Citations

Background Photophobia is experienced by most individuals with migraine, and it is frequently the most bothersome symptom other than headache. Light is not perceived uniformly; spectral composition and intensity influence discomfort and can exacerbate symptoms. While monochromatic green light shows therapeutic potential, it appears visually unnatural and is impractical for daily use. This study aimed to determine whether spectrally tailored white light, more visually acceptable in everyday environments, reduces light sensitivity among those with migraine. Methods Twenty adults (18–44 years) with episodic migraine completed two research sessions: one during an acute migraine attack and one between migraine attacks. Participants were exposed to four spectrally distinct white light conditions (red-, green-, cyan-, and blue-enriched) in a randomized order delivered at ten intensity levels (50–590 lux). After each exposure, visual discomfort was rated on a 0–10 scale. Pupil size was measured using a pupillometer. Repeated-measures ANOVAs examined the effects of light spectrum, intensity, and migraine state on visual discomfort and pupil response. Results Migraine attack status significantly increased visual discomfort ( F (1,19) = 25.84, p < .001, η 2 = .576). White light spectrum ( F (3,57) = 12.47, p < .001, η 2 = .396) and light intensity ( F (9171) = 124.30, p < .001, η 2 = .867) were associated with intensity of visual discomfort. Post-hoc analyses indicated that visual discomfort increased with increasing light intensity, especially at higher light intensities. Among all tested spectra, green-enriched white light resulted in the least visual discomfort; blue-, red-, and cyan-enriched white light produced significantly higher discomfort (all p < .001). Pupil size varied by spectrum ( F (3,57) = 14.13, p < .001, η 2 = .426), with green-enriched white light producing the largest pupil size. Conclusion Spectral composition, light intensity, and migraine state jointly influence both subjective and physiological responses to light. Across lighting spectra, lower light intensity was consistently associated with reduced visual discomfort, indicating greater visual comfort at lower intensities. These results identify green-enriched white light at lower intensities as a visually acceptable, migraine-conscious lighting option with potential for real-world application.

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 &lt; 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.

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 Objectives The aim of this work was to develop an American Headache Society position statement addressing diagnostic screening for migraine among girls and women. Background Despite its high prevalence and substantial negative impacts, migraine is underdiagnosed and undertreated. Diagnostic screening for migraine enables more patients to receive timely, appropriate, and effective management. Methods Development of this position statement followed the rules established by the American Headache Society Guidelines Committee. The published literature was reviewed to determine if migraine meets criteria for when disease screening is justified, to guide recommendations for screening tools, and to determine subpopulation(s) for which migraine screening is indicated. After author consensus was reached, the position statement was reviewed and approved by the American Headache Society Board of Directors. Results Migraine fulfills established criteria for conditions in which screening is appropriate since it is highly prevalent, results in significant morbidity, and exerts substantial economic and social costs. Migraine incidence and prevalence are exceptionally high among girls and women during adolescence and through menopause. Furthermore, there are valid and reliable diagnostic screening methods (e.g., ID Migraine) and effective treatments that reduce migraine symptoms and disease impact. Conclusion Yearly diagnostic screening for migraine should be included as part of women's preventive healthcare services, particularly from adolescence to menopause.

Background Migraine is a highly prevalent neurological disorder with many treatment options, both pharmacological and non-pharmacological. Artificial intelligence (AI) has great potential to optimize treatment selection strategies for individual patients. This review provides an overview of AI models and the techniques used to predict migraine treatment outcomes. Methods We conducted a literature search in PubMed and examined studies that reported employing AI models to predict migraine preventive and acute treatment outcomes. We also explored incorporating AI/machine learning to enhance personalized migraine treatment strategies, including forecasting migraine attacks. Additionally, we summarized future research directions, including incorporating multimodality data, using AI frameworks for the discovery of novel treatment targets, and advancing the field with innovative AI techniques such as digital twins, conversational AI and virtual AI agents. Results Studies have employed ML and deep learning on a combination of clinical features and imaging data to predict acute or preventive migraine treatment outcomes with reported success. Continued model optimization, validation, and prospective assessment of the clinical utility of deploying ML models in real-world settings are crucial. Conclusions While AI has demonstrated success in predicting migraine treatment responses, future research incorporating novel AI techniques and diverse data sources could pave the way to advance personalized migraine treatment.

Migraine is one of the most disabling diseases worldwide, especially when it transforms into chronic migraine, which is often associated with medication overuse and can become resistant or even refractory to treatments. Molecular, neuroimaging and neurophysiological changes have been described in chronic migraine, some of which might not be fully reversible with preventive treatment. For these reasons, we should aim to prevent this transition, and initiate preventive treatment before disease becomes refractory and burden increases. Preventive migraine treatments are often delayed because of access to care, stigma leading to undertreatment and patients’ reluctance as a result of fear of side effects and, in some cases, fear of being labeled as chronically ill. With the availability of effective and well-tolerated preventive treatments, we must shift our mindset and take advantage of new opportunities to initiate preventive treatment earlier. In this International Headache Society position statement, we propose a migraine preventive strategy under the idea of shifting from reactive treatment once disability is established (prevention of attacks), to proactive, individualized prevention initiated early with safe, effective and tolerable therapies (prevention of disease progression). This approach is based on 1) promoting the early initiation of effective and tolerable preventive therapies, starting from two to four monthly migraine days in line with the majority of current guidelines and recommendations and 2) fostering longitudinal studies to gather more evidence on the potential benefit of early prevention, with the final goal of improving patient outcomes, promoting excellent migraine care, enhancing individual and social well-being, and, ultimately, preventing migraine progression and preserving brain health.

Background This systematic review and meta-analysis synthesized migraine-related disability outcomes according to headache frequency subclassifications, including low-frequency episodic migraine (LFEM), high-frequency episodic migraine (HFEM) and chronic migraine (CM). Methods We searched the PubMed and Cochrane Library (CENTRAL) up to 16 October 2024 for peer-reviewed non-interventional studies reporting migraine-related disability outcomes in CM and subclassifications of episodic migraine (e.g. LFEM and HFEM). Eligible studies with an HFEM subgroup were grouped by headache frequency measure (monthly migraine days [MMD] or monthly headache days [MHD]), HFEM subgroup, disability parameter and study setting. Random-effects meta-analyses were conducted on groups with three or more studies, with the results presented in forest plots. Risk of bias was assessed using Joanna Briggs Institute tools. Results Of the 32 included studies, 27 were grouped, yielding five meta-analysis groups containing three or more studies. All five groups had an HFEM subgroup of 8–14 MHD. Accordingly, we classified LFEM as 0–7 MHD and CM as ≥15 MHD. Ten studies contributed data to the five meta-analysis groups. Estimated pooled values are reported by headache frequency subgroup for each meta-analysis group: LFEM (95% confidence interval [CI]), HFEM (95% CI) and CM (95% CI). For meta-analysis group 1, four population-based studies reported Migraine Disability Assessment (MIDAS) Grade IV proportions, with pooled values of 11.1% (7.1–17.1), 43.9% (31.8–56.9) and 57.5% (42.7–71.1), respectively. For meta-analysis group 2, five population-based studies documented Work Productivity and Activity Impairment (WPAI) outcomes. Pooled mean overall work productivity impairment (OWPI) scores were 36.9% (30.8–43.1), 44.7% (38.4–51.0) and 52.0% (47.7–56.3), respectively. Pooled mean activity impairment (AI) scores were 36.4% (33.7–39.1), 46.4% (42.8–50.0) and 53.5% (52.1–54.8), respectively. For meta-analysis group 3, three clinic-based studies presented MIDAS Grade IV proportions. Pooled values were 15.0% (4.4–40.5), 42.4% (17.1–72.4) and 65.7% (30.3–89.4), respectively. For meta-analysis group 4, three clinic-based studies reported WPAI outcomes. Pooled mean OWPI scores were 28.8% (21.6–35.9), 40.2% (36.2–44.2) and 49.6% (46.3–52.9), respectively. Pooled mean AI scores were 29.4% (21.9–36.9), 43.5% (39.0–48.1) and 51.6% (48.8–54.4), respectively. For meta-analysis group 5, three clinic-based studies detailed MIDAS scores. Pooled mean scores were 10.7 (3.9–17.5), 23.9 (9.4–38.4) and 49.6 (15.8–83.3), respectively. Conclusions This study showed a pattern of increasing migraine-related disability with rising headache frequency. Regardless of study setting, our meta-analyses also suggested a severe level of disability in many individuals (42%–44%) with HFEM, highlighting an unmet need for more effective migraine management. Disability burden and headache frequency should both be considered when determining treatment needs and therapy access, particularly for patients with HFEM. Study Registration: INPLASY2024120039.