The value of brain MRI functional connectivity data in a machine learning classifier for distinguishing migraine from persistent post-traumatic headache

Current and prospective roles of magnetic resonance imaging in mild traumatic brain injury

There is unmet clinical need for biomarkers to predict recovery or the development of long-term sequelae of mild traumatic brain injury, a highly prevalent condition causing a constellation of disabling symptoms. A substantial proportion of patients live with long-lasting sequelae affecting their quality of life and ability to work. At present, symptoms can be assessed through clinical tests; however, there are no imaging or laboratory tests fully reflective of pathophysiology routinely used by clinicians to characterize post-concussive symptoms. Magnetic resonance imaging has potential to link subtle pathophysiological alterations to clinical outcomes. Here, we review the state of the art of MRI research in adults with mild traumatic brain injury and provide recommendations to facilitate transition into clinical practice. Studies utilizing MRI can inform on pathophysiology of mild traumatic brain injury. They suggest presence of early cytotoxic and vasogenic oedema. They also show that mild traumatic brain injury results in cellular injury and microbleeds affecting the integrity of myelin and white matter tracts, all processes that appear to induce delayed vascular reactions and functional changes. Crucially, correlates between MRI parameters and post-concussive symptoms are emerging. Clinical sequences such as T1-weighted MRI, susceptibility-weighted MRI or fluid attenuation inversion recovery could be easily implementable in clinical practice, but are not sufficient, in isolation for prognostication. Diffusion sequences have shown promises and, although in need of analysis standardization, are a research priority. Lastly, arterial spin labelling is emerging as a high-utility research as it could become useful to assess delayed neurovascular response and possible long-term symptoms.

Functional Magnetic Resonance Imaging of Post-Traumatic Headache: A Systematic Review

PURPOSE OF REVIEW

To evaluate existing functional magnetic resonance imaging (fMRI) studies on post-traumatic headache (PTH) following traumatic brain injury (TBI).

RECENT FINDINGS

We conducted a systematic search of PubMed and Embase databases from inception to February 1, 2024. Eligible fMRI studies were required to include adult participants diagnosed with acute or persistent PTH post-TBI in accordance with any edition of the International Classification of Headache Disorders. We identified five eligible fMRI studies: two on acute PTH and three on persistent PTH. These studies assessed resting-state functional connectivity involving comparisons with one or more of the following groups: people with migraine, those with mild TBI but no PTH, and healthy controls. In acute PTH, studies focused exclusively on functional connectivity between the periaqueductal gray or hypothalamus and other brain regions. In persistent PTH, evidence of altered functional connectivity was identified primarily within cingulate, sensorimotor, and visual regions, indicating a hypersensitivity to sensory stimuli in PTH. Despite these insights, the fMRI data remains sparse and is limited by inconsistent results and small samples. The paucity of fMRI studies on PTH limits our understanding of its neurobiological basis. The available evidence suggests that alterations in functional connectivity occur within brain areas involved in emotional and sensory discriminative aspects of pain processing. However, inconsistent results and small sample sizes underscore a critical need for larger, more rigorous fMRI studies. Future studies should also consider using task-based fMRI to investigate possible hypersensitivity to different sensory stimuli in PTH after TBI.

Migraine aura discrimination using machine learning: an fMRI study during ictal and interictal periods

Functional magnetic resonance imaging (fMRI) studies on migraine with aura are challenging due to the rarity of patients with triggered cases. This study optimized methodologies to explore differences in ictal and interictal spatiotemporal activation patterns based on visual stimuli using fMRI in two patients with unique aura triggers. Both patients underwent separate fMRI sessions during the ictal and interictal periods. The Gaussian Process Classifier (GPC) was used to differentiate these periods by employing a machine learning temporal embedding approach and spatiotemporal activation patterns based on visual stimuli. When restricted to visual and occipital regions, GPC had an improved performance, with accuracy rates for patients A and B of roughly 86-90% and 77-81%, respectively (p < 0.01). The algorithm effectively differentiated visual stimulation and rest periods and identified times when aura symptoms manifested, as evident from the varying predicted probabilities in the GPC models. These findings contribute to our understanding of the role of visual processing and brain activity patterns in migraine with aura and the significance of temporal embedding techniques in examining aura phenomena. This finding has implications for diagnostic tools and therapeutic techniques, especially for patients suffering from aura symptoms.

Artificial intelligence and headache

BACKGROUND AND METHODS

In this narrative review, we introduce key artificial intelligence (AI) and machine learning (ML) concepts, aimed at headache clinicians and researchers. Thereafter, we thoroughly review the use of AI in headache, based on a comprehensive literature search across PubMed, Embase and IEEExplore. Finally, we discuss limitations, as well as ethical and political perspectives.

RESULTS

We identified six main research topics. First, natural language processing can be used to effectively extract and systematize unstructured headache research data, such as from electronic health records. Second, the most common application of ML is for classification of headache disorders, typically based on clinical record data, or neuroimaging data, with accuracies ranging from around 60% to well over 90%. Third, ML is used for prediction of headache disease trajectories. Fourth, ML shows promise in forecasting of headaches using self-reported data such as triggers and premonitory symptoms, data from wearable sensors and external data. Fifth and sixth, ML can be used for prediction of treatment responses and inference of treatment effects, respectively, aiming to optimize and individualize headache management.

CONCLUSIONS

The potential uses of AI and ML in headache are broad, but, at present, many studies suffer from poor reporting and lack out-of-sample evaluation, and most models are not validated in a clinical setting.

Posttraumatic Headache

OBJECTIVE

This article provides an overview of the epidemiology, diagnosis, clinical presentation, pathophysiology, prognosis, and treatment of posttraumatic headache attributed to mild traumatic brain injury (mTBI).

LATEST DEVELOPMENTS

The International Classification of Headache Disorders, Third Edition requires that posttraumatic headache begin within 7 days of the inciting trauma. Although posttraumatic headache characteristics and associated symptoms vary, most commonly there is substantial overlap with symptoms of migraine or tension-type headache. New insights into posttraumatic headache pathophysiology suggest roles for neuroinflammation, altered pain processing and modulation, and changes in brain structure and function. Although the majority of posttraumatic headache resolves during the acute phase, about one-third of individuals have posttraumatic headache that persists for at least several months. Additional work is needed to identify predictors and early markers of posttraumatic headache persistence, but several potential predictors have been identified such as having migraine prior to the mTBI, the total number of TBIs ever experienced, and the severity of initial symptoms following the mTBI. Few data are available regarding posttraumatic headache treatment; studies investigating different treatments and the optimal timing for initiating posttraumatic headache treatment are needed.

ESSENTIAL POINTS

Posttraumatic headache begins within 7 days of the causative injury. The characteristics of posttraumatic headache most commonly resemble those of migraine or tension-type headache. Posttraumatic headache persists for 3 months or longer in about one-third of individuals. Additional studies investigating posttraumatic headache treatment are needed.

Migraine headache (MH) classification using machine learning methods with data augmentation

Migraine headache, a prevalent and intricate neurovascular disease, presents significant challenges in its clinical identification. Existing techniques that use subjective pain intensity measures are insufficiently accurate to make a reliable diagnosis. Even though headaches are a common condition with poor diagnostic specificity, they have a significant negative influence on the brain, body, and general human function. In this era of deeply intertwined health and technology, machine learning (ML) has emerged as a crucial force in transforming every aspect of healthcare, utilizing advanced facilities ML has shown groundbreaking achievements related to developing classification and automatic predictors. With this, deep learning models, in particular, have proven effective in solving complex problems spanning computer vision and data analytics. Consequently, the integration of ML in healthcare has become vital, especially in developing countries where limited medical resources and lack of awareness prevail, the urgent need to forecast and categorize migraines using artificial intelligence (AI) becomes even more crucial. By training these models on a publicly available dataset, with and without data augmentation. This study focuses on leveraging state-of-the-art ML algorithms, including support vector machine (SVM), K-nearest neighbors (KNN), random forest (RF), decision tree (DST), and deep neural networks (DNN), to predict and classify various types of migraines. The proposed models with data augmentations were trained to classify seven various types of migraine. The proposed models with data augmentations were trained to classify seven various types of migraine. The revealed results show that DNN, SVM, KNN, DST, and RF achieved an accuracy of 99.66%, 94.60%, 97.10%, 88.20%, and 98.50% respectively with data augmentation highlighting the transformative potential of AI in enhancing migraine diagnosis.

Grey matter structure within the visual networks in migraine with aura: multivariate and univariate analyses

BACKGROUND

The visual cortex is involved in the generation of migraine aura. Voxel-based multivariate analyses applied to this region may provide complementary information about aura mechanisms relative to the commonly used mass-univariate analyses.

METHODS

Structural images constrained within the functional resting-state visual networks were obtained in migraine patients with (n = 50) and without (n = 50) visual aura and healthy controls (n = 50). The masked images entered a multivariate analysis in which Gaussian process classification was used to generate pairwise models. Generalizability was assessed by five-fold cross-validation and non-parametric permutation tests were used to estimate significance levels. A univariate voxel-based morphometry analysis was also performed.

RESULTS

A multivariate pattern of grey matter voxels within the ventral medial visual network contained significant information related to the diagnosis of migraine with visual aura (aura vs. healthy controls: classification accuracy = 78%, p < 0.001; area under the curve = 0.84, p < 0.001; migraine with aura vs. without aura: classification accuracy = 71%, p < 0.001; area under the curve = 0.73, p < 0.003). Furthermore, patients with visual aura exhibited increased grey matter volume in the medial occipital cortex compared to the two other groups.

CONCLUSIONS

Migraine with visual aura is characterized by multivariate and univariate patterns of grey matter changes within the medial occipital cortex that have discriminative power and may reflect pathological mechanisms.

Towards precision medicine in migraine: Recent therapeutic advances and potential biomarkers to understand heterogeneity and treatment response

After 35 years since the introduction of the International Classification of Headache Disorders (ICHD), we are living in the era of the second great revolution in migraine therapies. First, discoveries of triptans provided a breakthrough in acute migraine treatment utilizing bench-to-bedside research results on the role of serotonin in migraine. Next, the discovery of the role of neuropeptides, more specifically calcitonin gene-related peptide (CGRP) in migraine attack led to the development of anti-CGRP therapies that are effective both in acute and preventive treatment, and are also able to reduce migraine-related burden. Here, we reviewed the most recent clinical studies and real-world data on available migraine-specific medications, including triptans, ditants, gepants and anti-CGRP monoclonal antibodies. Novel drug targets, such as PACAP and amylins were also discussed. To address the main challenges of migraine therapy, the high heterogeneity of people with migraine, the prevalent presence of various comorbid disorders, and the insufficient medical care of migraine patients were covered. Promising novel approaches from the fields of omics, blood and saliva biomarker, imaging and provocation studies might bring solutions for these challenges with the potential to identify further drug targets, distinguish more homogeneous patient subgroups, contribute to more optimal drug selection strategies, and detect biomarkers in association with headache features or predicting treatment efficacy. In the future, the combined analysis of data of different biomarker modalities with machine learning algorithms may serve precision medicine in migraine treatment.

A state-of-the-art review of functional magnetic resonance imaging technique integrated with advanced statistical modeling and machine learning for primary headache diagnosis

Primary headache is a very common and burdensome functional headache worldwide, which can be classified as migraine, tension-type headache (TTH), trigeminal autonomic cephalalgia (TAC), and other primary headaches. Managing and treating these different categories require distinct approaches, and accurate diagnosis is crucial. Functional magnetic resonance imaging (fMRI) has become a research hotspot to explore primary headache. By examining the interrelationships between activated brain regions and improving temporal and spatial resolution, fMRI can distinguish between primary headaches and their subtypes. Currently the most commonly used is the cortical brain mapping technique, which is based on blood oxygen level-dependent functional magnetic resonance imaging (BOLD-fMRI). This review sheds light on the state-of-the-art advancements in data analysis based on fMRI technology for primary headaches along with their subtypes. It encompasses not only the conventional analysis methodologies employed to unravel pathophysiological mechanisms, but also deep-learning approaches that integrate these techniques with advanced statistical modeling and machine learning. The aim is to highlight cutting-edge fMRI technologies and provide new insights into the diagnosis of primary headaches.

A Narrative Review of Visual Hallucinations in Migraine and Epilepsy: Similarities and Differences in Children and Adolescents

Since the earliest descriptions of the simple visual hallucinations in migraine patients and in subjects suffering from occipital lobe epilepsy, several important issues have arisen in recognizing epileptic seizures of the occipital lobe, which often present with symptoms mimicking migraine. A detailed quantitative and qualitative clinical scrutiny of timing and characteristics of visual impairment can contribute to avoiding mistakes. Differential diagnosis, in children, might be challenging because of the partial clinical, therapeutic, and pathophysiological overlaps between the two diseases that often coexist. Ictal elementary visual hallucinations are defined by color, shape, size, location, movement, speed of appearance and duration, frequency, and associated symptoms and their progression. The evaluation of the distinctive clinical features of visual aura in migraine and visual hallucinations in occipital epilepsy could contribute to understanding the pathogenetic mechanisms of these two conditions. This paper aims to critically review the available scientific evidence on the main clinical criteria that address diagnosis, as well as similarities and differences in the pathophysiological mechanisms underlying the visual impairment in epilepsy and migraine.