of a generative adversarial network (GAN), known as fixed-point GAN (FP-GAN). FP-GAN was trained using unpaired CT and T1-MRI scans to generate synthetic T1-MRIs from real CT scans. This process produced pseudo-paired CT-MRI data, which was then used to train a deep learning classifier for outcome prediction. The classifier consists of dual parallel 3D ResNet-18 models, each independently processing T1-MRI and CT scans. We used Glasgow Outcome Scale-Extended (GOSE) scores at 3 months post-TBI as the measure of patient outcomes. To avoid data leakage, the subjects used in FP-GAN and ResNet-18 model have no overlap. We further divided the paired data, allocating 69 samples for 5-fold cross-validation and 17 samples for testing. Prognostic performance was evaluated using the area under the receiver operating characteristic curve (AUC), F1-score (the harmonic mean of precision and recall), sensitivity (true positive rate) and specificity (true negative rate). For binary classification, we defined good recovery as GOSE ≥ 7 (positive) and poor recovery (negative) as 3 ≤ GOSE ≤ 6. Accordingly, our training set consists of 24 subjects with poor recovery and 45 subjects with good recovery, while the testing set includes 5 subjects with poor recovery and 12 subjects with good recovery. A DeLong test on AUC confirms that the improvement from incorporating synthetic T1-MRI (AUC = 0.76 ± 0.10) is statistically significant (P < 0.05) compared to using CT alone (AUC = 0.68 ± 0.13). The significant improvement from using the combination of real CT and synthetic T1-MRI in sensitivity (SEN = 0.95 ± 0.07) and overall performance metrics, such as F1-score (F1 = 0.84 ± 0.03), suggests that the proposed approach provides a robust and effective prognostic approach compared to using CT alone (SEN = 0.83 ± 0.18 and F1 = 0.76 ± 0.07). This pilot research demonstrates the potential of a deep learning-based harmonization model to bridge the gap between CT and T1-MRI in TBI assessment. By integrating synthetic T1-MRI with CT, prediction performance is substantially enhanced.

ABSTRACT Magnetic Resonance Spectroscopy Imaging (MRSI) offers spatially-resolved, neurometabolic information, acquired non-invasively at whole-brain scales from human subjects. Analysis of MRSI however, is extremely challenging. The metabolic information is highly convolved, and sparsely distributed across millions of spatial-spectral datapoints, allowing for little direct human interpretation. Conversely, the overall low signal-to-noise with high-intensity artifacts can confound unsupervised machine learning approaches. These technical barriers have left much of the potential of MRSI unrealized. We acquired MRSI data from 4 human subjects with a diagnosis of multiple sclerosis (MS), incorporating experimental design into an informed machine learning approach. MRSI acquisitions were registered to anatomical MRI to label 105k spectra from brain tissue and 162 spectra from white matter hyperintensities (WMHs), an imaging biomarker associated with MS lesions. Spectral labels were then used in contrastive principal component analysis (cPCA) to filter artifacts and background features in the MRSI data from lesion salient features and clustered into statistically significant states based on features that could be interpreted from the original data. Our approach renders MRSI data into testable representations of neurometabolism, enabling the method for fundamental and clinical research. Graphical Abstract Analysis workflow for neurometabolic profiling of MS lesions. MRSI and anatomical MRI is acquired and processed in parallel for spectral data and anatomical labels. Spectra are then labeled and separated into experimental vs background data for contrastive PCA. Spectra are clustered for similarity, further labeled, and projected onto a brain atlas for a neurometabolic view.

Aim Post-traumatic headache (PTH) attributed to mild traumatic brain injury (mTBI) frequently co-occurs with other physical, cognitive, and emotional symptoms. This study assessed associations between PTH improvement and these symptoms in individuals with acute headaches (APTH) and compared symptoms between those who had recently developed persistent PTH (PPTH) to those who had long-standing PPTH. Methods This study included 105 individuals with APTH (mean age = 43.4, SD = 15.8; 70 females, 35 males) and 46 individuals with PPTH (mean age = 38.2, SD = 10.9; 16 females, 30 males) with an average duration of 11.3 years from two prospective longitudinal studies. For those who had APTH, PTH improvement was assessed at three months post-enrollment using an electronic headache diary. Participants completed questionnaires evaluating physical (including headache symptoms, photosensitivity, hyperacusis, insomnia, autonomic symptoms, and disability), emotional (including depression, anxiety, pain catastrophizing, and post-traumatic stress disorder screening), and cognitive symptoms (including memory and attention). The APTH cohort completed questionnaires at baseline, follow-up #1 (three to four months from baseline), and follow-up #2 (six to seven months from baseline). Mixed Effects Models were used to analyze the temporal trend of symptoms among the APTH improved and non-improved groups. Results Among the 105 individuals with APTH, 60 experienced PTH improvement and 45 did not. At baseline, compared to those who had PTH improvement, those who did not have PTH improvement had higher SCAT total scores and physical subscores, greater levels of hyperacusis, pain catastrophizing, anxiety and depression. At follow-up #1 (three to four months), these individuals continued to show more pronounced physical and emotional symptoms and worse cognitive function and insomnia. Most of these group differences persisted at follow-up #2 (six to seven months). Most symptoms showed progressive improvement over three months for individuals who had PTH improvement but not for those without PTH improvement. Furthermore, individuals with long-standing PPTH showed more severe insomnia, pain catastrophizing, and PTSD compared to those who had recently developed PPTH. Conclusion Individuals with APTH who did not experience PTH improvement at three months had more severe physical, cognitive, and emotional symptoms at baseline compared to those who had PTH improvement. While most symptoms normalized in individuals with PTH improvement, symptoms overall persisted at three and at six months for those with PTH persistence. Individuals who had long-standing PPTH had more severe insomnia and more negative cognitive/emotional responses to pain compared to those who had recently developed PPTH.

Learning from multimodal data sets can leverage complementary information and lead to improved performance for prediction tasks. A commonly used strategy to account for feature correlations in high-dimensional data sets is the latent variable approach. Several latent variable methods have been proposed for multimodal data sets; however, these methods either focus on extracting a shared component across all modalities or extracting a shared component and individual components specific to each modality, overlooking correlations within partial subsets of modalities. We propose multimodal fission learning (MMFL), the first supervised latent variable model that adopts a generalizable decomposition into globally joint, partially joint, and individual components from multimodal data sets. A key strength of MMFL is a natural extension to incorporate incomplete multimodal data in either training and test phases by leveraging the learned modality structure. Through simulation studies, we demonstrate that MMFL outperforms a variety of existing multimodal algorithms under both complete modality and incomplete modality settings. We applied MMFL to two real-world case studies: early prediction of Alzheimer’s disease using neuroimaging and genetic data and predicting posttraumatic headache improvement using clinical data collected via questionnaires and brain neuroimaging data. MMFL achieved improved predictive accuracy and enhanced interpretability offering insights for within- and cross-modal relationships of multimodal data sets. History: Rema Padman served as the senior editor for this article. Funding: This research was supported by the National Institutes of Health [Grants 2R42AG053149-02A1, R01AG069453, 30AG072980, R01AG069453, and 1R61NS113315-01], the National Science Foundation [Grant DMS-2053170], and the Department of Defense [Award W81XWH-19-0534]. The grantee organization is the Northern California Institute for Research and Education. In the past, ADNI has also received funding from the National Institute of Biomedical Imaging and Bioengineering, the Canadian Institutes of Health Research, and private sector contributions through the Foundation for the National Institutes of Health including generous contributions from the following: AbbVie, Alzheimer’s Association; Alzheimer’s Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research & Development, LLC.; Johnson & Johnson Pharmaceutical Research & Development LLC.; Lumosity; Lundbeck; Merck & Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. Data Ethics & Reproducibility Note: The code capsule is available at https://github.com/lingchm/MMFL and in the e-Companion to this article (available at https://doi.org/10.1287/ijds.2024.0059 ).

Abstract Background Post-traumatic headache (PTH) is a common acute and persistent symptom following mild traumatic brain injury (mTBI). Symptoms of cutaneous allodynia and presence of nociceptive sensitization might be associated with acute PTH and its persistence. The objectives of this study were to compare allodynia symptoms and cutaneous heat pain thresholds amongst males and females with acute PTH to healthy controls (HC) and determine if pain thresholds and allodynia symptoms are associated with PTH outcomes. Methods This prospective longitudinal study enrolled 139 adults with acute PTH attributed to mTBI as defined by the International Classification of Headache Disorders and 95 HC. All PTH participants completed a baseline research visit near PTH onset and a follow-up visit three to four months later. All PTH participants and a subset of HC completed the Allodynia Symptom Checklist (ASC-12) at each research visit. A different subset of the participants underwent quantitative sensory testing (QST) during baseline, 4-week, and 16-week research visits to quantify cutaneous heat pain thresholds at the forehead and forearms. Data from daily headache diaries were used to determine longitudinal PTH improvement versus non-improvement at three months. ASC-12 score and pain threshold comparisons were made between PTH and HC groups, PTH improved versus non-improved cohorts, and between PTH males and females. Results Participants with PTH had an average age of 42.6 years and 64.0% were female. HC had an average age of 40.0 years and 65.3% were female. At the first visit, PTH participant ASC-12 scores averaged 3.6 versus 0.1 amongst HC, p < 0.001. 44.8% of PTH participants had headache improvement at 3 months. ASC-12 scores were higher in the PTH non-improved versus improved group at baseline (4.0 versus 2.4, p = 0.038) and 3-month follow-up (3.4 versus 1.9, p = 0.012). ASC-12 scores were higher in females than males at baseline (4.7 versus 1.6, p < 0.001) and 3-months (3.9 versus 1.2, p < 0.001). Cutaneous heat pain thresholds at the forehead and forearm did not differ between any group. Conclusions PTH attributed to mTBI is associated with symptoms of cutaneous allodynia. Greater allodynia symptoms are present in females with PTH compared to males and may be associated with PTH non-improvement.

AbstractBackgroundPrevious publications have described the presence and severity of insomnia amongst those with persistent post‐traumatic headache (PPTH), but there has been a paucity of studies investigating insomnia during the acute phase of post‐traumatic headache (APTH). The primary study objective was to investigate insomnia symptoms and their severity in individuals with APTH due to mild traumatic brain injury (mTBI), and the secondary objective was to assess how psychological factors, sensory hypersensitivities, headache burden, and cognitive performance might associate with insomnia.MethodsIn this clinic‐based, cross‐sectional study, 82 individuals with APTH due to mTBI and 82 healthy controls (HC) were included. Participants completed the Insomnia Severity Index (ISI), Trail Making Test (TMT A and B), 12‐item Allodynia Symptom Checklist (ASC‐12), State–Trait Anxiety Inventory, Photosensitivity Assessment Questionnaire (PAQ), Beck Depression Inventory (BDI), Hyperacusis Questionnaire (HQ), Rey Auditory Verbal Learning Test (RAVLT), and a detailed headache characteristics questionnaire within 59 days of their mTBI to assess insomnia severity, psychological features, sensory hypersensitivities, headache symptoms, and cognitive performance. The questionnaire and test results were compared between APTH and HC groups. Within the APTH group, ISI scores were correlated with the other assessments to determine underlying clinical relationships.ResultsParticipants with APTH, evaluated an average of 27.2 days after their mTBI, had significantly higher ISI scores (median [interquartile range, IQR] score 12 [6–17]) compared to HC (0 [1.3–6], p < 0.001). Twenty‐four (29%) individuals with APTH had ISI scores categorized as moderate clinical insomnia compared to two (2%) in the HC group. Additionally, seven (9%) in the APTH group and none of the HC had ISI scores indicative of severe clinical insomnia. Those with APTH significantly differed from the HC on the BDI (median [IQR] score APTH: 9 [5–16.8] vs. HC: 2 [0–4]; p < 0.001), state anxiety (median [IQR] score APTH: 36.5 [26–45] vs. HC: 23 [20–27.5]; p < 0.001), trait anxiety (median [IQR] score APTH: 38 [27.3–46.8] vs. HC: 26 [23–30]; p < 0.001), photosensitivity (median [IQR] PAQ score APTH: 2 [1–4] vs. HC: 0 [0–1]; p < 0.001), allodynia (median [IQR] ASC‐12 score APTH: 2 [0–5.8] vs. HC: 0 [0–0], p < 0.001), hyperacusis (median [IQR] HQ score APTH: 15.5 [7–23] vs. HC: 4 [2.3–7], p < 0.001), and RAVLT‐delayed recall (median [IQR] score APTH: −0.8 [−1.5 to 0] vs. HC: −0.1 [−0.9 to 0.7], p = 0.019). For participants with APTH, the ISI was most significantly associated with the BDI (standardized regression coefficient (RC) [95% confidence interval, CI] 0.68 [0.52–0.84], p < 0.001), followed by state anxiety (RC [95% CI] 0.60 [0.42–0.78], p < 0.001), trait anxiety (RC [95% CI] 0.56 [0.37–0.74], p < 0.001), headache severity (RC [95% CI] 0.40 [0.19–0.60], p < 0.001), HQ (RC [95% CI] 0.36 [0.16–0.57], p = 0.001), and PAQ (RC [95% CI] 0.35 [0.15–0.56], p = 0.001).ConclusionsIndividuals with APTH have more symptoms of insomnia compared to HC with 38% of individuals with APTH experiencing moderate or severe insomnia symptoms. Insomnia symptoms may be associated with more severe depression, anxiety, photophobia, hyperacusis, headache severity, and cognitive impairment. To address the overall well‐being of patients with APTH, clinicians should screen for and appropriately manage insomnia along with other symptoms following mTBI.

Abstract Objectives/Background Post‐traumatic headache (PTH) is a common symptom following mild traumatic brain injury (mTBI). Currently, there is no identified way to accurately predict if, when, and at what pace a person will have PTH improvement. In our prior studies, we focused on predicting headache improvement at 3 months post‐mTBI. However, that approach may overlook individual differences in how headaches evolve over time. This study aimed to identify individual subgroups based on their headache trajectories and to develop machine‐learning (ML) models for early prediction of headache evolution. Methods Participants with acute PTH completed a daily electronic headache diary over 3 months, recording their headache‐related symptoms. Tensor decomposition was utilized to extract latent factors underlying the time‐varying symptoms. We applied clustering techniques on the latent factors to identify patient subgroups with varying headache improvement trajectory. Next, we developed an ML method to classify each individual into a headache trajectory subgroup as early as possible within the 3‐month interval. Results Seventy‐three individuals with acute PTH (mean age = 44.8 years, SD = 14.0; 50 females/23 males) were enrolled between 0 and 59 days post‐mTBI. Data from 54 individuals were used as the training cohort for model training, and 19 individuals were used as the test cohort for model evaluation. Tensor decomposition extracted two latent factors: one factor representing the overall state of PTH severity and disability and the other representing the improvement state of these symptoms over 3 months. Clustering identified four patient subgroups with distinct headache evolution trajectories: (1) severe symptoms without improvement, (2) severe symptoms with mild improvement, (3) milder symptoms with substantial improvement, and (4) mildest symptoms with mild improvement. The proposed ML model achieved 0.80 cross‐validation accuracy in classifying individuals with PTH into subgroups for the training cohort and 0.84 accuracy for the test cohort. Notably, the model required only the first 2 weeks of headache data to accurately identify the subgroup with the mildest headaches, 3 additional weeks to identify the subgroup with the most severe headaches and no improvement in 3 months, and 2 additional weeks to distinguish the remaining subgroups. Conclusion This study identified subgroups of individuals with acute PTH with distinct headache improvement trajectories. The proposed ML method accurately classified individuals into these subgroups using the minimally necessary early headache data for each person, including detecting the subgroup with the mildest headaches at 2 weeks. This approach could offer an estimated forecast of headache burden over time and could assist clinicians with determining treatment needs and eligibility for PTH clinical trials.