Extraction and Analysis of Dynamic Functional Connectome Patterns in Migraine Sufferers: A Resting-State fMRI Study

Artificial Intelligence and Virtual Reality in Headache Disorder Diagnosis, Classification, and Management

PURPOSE OF REVIEW

This review provides an overview of the current and future role of artificial intelligence (AI) and virtual reality (VR) in addressing the complexities inherent to the diagnosis, classification, and management of headache disorders.

RECENT FINDINGS

Through machine learning and natural language processing approaches, AI offers unprecedented opportunities to identify patterns within complex and voluminous datasets, including brain imaging data. This technology has demonstrated promise in optimizing diagnostic approaches to headache disorders and automating their classification, an attribute particularly beneficial for non-specialist providers. Furthermore, AI can enhance headache disorder management by enabling the forecasting of acute events of interest, such as migraine headaches or medication overuse, and by guiding treatment selection based on insights from predictive modeling. Additionally, AI may facilitate the streamlining of treatment efficacy monitoring and enable the automation of real-time treatment parameter adjustments. VR technology, on the other hand, offers controllable and immersive experiences, thus providing a unique avenue for the investigation of the sensory-perceptual symptomatology associated with certain headache disorders. Moreover, recent studies suggest that VR, combined with biofeedback, may serve as a viable adjunct to conventional treatment. Addressing challenges to the widespread adoption of AI and VR in headache medicine, including reimbursement policies and data privacy concerns, mandates collaborative efforts from stakeholders to enable the equitable, safe, and effective utilization of these technologies in advancing headache disorder care. This review highlights the potential of AI and VR to support precise diagnostics, automate classification, and enhance management strategies for headache disorders.

Disrupted Brain Functional Status in Patients with Reversible Cerebral Vasoconstriction Syndrome

OBJECTIVES

The aim of this study was to investigate the functional networks in subjects with reversible cerebral vasoconstriction syndrome (RCVS) using resting-state functional magnetic resonance imaging (rs-fMRI).

METHODS

We prospectively recruited patients with RCVS and healthy controls (HCs) between February 2017 and April 2021. The rs-fMRI data were analyzed using graph theory methods. We compared node-based global and regional topological metrics (Bundle 1) and network-based intranetwork and internetwork connectivity (Bundle 2) between RCVS patients and HCs. We also explored the associations of clinical and vascular (ie, the Lindegaard index, LI) parameters with significant rs-fMRI metrics.

RESULTS

A total of 104 RCVS patients and 93 HCs were included in the final analysis. We identified significantly decreased local efficiency of the left dorsal anterior insula (dAI; p = 0.0005) in RCVS patients within 30 days after disease onset as compared to HCs, which improved 1 month later. RCVS patients also had increased global efficiency (p = 0.009) and decreased average degree centrality (p = 0.045), clustering coefficient (p = 0.033), and assortativity values (p = 0.003) in node-based analysis. In addition, patients with RCVS had increased internetwork connectivity of the default mode network (DMN) with the salience (p = 0.027) and dorsal attention (p = 0.016) networks. Significant correlations between LI and regional local efficiency in left dAI (rs  = -0.418, p = 0.042) was demonstrated.

INTERPRETATION

The significantly lower local efficiency of the left dAI, suggestive of impaired central autonomic modulation, was negatively correlated with vasoconstriction severity, which is highly plausible for the pathogenesis of RCVS. ANN NEUROL 2023;94:772-784.

Classification of Migraine Using Static Functional Connectivity Strength and Dynamic Functional Connectome Patterns: A Resting-State fMRI Study

Migraine is a common, chronic dysfunctional disease with recurrent headaches. Its etiology and pathogenesis have not been fully understood and there is a lack of objective diagnostic criteria and biomarkers. Meanwhile, resting-state functional magnetic resonance imaging (RS-fMRI) is increasingly being used in migraine research to classify and diagnose brain disorders. However, the RS-fMRI data is characterized by a large amount of data information and the difficulty of extracting high-dimensional features, which brings great challenges to relevant studies. In this paper, we proposed an automatic recognition framework based on static functional connectivity (sFC) strength features and dynamic functional connectome pattern (DFCP) features of migraine sufferers and normal control subjects, in which we firstly extracted sFC strength and DFCP features and then selected the optimal features using the recursive feature elimination based on the support vector machine (SVM−RFE) algorithm and, finally, trained and tested a classifier with the support vector machine (SVM) algorithm. In addition, we compared the classification performance of only using sFC strength features and DFCP features, respectively. The results showed that the DFCP features significantly outperformed sFC strength features in performance, which indicated that DFCP features had a significant advantage over sFC strength features in classification. In addition, the combination of sFC strength and DFCP features had the optimal performance, which demonstrated that the combination of both features could make full use of their advantage. The experimental results suggested the method had good performance in differentiating migraineurs and our proposed classification framework might be applicable for other mental disorders.

The Patent Foramen Ovale and Migraine: Associated Mechanisms and Perspectives from MRI Evidence

Migraine is a common neurological disease with a still-unclear etiology and pathogenesis. Patent foramen ovale (PFO) is a kind of congenital heart disease that leads to a right-to-left shunt (RLS). Although previous studies have shown that PFO has an effect on migraine, a clear conclusion about the link between PFO and migraine is lacking. We first summarized the PFO potential mechanisms associated with migraine, including microembolus-triggered cortical spreading depression (CSD), the vasoactive substance hypothesis, impaired cerebral autoregulation (CA), and a common genetic basis. Further, we analyzed the changes in brain structure and function in migraine patients and migraine patients with PFO. We found that in migraine patients with PFO, the presence of PFO may affect the structure of the cerebral cortex and the integrity of white matter, which is mainly locked in subcortical, deep white matter, and posterior circulation, and may lead to changes in brain function, such as cerebellum and colliculus, which are involved in the processing and transmission of pain. In summary, this paper provides neuroimaging evidence and new insights into the correlation between PFO and migraine, which will help to clarify the etiology and pathogenesis of migraine, and aid in the diagnosis and treatment of migraine in the future.

Dynamical Complexity Fingerprints of Occupation-Dependent Brain Functional Networks in Professional Seafarers

The complexity derived from resting-state functional magnetic resonance imaging (rs-fMRI) data has been applied for exploring cognitive states and occupational neuroplasticity. However, there is little information about the influence of occupational factors on dynamic complexity and topological properties of the connectivity networks. In this paper, we proposed a novel dynamical brain complexity analysis (DBCA) framework to explore the changes in dynamical complexity of brain activity at the voxel level and complexity topology for professional seafarers caused by long-term working experience. The proposed DBCA is made up of dynamical brain entropy mapping analysis and complex network analysis based on brain entropy sequences, which generate the dynamical complexity of local brain areas and the topological complexity across brain areas, respectively. First, the transient complexity of voxel-wise brain map was calculated; compared with non-seafarers, seafarers showed decreased dynamic entropy values in the cerebellum and increased values in the left fusiform gyrus (BA20). Further, the complex network analysis based on brain entropy sequences revealed small-worldness in terms of topological complexity in both seafarers and non-seafarers, indicating that it is an inherent attribute of human the brain. In addition, seafarers showed a higher average path length and lower average clustering coefficient than non-seafarers, suggesting that the information processing ability is reduced in seafarers. Moreover, the reduction in efficiency of seafarers suggests that they have a less efficient processing network. To sum up, the proposed DBCA is effective for exploring the dynamic complexity changes in voxel-wise activity and region-wise connectivity, showing that occupational experience can reshape seafarers’ dynamic brain complexity fingerprints.