An fMRI-based neural marker for migraine without aura

Cerebral morphometric alterations predict the outcome of migraine diagnosis and subtyping: a radiomics analysis

BACKGROUND

This study aimed to identify cerebral radiomic features related to migraine diagnosis and subtyping into migraine with aura (MwA) and migraine without aura (MwoA) and to develop predictive models based on these markers.

METHOD

We retrospectively analyzed MR imaging from 88 migraine patients (32 MwA and 56 MwoA) and 49 healthy control subjects (HCs). Features representing the gray matter morphometry and diffusion properties were extracted from participants via histogram analysis. These features were put through an all-relevant feature selection procedure within cross-validation loops to identify features with significant discriminative power for migraine diagnosis and subtyping. Based on the selected features, the predictive ability of the random forest models constructed from the previous sample was tested in an independent sample of 30 patients (10 MwA) and 17 HCs.

RESULT

No overall differences in total brain volume or gray matter volume were revealed between patients and HCs, or between MwA and MwoA (all P values > 0.05). Six features significantly differed between patients and HCs for migraine diagnosis, and four features distinguished MwA from MwoA for subtyping (all P values < 0.001). Four features were significantly correlated with headache severity score (all P values < 0.01). Based on these relevant features, the random forest models achieved accuracies of 80.9% in distinguishing patients from HCs and 76.7% in differentiating MwA from MwoA in the testing cohort.

CONCLUSION

Our findings suggest cerebral radiomic alterations in migraine patients may potentially serve as a biomarker to assist in migraine diagnosis and subtyping, contributing to personalized treatment strategy.

CLINICAL TRIAL NUMBER

Not applicable.

fMRI Insights into Visual Cortex Dysfunction as a Biomarker for Migraine with Aura

Migraine with aura (MwA) is a common and severely disabling neurological disorder, characterised by transient yet recurrent visual disturbances, including scintillating scotomas, flickering photopsias, and complex geometric patterns. These episodic visual phenomena significantly compromise daily functioning, productivity, and overall quality of life. Despite extensive research, the underlying pathophysiological mechanisms remain only partially understood. Cortical spreading depression (CSD), a propagating wave of neuronal and glial depolarisation, has been identified as a central process in MwA. This phenomenon is triggered by ion channel dysfunction, leading to elevated intracellular calcium levels and excessive glutamate release, which contribute to widespread cortical hyperexcitability. Genetic studies, particularly involving the CACNA gene family, further implicate dysregulation of calcium channels in the pathogenesis of MwA. Recent advances in neuroimaging, particularly functional magnetic resonance imaging (fMRI), have provided critical insights into the neurophysiology of MwA. These results support the central role of CSD as a basic mechanism behind MwA and imply that cortical dysfunction endures beyond brief episodes, possibly due to chronic neuronal dysregulation or hyperexcitability. The visual cortex of MwA patients exhibits activation patterns in comparison to other neuroimaging studies, supporting the possibility that it is a disease-specific biomarker. Its distinctive sensory and cognitive characteristics are influenced by a complex interplay of cortical, vascular, and genetic factors, demonstrating the multifactorial nature of MwA. We now know much more about the pathophysiology of MwA thanks to the combination of molecular and genetic research with sophisticated neuroimaging techniques like arterial spin labelling (ASL) and fMRI. This review aims to synthesize current knowledge and analyse molecular and neurophysiological targets, providing a foundation for developing targeted therapies to modulate cortical excitability, restore neural network stability, and alleviate the burden of migraine with aura. The most important and impactful research in our field has been the focus of this review, which highlights important developments and their contributions to the knowledge and treatment of migraine with aura.

Analysis of the relationships between the degree of migraine with right-to-left shunts and changes in white matter lesions and brain structural volume

To investigate the location of white matter lesions (WMLs) in migraineurs with right‒to‒left shunts (RLS); the relationships among the severity of WMLs, changes in brain structural volume and RLS shunts; and the relationships among the severity of WMLs, changes in brain structural volume and degree of headache in RLS migraine patients. A total of 102 migraineurs with RLS admitted to the affiliated Central Hospital of Dalian University of Technology from December 2018 to December 2022 were enrolled in this study. RLS flow and the 6-item Headache Impact Test (HIT-6) scores were recorded to reflect the degree of headache. The brain structural volumes of 102 migraineurs with RLS were calculated from T1-weighted images via artificial intelligence, and the brain structural volumes of healthy controls matched according to age and sex were also calculated. The correlations among WML location, RLS, headache degree, WML severity and brain structural volume changes in migraineurs were analyzed. (1) The WMLs of migraineurs with RLS were concentrated mainly in the white matter of the lateral ventricular margin and deep white matter. Subcortical WMLs were concentrated mainly in the parietal lobe, occipital lobe and frontal lobe. (2) There were no significant differences in the WML variables of cerebral white matter high signal volume, ratio of high-signal white matter volume to whole-brain white matter volume (%) or Fazekas score among migraineurs with different RLS flows, but there were significant differences in WML variables among migraineurs with RLS with different HIT-6 grades and MIDAS grades. RLS flow, HIT-6 score and MIDAS grade were not correlated with the WML variables measured in this study. (3) There was a significant difference in the volume of the precentral gyrus between migraineurs with RLS and normal controls (P < 0.001), and there was a significant difference between migraineurs with different RLS flows and different HIT-6 scores and peripheral cerebrospinal fluid volumes. There was also a positive correlation between frontal pole structural volume and RLS flow. The volume of the precentral gyrus was negatively correlated with RLS flow, whereas the volume of the pons gyrus was positively correlated with the HIT-6 score. The volume of the temporal pole was negatively correlated with the HIT-6 score. (1) The WMLs of migraineurs with RLS were concentrated mainly in the white matter of the lateral ventricular margin and deep white matter. Subcortical WMLs were concentrated mainly in the parietal lobe, occipital lobe and frontal lobe. (2) There was no correlation between WML severity and RLS flow in migraineurs with RLS. (3) There was no correlation between WML severity and migraine severity in migraineurs with RLS. (4) Volume changes occurred in some brain structures of migraineurs with RLS. (5) Shunt flow and the degree of headache in migraineurs with RLS were correlated with structural volume changes in specific brain regions.

The abnormally increased functional connectivity of the locus coeruleus in migraine without aura patients

BACKGROUND

The neurovascular theory is thought to be one of the main pathological mechanisms of migraine. Locus coeruleus (LC) is a major node in the neurovascular pathway. Exploring the functional network characteristics of LC in migraine without aura (MwoA) patients can help us gain insight into the underlying neural mechanisms in MwoA patients.

METHODS

In this study, we used resting-state functional magnetic resonance imaging (rsfMRI) and a functional connectivity (FC) approach to explore the functional characteristics of LC in MwoA patients. 17 healthy controls (HCs) and 28 MwoA patients were included in the study. FC was calculated based on rsfMRI data collected by a 3T MRI scanner. General linear model were used to compare whether there were differences in LC brain networks between the two groups. We also utilized logistic regression to explore the role of LC functional networks in the clinical diagnosis of MwoA.

RESULTS

After general linear analysis, MwoA patients displayed increased FC from right LC to the left lingual and calcarine sulcus, as well as to the right frontal medial gyrus/orbit part, when compared with HCs. The results of the logistic regression showed that the LC FC signals were 81% accurate in distinguishing MwoA from the HCs.

CONCLUSION

Our results demonstrated that patients with MwoA exhibited significant LC FC differences in the brain areas associated with visual and cognitive function. Understanding the changes in the LC brain network in MwoA patients can provide us with new ideas to understand the pathological mechanisms of MwoA.

Identification of asymmetrical abnormalities in functional connectivity and brain network topology for migraine sufferers: A preliminary study based on resting-state fMRI data

Research on the neural mechanisms underlying brain asymmetry in patients with migraine patients using fMRI is insufficient. This study proposed using lateralized algorithms for functional connectivity and brain network topology and investigated changes in their lateralization in patients with migraine. In study 1, laterality indices of functional connectivity (LFunctionCorr) and brain network topological properties (LBetweennessCentrality, LDegree, and LStrength) were defined. Differences between migraineurs and normal subjects were compared at whole-brain, half-brain, and region levels. In study 2, laterality indices were used to classify migraine and were validated using independent samples and the segment method for repeatability. In study 3, abnormal brain regions related to migraine were extracted based on the classification results and differences analysis. Study 1 found no significant differences related to in for migraine at the whole-brain level; however, significant differences were identified at the half-brain level for the hemispheric lateralization of the LFunctionCorr, while 11 significantly different brain regions were also identified at the brain region level. Furthermore, the classification accuracy in study 2 was 0.9366. With repeated validation, the accuracy reached 0.8561. Furthermore, after extending the samples according to the segmentation strategy, the classification accuracies were improved to 0.9408 and 0.8585. Study 3 identified 10 crucial brain regions with asymmetrical specificity based on laterality indices distributed across the visual network, the frontoparietal control network, the default mode network, the salience/ventral attention network and the limbic system. The results revealed novel insights and avenues for research into the mechanisms of migraine asymmetry and showed that the laterality indices could be used as a potential diagnostic imaging marker for migraine.

Altered brainstem-cortex activation and interaction in migraine patients: somatosensory evoked EEG responses with machine learning

BACKGROUND

To gain a comprehensive understanding of the altered sensory processing in patients with migraine, in this study, we developed an electroencephalography (EEG) protocol for examining brainstem and cortical responses to sensory stimulation. Furthermore, machine learning techniques were employed to identify neural signatures from evoked brainstem-cortex activation and their interactions, facilitating the identification of the presence and subtype of migraine.

METHODS

This study analysed 1,000-epoch-averaged somatosensory evoked responses from 342 participants, comprising 113 healthy controls (HCs), 106 patients with chronic migraine (CM), and 123 patients with episodic migraine (EM). Activation amplitude and effective connectivity were obtained using weighted minimum norm estimates with spectral Granger causality analysis. This study used support vector machine algorithms to develop classification models; multimodal data (amplitude, connectivity, and scores of psychometric assessments) were applied to assess the reliability and generalisability of the identification results from the classification models.

RESULTS

The findings revealed that patients with migraine exhibited reduced amplitudes for responses in both the brainstem and cortical regions and increased effective connectivity between these regions in the gamma and high-gamma frequency bands. The classification model with characteristic features performed well in distinguishing patients with CM from HCs, achieving an accuracy of 81.8% and an area under the curve (AUC) of 0.86 during training and an accuracy of 76.2% and an AUC of 0.89 during independent testing. Similarly, the model effectively identified patients with EM, with an accuracy of 77.5% and an AUC of 0.84 during training and an accuracy of 87% and an AUC of 0.88 during independent testing. Additionally, the model successfully differentiated patients with CM from patients with EM, with an accuracy of 70.5% and an AUC of 0.73 during training and an accuracy of 72.7% and an AUC of 0.74 during independent testing.

CONCLUSION

Altered brainstem-cortex activation and interaction are characteristic of the abnormal sensory processing in migraine. Combining evoked activity analysis with machine learning offers a reliable and generalisable tool for identifying patients with migraine and for assessing the severity of their condition. Thus, this approach is an effective and rapid diagnostic tool for clinicians.

Influence of next-generation artificial intelligence on headache research, diagnosis and treatment: the junior editorial board members' vision - part 1

Artificial intelligence (AI) is revolutionizing the field of biomedical research and treatment, leveraging machine learning (ML) and advanced algorithms to analyze extensive health and medical data more efficiently. In headache disorders, particularly migraine, AI has shown promising potential in various applications, such as understanding disease mechanisms and predicting patient responses to therapies. Implementing next-generation AI in headache research and treatment could transform the field by providing precision treatments and augmenting clinical practice, thereby improving patient and public health outcomes and reducing clinician workload. AI-powered tools, such as large language models, could facilitate automated clinical notes and faster identification of effective drug combinations in headache patients, reducing cognitive burdens and physician burnout. AI diagnostic models also could enhance diagnostic accuracy for non-headache specialists, making headache management more accessible in general medical practice. Furthermore, virtual health assistants, digital applications, and wearable devices are pivotal in migraine management, enabling symptom tracking, trigger identification, and preventive measures. AI tools also could offer stress management and pain relief solutions to headache patients through digital applications. However, considerations such as technology literacy, compatibility, privacy, and regulatory standards must be adequately addressed. Overall, AI-driven advancements in headache management hold significant potential for enhancing patient care, clinical practice and research, which should encourage the headache community to adopt AI innovations.

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.

Aberrant concordance among dynamics of spontaneous brain activity in patients with migraine without aura: A multivariate pattern analysis study

Background

Alterations in the static and dynamic characteristics of spontaneous brain activity have been extensively studied to investigate functional brain changes in migraine without aura (MwoA). However, alterations in concordance among the dynamics of spontaneous brain activity in MwoA remain largely unknown. This study aimed to determine the possibilities of diagnosis based on the concordance indices.

Methods

Resting-state functional MRI scans were performed on 32 patients with MwoA and 33 matched healthy controls (HCs) in the first cohort, as well as 36 patients with MwoA and 32 HCs in the validation cohort. The dynamic indices including fractional amplitude of low-frequency fluctuation, regional homogeneity, voxel-mirrored homotopic connectivity, degree centrality and global signal connectivity were analyzed. We calculated the concordance of grey matter volume-wise (across voxels) and voxel-wise (across time windows) to quantify the degree of integration among different functional levels represented by these dynamic indices. Subsequently, the voxel-wise concordance alterations were analyzed as features for multi-voxel pattern analysis (MVPA) utilizing the support vector machine.

Results

Compared with that of HCs, patients with MwoA had lower whole-grey matter volume-wise concordance, and the mean value of volume-wise concordance was negatively correlated with the frequency of migraine attacks. The MVPA results revealed that the most discriminative brain regions were the right thalamus, right cerebellar Crus II, left insula, left precentral gyrus, right cuneus, and left inferior occipital gyrus.

Conclusions

Concordance alterations in the dynamics of spontaneous brain activity in brain regions could be an important feature in the identification of patients with MwoA.

Cracking the Chronic Pain code: A scoping review of Artificial Intelligence in Chronic Pain research

OBJECTIVE

The aim of this review is to identify gaps and provide a direction for future research in the utilization of Artificial Intelligence (AI) in chronic pain (CP) management.

METHODS

A comprehensive literature search was conducted using various databases, including Ovid MEDLINE, Web of Science Core Collection, IEEE Xplore, and ACM Digital Library. The search was limited to studies on AI in CP research, focusing on diagnosis, prognosis, clinical decision support, self-management, and rehabilitation. The studies were evaluated based on predefined inclusion criteria, including the reporting quality of AI algorithms used.

RESULTS

After the screening process, 60 studies were reviewed, highlighting AI's effectiveness in diagnosing and classifying CP while revealing gaps in the attention given to treatment and rehabilitation. It was found that the most commonly used algorithms in CP research were support vector machines, logistic regression and random forest classifiers. The review also pointed out that attention to CP mechanisms is negligible despite being the most effective way to treat CP.

CONCLUSION

The review concludes that to achieve more effective outcomes in CP management, future research should prioritize identifying CP mechanisms, CP management, and rehabilitation while leveraging a wider range of algorithms and architectures.

SIGNIFICANCE

This review highlights the potential of AI in improving the management of CP, which is a significant personal and economic burden affecting more than 30% of the world's population. The identified gaps and future research directions provide valuable insights to researchers and practitioners in the field, with the potential to improve healthcare utilization.

The Clinical Relevance of Artificial Intelligence in Migraine

Migraine is a burdensome neurological disorder that still lacks clear and easily accessible diagnostic biomarkers. Furthermore, a straightforward pathway is hard to find for migraineurs' management, so the search for response predictors has become urgent. Nowadays, artificial intelligence (AI) has pervaded almost every aspect of our lives, and medicine has not been missed. Its applications are nearly limitless, and the ability to use machine learning approaches has given researchers a chance to give huge amounts of data new insights. When it comes to migraine, AI may play a fundamental role, helping clinicians and patients in many ways. For example, AI-based models can increase diagnostic accuracy, especially for non-headache specialists, and may help in correctly classifying the different groups of patients. Moreover, AI models analysing brain imaging studies reveal promising results in identifying disease biomarkers. Regarding migraine management, AI applications showed value in identifying outcome measures, the best treatment choices, and therapy response prediction. In the present review, the authors introduce the various and most recent clinical applications of AI regarding migraine.

Brain connectome-based imaging markers for identifiable signature of migraine with and without aura

Background

Cortical spreading depression (CSD) has been considered the prominent theory for migraine with aura (MwA). However, it is also argued that CSD can exist in patients in a silent state, and not manifest as aura. Thus, the MwA classification based on aura may be questionable. This study aimed to capture whole-brain connectome-based imaging markers with identifiable signatures for MwA and migraine without aura (MwoA).

Methods

A total of 88 migraine patients (32 MwA) and 49 healthy controls (HC) underwent a diffusion tensor imaging and resting-state functional magnetic resonance imaging scan. The whole-brain structural connectivity (SC) and functional connectivity (FC) analysis was employed to extract imaging features. The extracted features were subjected to an all-relevant feature selection process within cross-validation loops to pinpoint attributes demonstrating substantial efficacy for patient categorization. Based on the identified features, the predictive ability of the random forest classifiers constructed with the 88 migraine patients' sample was tested using an independent sample of 32 migraine patients (eight MwA).

Results

Compared to MwoA and HC, MwA showed two reduced SC and six FC (five increased and one reduced) features [all P<0.01, after false discovery rate (FDR) correction], involving frontal areas, temporal areas, visual areas, amygdala, and thalamus. A total of four imaging features were significantly correlated with clinical rating scales in all patients (r=-0.38 to 0.47, P<0.01, after FDR correction). The predictive ability of the random forest classifiers achieved an accuracy of 78.1% in the external sample to identify MwA.

Conclusions

The whole-brain connectivity features in our results may serve as connectome-based imaging markers for MwA identification. The alterations of SC and FC strength provide possible evidence in further understanding the heterogeneity and mechanism of MwA which may help for patient-specific decision-making.

Abnormal Thalamo-Cortical Interactions in Overlapping Communities of Migraine: An Edge Functional Connectivity Study

OBJECTIVE

Migraine has been demonstrated to exhibit abnormal functional connectivity of large-scale brain networks, which is closely associated with its pathophysiology and has not yet been explored by edge functional connectivity. We used an edge-centric approach combined with motif analysis to evaluate higher-order communication patterns of brain networks in migraine.

METHODS

We investigated edge-centric metrics in 108 interictal migraine patients and 71 healthy controls. We parcellated the brain into networks using independent component analysis. We applied edge graph construction, k-means clustering, community overlap detection, graph-theory-based evaluations, and clinical correlation analysis. We conducted motif analysis to explore the interactions among regions, and a classification model to test the specificity of edge-centric results.

RESULTS

The normalized entropy of lateral thalamus was significantly increased in migraine, which was positively correlated with the baseline headache duration, and negatively correlated with headache duration reduction following preventive medications at 3-month follow-up. Network-wise entropy of the sensorimotor network was significantly elevated in migraine. The community similarity between lateral thalamus and postcentral gyrus was enhanced in migraine. Migraine patients showed overrepresented L-shape and diverse motifs, and underrepresented forked motifs with lateral thalamus serving as the reference node. Furthermore, migraine patients presented with overrepresented L-shape triads, where the postcentral gyrus shared different edges with the lateral thalamus. The classification model showed that entropy of the lateral thalamus had the highest discriminative power, with an area under the curve of 0.86.

INTERPRETATION

Our findings indicated an abnormal higher-order thalamo-cortical communication pattern in migraine patients. The thalamo-cortical-somatosensory disturbance of concerted working may potentially lead to aberrant information flow and deficit pain processing of migraine. ANN NEUROL 2023;94:1168-1181.

Persistent post-COVID headache is associated with suppression of scale-free functional brain dynamics in non-hospitalized individuals

INTRODUCTION

Post-acute coronavirus disease 2019 (COVID-19) syndrome (PACS) is a growing concern, with headache being a particularly debilitating symptom with high prevalence. The long-term effects of COVID-19 and post-COVID headache on brain function remain poorly understood, particularly among non-hospitalized individuals. This study focused on the power-law scaling behavior of functional brain dynamics, indexed by the Hurst exponent (H). This measure is suppressed during physiological and psychological distress and was thus hypothesized to be reduced in individuals with post-COVID syndrome, with greatest reductions among those with persistent headache.

METHODS

Resting-state blood oxygenation level-dependent (BOLD) functional magnetic resonance imaging data were collected for 57 individuals who had COVID-19 (32 with no headache, 14 with ongoing headache, 11 recovered) and 17 controls who had cold and flu-like symptoms but  tested negative for COVID-19. Individuals were assessed an average of 4-5 months after COVID testing, in a cross-sectional, observational study design.

RESULTS

No significant differences in H values were found between non-headache COVID-19 and control groups., while those with ongoing headache had significantly reduced H values, and those who had recovered from headache had elevated H values, relative to non-headache groups. Effects were greatest in temporal, sensorimotor, and insular brain regions. Reduced H in these regions was also associated with decreased BOLD activity and local functional connectivity.

CONCLUSIONS

These findings provide new insights into the neurophysiological mechanisms that underlie persistent post-COVID headache, with reduced BOLD scaling as a potential biomarker that is specific to this debilitating condition.

Functional MRI and Diffusion Tensor Imaging in Migraine: A Review of Migraine Functional and White Matter Microstructural Changes

Migraine is a complex and heterogenous disorder whose disease mechanisms remain disputed. This narrative review summarizes functional MRI (fMRI) and diffusion tensor imaging (DTI) findings and interprets their association with migraine symptoms and subtype to support and expand our current understanding of migraine pathophysiology. Our PubMed search evaluated and included fMRI and DTI studies involving comparisons between migraineurs vs healthy controls, migraineurs with vs without aura, and episodic vs chronic migraineurs. Migraineurs demonstrate changes in functional connectivity (FC) and regional activation in numerous pain-related networks depending on migraine phase, presence of aura, and chronicity. Changes to diffusion indices are observed in major cortical white matter tracts extending to the brainstem and cerebellum, more prominent in chronic migraine and associated with FC changes. Reported changes in FC and regional activation likely relate to pain processing and sensory hypersensitivities. Diffuse white matter microstructural changes in dysfunctional cortical pain and sensory pathways complement these functional differences. Interpretations of reported fMRI and DTI measure trends have not achieved a clear consensus due to inconsistencies in the migraine neuroimaging literature. Future fMRI and DTI studies should establish and implement a uniform methodology that reproduces existing results and directly compares migraineurs with different subtypes. Combined fMRI and DTI imaging may provide better pathophysiological explanations for nonspecific FC and white matter microstructural differences.

Characteristic oscillatory brain networks for predicting patients with chronic migraine

To determine specific resting-state network patterns underlying alterations in chronic migraine, we employed oscillatory connectivity and machine learning techniques to distinguish patients with chronic migraine from healthy controls and patients with other pain disorders. This cross-sectional study included 350 participants (70 healthy controls, 100 patients with chronic migraine, 40 patients with chronic migraine with comorbid fibromyalgia, 35 patients with fibromyalgia, 30 patients with chronic tension-type headache, and 75 patients with episodic migraine). We collected resting-state magnetoencephalographic data for analysis. Source-based oscillatory connectivity within each network, including the pain-related network, default mode network, sensorimotor network, visual network, and insula to default mode network, was examined to determine intrinsic connectivity across a frequency range of 1-40 Hz. Features were extracted to establish and validate classification models constructed using machine learning algorithms. The findings indicated that oscillatory connectivity revealed brain network abnormalities in patients with chronic migraine compared with healthy controls, and that oscillatory connectivity exhibited distinct patterns between various pain disorders. After the incorporation of network features, the best classification model demonstrated excellent performance in distinguishing patients with chronic migraine from healthy controls, achieving high accuracy on both training and testing datasets (accuracy > 92.6% and area under the curve > 0.93). Moreover, in validation tests, classification models exhibited high accuracy in discriminating patients with chronic migraine from all other groups of patients (accuracy > 75.7% and area under the curve > 0.8). In conclusion, oscillatory synchrony within the pain-related network and default mode network corresponded to altered neurophysiological processes in patients with chronic migraine. Thus, these networks can serve as pivotal signatures in the model for identifying patients with chronic migraine, providing reliable and generalisable results. This approach may facilitate the objective and individualised diagnosis of migraine.

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.

Insights into migraine attacks from neuroimaging

Migraine is one of the most common neurological diseases and it has a huge social and personal impact. Although head pain is the core symptom, individuals with migraine can have a plethora of non-headache symptoms that precede, accompany, or follow the pain. Neuroimaging studies have shown that the involvement of specific brain areas can explain many of the symptoms reported during the different phases of migraine. Recruitment of the hypothalamus, pons, spinal trigeminal nucleus, thalamus, and visual and pain-processing cortical areas starts during the premonitory phase and persists through the headache phase, contributing to the onset of pain and associated symptoms. Once the pain stops, the involvement of most brain areas ends, although the pons, hypothalamus, and visual cortex remain active after acute treatment intake and resolution of migraine symptoms. A better understanding of the correlations between imaging findings and migraine symptomatology can provide new insight into migraine pathophysiology and the mechanisms of novel migraine-specific treatments.

Evaluation of a Clustering Approach to Define Distinct Subgroups of Patients With Migraine to Select Electroacupuncture Treatments

BACKGROUND AND OBJECTIVES

The objective of this study was to propose a clustering approach to identify migraine subgroups and test the clinical usefulness of the approach by providing prognostic information for electroacupuncture treatment selection.

METHODS

Participants with migraine without aura (MWoA) were asked to complete a daily headache diary, self-rating depression and anxiety, and quality-of-life questionnaires. Whole-brain functional connectivities (FCs) were assessed on resting-state functional MRI (fMRI). By integrating clinical measurements and fMRI data, partial least squares correlation and hierarchical clustering analysis were used to cluster participants with MWoA. Multivariate pattern analysis was applied to validate the proposed subgrouping strategy. Some participants had an 8-week electroacupuncture treatment, and the response rate was compared between different MWoA subgroups.

RESULTS

In study 1, a total of 97 participants (age of 28.2 ± 1.0 years, 70 female participants) with MWoA and 77 healthy controls (HCs) (age of 26.8 ± 0.1 years, 61 female participants) were enrolled (dataset 1), and 2 MWoA subgroups were defined. The participants in subgroup 1 had a significantly lower headache frequency (times/month of 4.4 ± 1.1) and significantly higher self-ratings of depression (depression score of 49.5 ± 2.3) when compared with participants in subgroup 2 (times/month of 7.0 ± 0.6 and depression score of 43.4 ± 1.2). The between-group differences of FCs were predominantly related to the amygdala, thalamus, hippocampus, and parahippocampal area. In study 2, 33 participants with MWoA (age of 30.9 ± 2.0 years, 28 female participants) and 23 HCs (age of 29.8 ± 1.1 years, 13 female participants) were enrolled as an independent dataset (dataset 2). The classification analysis validated the effectiveness of the 2-cluster solution of participants with MWoA in datasets 1 and 2. In study 3, 58 participants with MWoA were willing to receive electroacupuncture treatment and were assigned to different subgroups. Participants in different subgroups exhibited different response rates (p = 0.03, OR CI 0.086-0.93) to electroacupuncture treatment (18% and 44% for subgroups 1 and 2, respectively).

DISCUSSION

Our study proposed a novel clustering approach to define distinct MWoA subgroups, which could be useful for refining the diagnosis of participants with MWoA and guiding individualized strategies for pain prophylaxis and analgesia.

Psychological and neurological predictors of acupuncture effect in patients with chronic pain: a randomized controlled neuroimaging trial

ABSTRACT

Chronic pain has been one of the leading causes of disability. Acupuncture is globally used in chronic pain management. However, the efficacy of acupuncture treatment varies across patients. Identifying individual factors and developing approaches that predict medical benefits may promise important scientific and clinical applications. Here, we investigated the psychological and neurological factors collected before treatment that would determine acupuncture efficacy in knee osteoarthritis. In this neuroimaging-based randomized controlled trial, 52 patients completed a baseline assessment, 4-week acupuncture or sham-acupuncture treatment, and an assessment after treatment. The patients, magnetic resonance imaging operators, and outcome evaluators were blinded to treatment group assignment. First, we found that patients receiving acupuncture treatment showed larger pain intensity improvements compared with patients in the sham-acupuncture arm. Second, positive expectation, extraversion, and emotional attention were correlated with the magnitude of clinical improvements in the acupuncture group. Third, the identified neurological metrics encompassed striatal volumes, posterior cingulate cortex (PCC) cortical thickness, PCC/precuneus fractional amplitude of low-frequency fluctuation (fALFF), striatal fALFF, and graph-based small-worldness of the default mode network and striatum. Specifically, functional metrics predisposing patients to acupuncture improvement changed as a consequence of acupuncture treatment, whereas structural metrics remained stable. Furthermore, support vector machine models applied to the questionnaire and brain features could jointly predict acupuncture improvement with an accuracy of 81.48%. Besides, the correlations and models were not significant in the sham-acupuncture group. These results demonstrate the specific psychological, brain functional, and structural predictors of acupuncture improvement and may offer opportunities to aid clinical practices.

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.

Effect of acupuncture on the modulation of functional brain regions in migraine: A meta-analysis of fMRI studies

Background

Acupuncture, a traditional Chinese medicine therapy, is an effective migraine treatment, especially in improving pain. In recent years, many acupuncture brain imaging studies have found significant changes in brain function following acupuncture treatment of migraine, providing a new perspective to elucidate the mechanism of action of acupuncture.

Objective

To analyse and summarize the effects of acupuncture on the modulation of specific patterns of brain region activity changes in migraine patients, thus providing a mechanism for treating migraine by acupuncture.

Methods

Chinese and English articles published up to May 2022 were searched in three English databases (PubMed, Embase and Cochrane) and four Chinese databases (China national knowledge infrastructure, CNKI; Chinese Biomedical Literature database, CBM; the Chongqing VIP database, VIP; and the Wanfang database, WF). A neuroimaging meta-analysis on ALFF, ReHo was performed on the included studies using Seed-based d Mapping with Permutation of Subject Images (SDM-PSI) software. Subgroup analyses were used to compare differences in brain regions between acupuncture and other groups. Meta-regression was used to explore the effect of demographic information and migraine alterations on brain imaging outcomes. Linear models were drawn using MATLAB 2018a, and visual graphs for quality evaluation were produced using R and RStudio software.

Results

A total of 7 studies comprising 236 patients in the treatment group and 173 in the control group were included in the meta-analysis. The results suggest that acupuncture treatment helps to improve pain symptoms in patients with migraine. The left angular gyrus is hyperactivation, and the left superior frontal gyrus and the right superior frontal gyrus are hypoactivated. The migraine group showed hyperactivation in the corpus callosum compared to healthy controls.

Conclusion

Acupuncture can significantly regulate changes in brain regions in migraine patients. However, due to the experimental design of neuroimaging standards are not uniform, the results also have some bias. Therefore, to better understand the potential mechanism of acupuncture on migraine, a large sample, multicenter controlled trial is needed for further study. In addition, the application of machine learning methods in neuroimaging studies could help predict the efficacy of acupuncture and screen migraine patients suitable for acupuncture treatment.

Acupuncture-Neuroimaging Research Trends over Past Two Decades: A Bibliometric Analysis

OBJECTIVE

To identify topics attracting growing research attention as well as frontier trends of acupuncture-neuroimaging research over the past two decades.

METHODS

This paper reviewed data in the published literature on acupuncture neuroimaging from 2000 to 2020, which was retrieved from the Web of Science database. CiteSpace was used to analyze the publication years, countries, institutions, authors, keywords, co-citation of authors, journals, and references.

RESULTS

A total of 981 publications were included in the final review. The number of publications has increased in the recent 20 years accompanied by some fluctuations. Notably, the most productive country was China, while Harvard University ranked first among institutions in this field. The most productive author was Tian J with the highest number of articles (50), whereas the most co-cited author was Hui KKS (325). Evidence-Based Complementary and Alternative Medicine (92) was the most prolific journal, while Neuroimage was the most co-cited journal (538). An article written by Hui KKS (2005) exhibited the highest co-citation number (112). The keywords "acupuncture" (475) and "electroacupuncture" (0.10) had the highest frequency and centrality, respectively. Functional magnetic resonance imaging (fMRI) ranked first with the highest citation burst (6.76).

CONCLUSION

The most active research topics in the field of acupuncture-neuroimaging over the past two decades included research type, acupoint specificity, neuroimaging methods, brain regions, acupuncture modality, acupoint specificity, diseases and symptoms treated, and research type. Whilst research frontier topics were "nerve regeneration", "functional connectivity", "neural regeneration", "brain network", "fMRI" and "manual acupuncture".

Electroacupuncture alleviates pain after total knee arthroplasty through regulating neuroplasticity: A resting-state functional magnetic resonance imaging study

INTRODUCTION

We aimed to evaluate the efficacy of electroacupuncture in relieving acute pain after total knee arthroplasty (TKA) and related mechanism.

METHODS

In this randomized, single-blind, and sham-acupuncture controlled study. Forty patients with postoperative acute pain were recruited and randomly divided electroacupuncture group (n = 20) and sham-acupuncture group (n = 20) from November 2020 to October 2021. All patients received electroacupuncture or sham-acupuncture for 5 days after TKA. Their brain regions were scanned with resting-state functional magnetic resonance imaging before and after intervention. Pain was scaled. Another 40 matched healthy controls underwent scanning once. The amplitude of low-frequency fluctuation (ALFF) values was compared. Pearson's correlation analysis was utilized to explore the correlation of ALFF with clinical variables in patients after intervention.

RESULTS

Compared with the HCs, patients with acute pain following TKA had significantly decreased ALFF value in right middle frontal gyrus, right supplementary motor area, bilateral precuneus, right calcarine fissure and surrounding cortex, and left triangular part of inferior frontal gyrus (false discovery rate corrected p < .05). Patients had higher ALFF value in bilateral precuneus, right cuneus, right angular gyrus, bilateral middle occipital gyrus, and left middle temporal gyrus after electroacupuncture (AlphaSim corrected p < .01). Correlation analysis revealed that the change (postoperative day 7 to postoperative day 3) of ALFF in bilateral precuneus were negatively correlated with the change of NRS scores (r = -0.706; p = .002; 95% CI = -0.890 to -0.323) in EA group.

CONCLUSIONS

The functional activities of related brain regions decreased in patients with acute pain after TKA. The enhancement of the functional activity of precuneus may be the neurobiological mechanism of electroacupuncture in treating pain following TKA.

Functional magnetic resonance imaging of headache: Issues, best-practices, and new directions, a narrative review

OBJECTIVE

To ensure readers are informed consumers of functional magnetic resonance imaging (fMRI) research in headache, to outline ongoing challenges in this area of research, and to describe potential considerations when asked to collaborate on fMRI research in headache, as well as to suggest future directions for improvement in the field.

BACKGROUND

Functional MRI has played a key role in understanding headache pathophysiology, and mapping networks involved with headache-related brain activity have the potential to identify intervention targets. Some investigators have also begun to explore its use for diagnosis.

METHODS/RESULTS

The manuscript is a narrative review of the current best practices in fMRI in headache research, including guidelines on transparency and reproducibility. It also contains an outline of the fundamentals of MRI theory, task-related study design, resting-state functional connectivity, relevant statistics and power analysis, image preprocessing, and other considerations essential to the field.

CONCLUSION

Best practices to increase reproducibility include methods transparency, eliminating error, using a priori hypotheses and power calculations, using standardized instruments and diagnostic criteria, and developing large-scale, publicly available datasets.

Amplitude of low-frequency fluctuation-based regional radiomics similarity network: Biomarker for Parkinson's disease

Parkinson's disease (PD) is a highly heterogeneous disorder that is difficult to diagnose. Therefore, reliable biomarkers are needed. We implemented a method constructing a regional radiomics similarity network (R2SN) based on the amplitude of low-frequency fluctuation (ALFF). We classified patients with PD and healthy individuals by using a machine learning approach in accordance with the R2SN connectome. The ALFF-based R2SN exhibited great reproducibility with different brain atlases and datasets. Great classification performances were achieved both in primary (AUC = 0.85 ± 0.02 and accuracy = 0.81 ± 0.03) and independent external validation (AUC = 0.77 and accuracy = 0.70) datasets. The discriminative R2SN edges correlated with the clinical evaluations of patients with PD. The nodes of discriminative R2SN edges were primarily located in the default mode, sensorimotor, executive control, visual and frontoparietal network, cerebellum and striatum. These findings demonstrate that ALFF-based R2SN is a robust potential neuroimaging biomarker for PD and could provide new insights into connectome reorganization in PD.

Functional magnetic resonance imaging in migraine: A systematic review

BACKGROUND

Migraine is a highly prevalent primary headache disorder. Despite a high burden of disease, key disease mechanisms are not entirely understood. Functional magnetic resonance imaging is an imaging method using the blood-oxygen-level-dependent signal, which has been increasingly used in migraine research over recent years. This systematic review summarizes recent findings employing functional magnetic resonance imaging for the investigation of migraine.

METHODS

We conducted a systematic search and selection of functional magnetic resonance imaging applications in migraine from April 2014 to December 2021 (PubMed and references of identified articles according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines). Methodological details and main findings were extracted and synthesized.

RESULTS

Out of 224 articles identified, 114 were included after selection. Repeatedly emerging structures of interest included the insula, brainstem, limbic system, hypothalamus, thalamus, and functional networks. Assessment of functional brain changes in response to treatment is emerging, and machine learning has been used to investigate potential functional magnetic resonance imaging-based markers of migraine.

CONCLUSIONS

A wide variety of functional magnetic resonance imaging-based metrics were found altered across the brain for heterogeneous migraine cohorts, partially correlating with clinical parameters and supporting the concept to conceive migraine as a brain state. However, a majority of findings from previous studies have not been replicated, and studies varied considerably regarding image acquisition and analyses techniques. Thus, while functional magnetic resonance imaging appears to have the potential to advance our understanding of migraine pathophysiology, replication of findings in large representative datasets and precise, standardized reporting of clinical data would likely benefit the field and further increase the value of observations.

Central Mechanism of Acupuncture Treatment in Patients with Migraine: Study Protocol for Randomized Controlled Neuroimaging Trial

Purpose

Acupuncture has been recognized as an effective and safe alternative therapy for migraine, but its central mechanism has not yet been adequately explained. Meanwhile, research into the clinical efficacy and central mechanism of true acupuncture (TA) and sham acupuncture (SA) is lacking. It is necessary to investigate whether TA has better efficacy than SA, and how they achieve different effects. This study aims to evaluate the efficacy of TA and SA, observe the brain response caused by TA and SA, and further investigate the central nervous mechanism of TA and SA treatment for patients with migraine.

Patients and Methods

This is a randomized controlled neuroimaging trial combining acupuncture treatment with functional magnetic resonance imaging, with patients and outcome assessors blinded. A total of 60 patients with migraine will be randomly allocated to receive 12 sessions of either TA or SA treatments (three sessions per week for 4 weeks), and 30 healthy participants will be recruited as the healthy control (HC) group. Outcome assessment and neuroimaging will be conducted before and after the entire intervention. A headache diary and questionnaires of life quality and psychological properties will be used to evaluate clinical efficacy. Multimodal magnetic resonance imagining data analysis will be used to investigate the central mechanism of TA or SA in treating migraine. Pearson's correlation analysis will be used to reveal the relationship between the brain response and clinical improvements.

Conclusion

The results of this study will reveal the brain response to TA and SA in patients with migraine and contribute to further expanding the knowledge of their central mechanism.

Study Registration

This trial has been approved by the ethics committee of Dongzhimen Hospital affiliated to Beijing University of Chinese Medicine (DZMEC-KY-2020-38) and registered in the Chinese Clinical Trial Registry (registration number ChiCTR2000033995).

Circulating exosomal microRNA profiles in migraine patients receiving acupuncture treatment: A placebo-controlled clinical trial

Background

Acupuncture has a long history of being used in Chinese medicine for the treatment of migraine. However, molecular biomarkers for diagnosis and prognosis of migraine and its treatment are lacking. This study aimed to explore whether acupuncture could regulate differentially expressed exosomal miRNAs between patients with migraine without aura (MWoA) and healthy controls (HCs) and to identify diagnostic biomarkers that helped differentiate MWoA patients from HCs and identify prognostic biomarkers that helped to predict the effect of acupuncture.

Methods

Here, we isolated serum exosomes from patients with MWoA and HCs before and after true and sham acupuncture treatment. Then, small RNA sequencing and bioinformatics analysis were performed to screen out key miRNAs specifically responding to acupuncture treatment. Pearson's correlation analysis was used to evaluate the correlation between miRNAs and clinical phenotypes. Finally, we applied a machine learning method to identify diagnostic biomarkers of MWoA patients and identify prognostic biomarkers that helped to predict the effect of acupuncture.

Results

Small RNA sequencing identified 68 upregulated and 104 downregulated miRNAs in MWoA patients compared to those in HCs. Further, we identified eight upregulated and four downregulated miRNAs in migraine patients after true acupuncture treatment (trAMWoA), but not in the sham acupuncture treatment (shAMWoA) or HC group. Among them, has-miR-378a-5p was positively correlated with time unable to work, study, or do housework due to migraine (p < 0.05), whereas has-miR-605-3p was negatively correlated with the restrictive subscale of the migraine-specific quality of life questionnaire (MSQ) (p < 0.05). We then evaluated the diagnostic and prognostic potential of these 12 miRNAs in patients with MWoA. The combination of serum levels of exosomal has-miR-369-5p, has-miR-145-5p, and has-miR-5,010-3p could serve as diagnostic and prognostic biomarkers for MWoA patients following acupuncture treatment.

Conclusion

This is the first study on the serum exosomal miRNA profiles of migraineurs before and after acupuncture treatment. Our results improve our understanding of the molecular functions of miRNAs in MWoA. More importantly, they expand our view of evaluating the clinical outcomes of migraine patients treated with acupuncture, using exosomal RNA markers.

Clinical Trial Registration

Chinese Clinical Trial Registry, ChiCTR2000034417, July 2020.

Bibliometric Analysis of 100 Most Highly Cited Publications on Acupuncture for Migraine

Background

Migraine is a serious global health concern that imposed a huge economic burden on social health care. Over the past few decades, the analgesic effects of acupuncture have been widely recognized, and there is a growing body of research on acupuncture for migraine. Citation analysis is a branch of bibliometrics that helps researchers analyze and identify historical or landmark studies within the scientific literature. Currently, there is no analysis of the 100 most highly cited publications on acupuncture for migraine.

Methods

The 100 most highly cited publications on acupuncture for migraine were screened using the Science Citation Index Expanded of the Web of Science Core Collection database. CiteSpace and VOSviewer programs were used for bibliometric analysis.

Results

A total of 493 publications on acupuncture for migraine were identified. 100 of the most highly cited publications on acupuncture for migraine were published from 1984-2020. These publications were cited 6142 times with an h-index of 44 and 84% were original articles. The highest frequency of citations was 416. A total of 335 authors were involved in the study with 37 lead authors. 212 institutions from 20 countries contributed to the 100 most highly cited publications. The most published studies came from the United States (n=36), followed by China (n=27) and Germany (n=26). The Technical University of Munich published the largest number of papers (n = 15). Top-cited publications mainly came from the Headache (n=13, citations=582). Neuroimaging is gradually emerging as a hot topic of research.

Conclusion

This is the first bibliometric analysis to offer a thorough list of the 100 most highly cited papers on acupuncture for migraine, demonstrating significant progress and emerging trends in this field to assist researchers in determining the direction for further research.

What imaging has revealed about migraine and chronic migraine

Although migraine pathophysiology is not yet entirely understood, it is now established that migraine should be viewed as a complex neurological disease, which involves the interplay of different brain networks and the release of signaling molecules, instead of a pure vascular disorder. The field of migraine research has also progressed significantly due to the advancement of brain imaging techniques. Numerous studies have investigated the relation between migraine pathophysiology and cerebral hemodynamic changes, showing that vascular changes are neither necessary nor sufficient to cause the migraine pain. Abnormal function and structure of key cortical, subcortical, and brainstem regions involved in multisensory, including pain, processing have been shown to occur in migraine patients during both an acute attack and the interictal phase. Whether brain imaging alterations represent a predisposing trait or are the consequence of the recurrence of headache attacks is still a matter of debate. It is highly likely that brain functional and structural alterations observed in migraine patients derive from the interaction between predisposing brain traits and experience-dependent responses. Neuroimaging studies have also enriched our knowledge of the mechanisms responsible for migraine chronification and have shed light on the mechanisms of actions of acute and preventive migraine treatments.

The Role of fMRI in Drug Development: An Update

Functional magnetic resonance imaging (fMRI) of the brain is a technology that holds great potential for increasing the efficiency of drug development for the central nervous system (CNS). In preclinical studies and both early- and late-phase human trials, fMRI has the potential to improve cross-species translation of drug effects, help to de-risk compounds early in development, and contribute to the portfolio of evidence for a compound's efficacy and mechanism of action. However, to date, the utilization of fMRI in the CNS drug development process has been limited. The purpose of this chapter is to explore this mismatch between potential and utilization. This chapter provides introductory material related to fMRI and drug development, describes what is required of fMRI measurements for them to be useful in a drug development setting, lists current capabilities of fMRI in this setting and challenges faced in its utilization, and ends with directions for future development of capabilities in this arena. This chapter is the 5-year update of material from a previously published workshop summary (Carmichael et al., Drug DiscovToday 23(2):333-348, 2018).

Identifying the neural marker of chronic sciatica using multimodal neuroimaging and machine learning analyses

Introduction

Sciatica is a pain disorder often caused by the herniated disk compressing the lumbosacral nerve roots. Neuroimaging studies have identified functional abnormalities in patients with chronic sciatica (CS). However, few studies have investigated the neural marker of CS using brain structure and the classification value of multidimensional neuroimaging features in CS patients is unclear.

Methods

Here, structural and resting-state functional magnetic resonance imaging (fMRI) was acquired for 34 CS patients and 36 matched healthy controls (HCs). We analyzed cortical surface area, cortical thickness, amplitude of low-frequency fluctuation (ALFF), regional homogeneity (REHO), between-regions functional connectivity (FC), and assessed the correlation between neuroimaging measures and clinical scores. Finally, the multimodal neuroimaging features were used to differentiate the CS patients and HC individuals by support vector machine (SVM) algorithm.

Results

Compared to HC, CS patients had a larger cortical surface area in the right banks of the superior temporal sulcus and rostral anterior cingulate; higher ALFF value in the left inferior frontal gyrus; enhanced FCs between somatomotor and ventral attention network. Three FCs values were associated with clinical pain scores. Furthermore, the three multimodal neuroimaging features with significant differences between groups and the SVM algorithm could classify CS patients and HC with an accuracy of 90.00%.

Discussion

Together, our findings revealed extensive reorganization of local functional properties, surface area, and network metrics in CS patients. The success of patient identification highlights the potential of using artificial intelligence and multimodal neuroimaging markers in chronic pain research.

Identification of Resting-State Network Functional Connectivity and Brain Structural Signatures in Fibromyalgia Using a Machine Learning Approach

Abnormal resting-state functional connectivity (rs-FC) and brain structure have emerged as pathological hallmarks of fibromyalgia (FM). This study investigated and compared the accuracy of network rs-FC and brain structural features in identifying FM with a machine learning (ML) approach. Twenty-six FM patients and thirty healthy controls were recruited. Clinical presentation was measured by questionnaires. After MRI acquisitions, network rs-FC z-score and network-based gray matter volume matrices were exacted and preprocessed. The performance of feature selection and classification methods was measured. Correlation analyses between predictive features in final models and clinical data were performed. The combination of the recursive feature elimination (RFE) selection method and support vector machine (rs-FC data) or logistic regression (structural data), after permutation importance feature selection, showed high performance in distinguishing FM patients from pain-free controls, in which the rs-FC ML model outperformed the structural ML model (accuracy: 0.91 vs. 0.86, AUC: 0.93 vs. 0.88). The combined rs-FC and structural ML model showed the best performance (accuracy: 0.95, AUC: 0.95). Additionally, several rs-FC features in the final ML model correlated with FM's clinical data. In conclusion, ML models based on rs-FC and brain structural MRI features could effectively differentiate FM patients from pain-free subjects.

Research Hotspots and Trends on Acupuncture for Neuropathic Pain: A Bibliometric Analysis from 2002 to 2021

Purpose

In this study, we aimed to systematically determine the trend, research hotspots, and directions of the future development of acupuncture for neuropathic pain (NP) by bibliometric analysis.

Methods

Based on the relevant literature on acupuncture for NP in the databases of Web of Science from January 2002 to December 2021, Citespace software and VOSviewer were used to determine the use of acupuncture for the treatment of NP. The annual publications, countries, authors, research institutions, keywords, co-cited references, and journals were analyzed to explore the research hotspot and development trends in this field.

Results

A total of 1462 records of acupuncture for NP from 2002 to 2021 were obtained. Chingliang Hsieh (20) is the most effective author and Han JS (585 co-citations) is the most influential author. The most productive institutions and countries are Kyung Hee UNIV (88) and China, respectively (480). UNIV Maryland of the USA has the highest centrality (0.12). Evidence-based complementary and alternative medicine (89) is the most prolific journal, and Pain is the most influential journal (4200 co-citations). Ji-sheng Han (2003) is the most frequently cited article (158 co-citations). Electroacupuncture, bee-venom acupuncture, and percutaneous electrical stimulation are the most commonly studied acupuncture types. The analgesic mechanism of acupuncture and acupuncture-neuroimaging was a research hotspot over the years. The clinical evidence of acupuncture for NP should be further studied in the future.

Conclusion

The study using bibliometric analysis methods to investigate the publications on acupuncture for NP so as to provide potential research directions in the future.

Therapeutic applications and potential mechanisms of acupuncture in migraine: A literature review and perspectives

Acupuncture is commonly used as a treatment for migraines. Animal studies have suggested that acupuncture can decrease neuropeptides, immune cells, and proinflammatory and excitatory neurotransmitters, which are associated with the pathogenesis of neuroinflammation. In addition, acupuncture participates in the development of peripheral and central sensitization through modulation of the release of neuronal-sensitization-related mediators (brain-derived neurotrophic factor, glutamate), endocannabinoid system, and serotonin system activation. Clinical studies have demonstrated that acupuncture may be a beneficial migraine treatment, particularly in decreasing pain intensity, duration, emotional comorbidity, and days of acute medication intake. However, specific clinical effectiveness has not been substantiated, and the mechanisms underlying its efficacy remain obscure. With the development of biomedical and neuroimaging techniques, the neural mechanism of acupuncture in migraine has gained increasing attention. Neuroimaging studies have indicated that acupuncture may alter the abnormal functional activity and connectivity of the descending pain modulatory system, default mode network, thalamus, frontal-parietal network, occipital-temporal network, and cerebellum. Acupuncture may reduce neuroinflammation, regulate peripheral and central sensitization, and normalize abnormal brain activity, thereby preventing pain signal transmission. To summarize the effects and neural mechanisms of acupuncture in migraine, we performed a systematic review of literature about migraine and acupuncture. We summarized the characteristics of current clinical studies, including the types of participants, study designs, and clinical outcomes. The published findings from basic neuroimaging studies support the hypothesis that acupuncture alters abnormal neuroplasticity and brain activity. The benefits of acupuncture require further investigation through basic and clinical studies.

Cerebral blood flow alterations in migraine patients with and without aura: An arterial spin labeling study

Background

Migraine aura is a transient, fully reversible visual, sensory, or other central nervous system symptom that classically precedes migraine headache. This study aimed to investigate cerebral blood flow (CBF) alterations of migraine with aura patients (MwA) and without aura patients (MwoA) during inter-ictal periods, using arterial spin labeling (ASL).

Methods

We evaluated 88 migraine patients (32 MwA) and 44 healthy control subjects (HC) who underwent a three-dimensional pseudo-continuous ASL MRI scanning. Voxel-based comparison of normalized CBF was conducted between MwA and MwoA. The relationship between CBF variation and clinical scale assessment was further analyzed. The mean CBF values in brain regions showed significant differences were calculated and considered as imaging features. Based on these features, different machine learning–based models were established to differentiate MwA and MwoA under five-fold cross validation. The predictive ability of the optimal model was further tested in an independent sample of 30 migraine patients (10 MwA).

Results

In comparison to MwoA and HC, MwA exhibited higher CBF levels in the bilateral superior frontal gyrus, bilateral postcentral gyrus and cerebellum, and lower CBF levels in the bilateral middle frontal gyrus, thalamus and medioventral occipital cortex (all p values < 0.05). These variations were also significantly correlated with multiple clinical rating scales about headache severity, quality of life and emotion. On basis of these CBF features, the accuracies and areas under curve of the final model in the training and testing samples were 84.3% and 0.872, 83.3% and 0.860 in discriminating patients with and without aura, respectively.

Conclusion

In this study, CBF abnormalities of MwA were identified in multiple brain regions, which might help better understand migraine-stroke connection mechanisms and may guide patient-specific decision-making.

Resting-state magnetoencephalographic oscillatory connectivity to identify patients with chronic migraine using machine learning

To identify and validate the neural signatures of resting-state oscillatory connectivity for chronic migraine (CM), we used machine learning techniques to classify patients with CM from healthy controls (HC) and patients with other pain disorders. The cross-sectional study obtained resting-state magnetoencephalographic data from 240 participants (70 HC, 100 CM, 35 episodic migraine [EM], and 35 fibromyalgia [FM]). Source-based oscillatory connectivity of relevant cortical regions was calculated to determine intrinsic connectivity at 1–40 Hz. A classification model that employed a support vector machine was developed using the magnetoencephalographic data to assess the reliability and generalizability of CM identification. In the findings, the discriminative features that differentiate CM from HC were principally observed from the functional interactions between salience, sensorimotor, and part of the default mode networks. The classification model with these features exhibited excellent performance in distinguishing patients with CM from HC (accuracy ≥ 86.8%, area under the curve (AUC) ≥ 0.9) and from those with EM (accuracy: 94.5%, AUC: 0.96). The model also achieved high performance (accuracy: 89.1%, AUC: 0.91) in classifying CM from other pain disorders (FM in this study). These resting-state magnetoencephalographic electrophysiological features yield oscillatory connectivity to identify patients with CM from those with a different type of migraine and pain disorder, with adequate reliability and generalizability.

Deqi Sensation to Predict Acupuncture Effect on Functional Dyspepsia: A Machine Learning Study

Objectives

The aim of the study was to predict the effect of acupuncture for treating functional dyspepsia (FD) using the support vector machine (SVM) techniques based on initial deqi sensations of patients.

Methods

This retrospective study involved 90 FD patients who had received four weeks of acupuncture treatment. The support vector classification model was used to distinguish higher responders (patients with Symptom Index of Dyspepsia improvement score ≥ 2) from lower responders (patients with Symptom Index of Dyspepsia improvement score < 2). A support vector regression model was used to predict the change in the Symptom Index of Dyspepsia at the end of acupuncture treatment. Deqi sensations of patients in the first acupuncture treatment of a 20-session acupuncture intervention were defined as features and used to train models. Models were validated by 10-fold cross-validation and evaluated by accuracy, specificity, sensitivity, the area under the receive-operating curve, the coefficient of determination (R²), and the mean squared error.

Results

The two models could predict the efficacy of acupuncture successfully. These models had an accuracy of 0.84 in predicting acupuncture response, and an R² of 0.16 in the prediction of symptom improvements, respectively. The presence or absence of deqi sensation, the duration of deqi sensation, distention, and pain were finally selected as significant predicting features.

Conclusion

Based on the SVM algorithms and deqi sensation, the current study successfully predicted the acupuncture response as well as clinical symptom improvement in FD patients at the end of treatment. Our prediction models are expected to promote the clinical efficacy of acupuncture treatment for FD, reduce medical expenditures, and optimize the allocation of medical resources.

Altered static functional network connectivity predicts the efficacy of non-steroidal anti-inflammatory drugs in migraineurs without aura

Brain networks have significant implications for the understanding of migraine pathophysiology and prognosis. This study aimed to investigate whether large-scale network dysfunction in patients with migraine without aura (MwoA) could predict the efficacy of non-steroidal anti-inflammatory drugs (NSAIDs). Seventy patients with episodic MwoA and 33 healthy controls (HCs) were recruited. Patients were divided into MwoA with effective NSAIDs (M-eNSAIDs) and with ineffective NSAIDs (M-ieNSAIDs). Group-level independent component analysis and functional network connectivity (FNC) analysis were used to extract intrinsic networks and detect dysfunction among these networks. The clinical characteristics and FNC abnormalities were considered as features, and a support vector machine (SVM) model with fivefold cross-validation was applied to distinguish the subjects at an individual level. Dysfunctional connections within seven networks were observed, including default mode network (DMN), executive control network (ECN), salience network (SN), sensorimotor network (SMN), dorsal attention network (DAN), visual network (VN), and auditory network (AN). Compared with M-ieNSAIDs and HCs, patients with M-eNSAIDs displayed reduced DMN-VN and SMN-VN, and enhanced VN-AN connections. Moreover, patients with M-eNSAIDs showed increased FNC patterns within ECN, DAN, and SN, relative to HCs. Higher ECN-SN connections than HCs were revealed in patients with M-ieNSAIDs. The SVM model demonstrated that the area under the curve, sensitivity, and specificity were 0.93, 0.88, and 0.89, respectively. The widespread FNC impairment existing in the modulation of medical treatment suggested FNC disruption as a biomarker for advancing the understanding of neurophysiological mechanisms and improving the decision-making of therapeutic strategy.

Predicting response to tVNS in patients with migraine using functional MRI: A voxels-based machine learning analysis

Background

Migraine is a common disorder, affecting many patients. However, for one thing, lacking objective biomarkers, misdiagnosis, and missed diagnosis happen occasionally. For another, though transcutaneous vagus nerve stimulation (tVNS) could alleviate migraine symptoms, the individual difference of tVNS efficacy in migraineurs hamper the clinical application of tVNS. Therefore, it is necessary to identify biomarkers to discriminate migraineurs as well as select patients suitable for tVNS treatment.

Methods

A total of 70 patients diagnosed with migraine without aura (MWoA) and 70 matched healthy controls were recruited to complete fMRI scanning. In study 1, the fractional amplitude of low-frequency fluctuation (fALFF) of each voxel was calculated, and the differences between healthy controls and MWoA were compared. Meaningful voxels were extracted as features for discriminating model construction by a support vector machine. The performance of the discriminating model was assessed by accuracy, sensitivity, and specificity. In addition, a mask of these significant brain regions was generated for further analysis. Then, in study 2, 33 of the 70 patients with MWoA in study 1 receiving real tVNS were included to construct the predicting model in the generated mask. Discriminative features of the discriminating model in study 1 were used to predict the reduction of attack frequency after a 4-week tVNS treatment by support vector regression. A correlation coefficient between predicted value and actual value of the reduction of migraine attack frequency was conducted in 33 patients to assess the performance of predicting model after tVNS treatment. We vislized the distribution of the predictive voxels as well as investigated the association between fALFF change (post-per treatment) of predict weight brain regions and clinical outcomes (frequency of migraine attack) in the real group.

Results

A biomarker containing 3,650 features was identified with an accuracy of 79.3%, sensitivity of 78.6%, and specificity of 80.0% (p &lt; 0.002). The discriminative features were found in the trigeminal cervical complex/rostral ventromedial medulla (TCC/RVM), thalamus, medial prefrontal cortex (mPFC), and temporal gyrus. Then, 70 of 3,650 discriminative features were identified to predict the reduction of attack frequency after tVNS treatment with a correlation coefficient of 0.36 (p = 0.03). The 70 predictive features were involved in TCC/RVM, mPFC, temporal gyrus, middle cingulate cortex (MCC), and insula. The reduction of migraine attack frequency had a positive correlation with right TCC/RVM (r = 0.433, p = 0.021), left MCC (r = 0.451, p = 0.016), and bilateral mPFC (r = 0.416, p = 0.028), and negative with left insula (r = −0.473, p = 0.011) and right superior temporal gyrus/middle temporal gyrus (r = −0.684, p &lt; 0.001), respectively.

Conclusions

By machine learning, the study proposed two potential biomarkers that could discriminate patients with MWoA and predict the efficacy of tVNS in reducing migraine attack frequency. The pivotal features were mainly located in the TCC/RVM, thalamus, mPFC, and temporal gyrus.

The cumulative therapeutic effect of acupuncture in patients with migraine without aura: Evidence from dynamic alterations of intrinsic brain activity and effective connectivity

We explored the dynamic alterations of intrinsic brain activity and effective connectivity after acupuncture treatment to investigate the underlying neurological mechanism of acupuncture treatment in patients with migraine without aura (MwoA). The Functional Magnetic Resonance Imaging (fMRI) scans were separately obtained at baseline, after the first and 12th acupuncture sessions in 40 patients with MwoA. Compared with the healthy controls (HCs), patients with MwoA mostly showed a decreased dynamic amplitude of low-frequency fluctuation (dALFF) variability in the rostral ventromedial medulla (RVM), superior lobe of left cerebellum (Cerebellum_Crus1_L), right precuneus (PCUN.R), and so on. The decreased dALFF variability of RVM, Cerebellum_Crus1_L, and PCUN.R progressively recovered after the first and 12th acupuncture treatment sessions as compared to the baseline. There was gradually increased dynamic effective connectivity (DEC) variability in RVM outflow to the right middle frontal gyrus, left insula, right precentral gyrus, and right supramarginal gyrus, and gradually enhanced DEC variability from the right fusiform gyrus inflow to RVM. Furthermore, the gradually increased DEC variability was found from Cerebellum_Crus1_L outflow to the left middle occipital gyrus and the left precentral gyrus, from PCUN.R outflow to the right thalamus. These dALFF variabilities were positively correlated with the frequency of migraine attacks and negatively correlated with disease duration at baseline. The dynamic Granger causality analysis (GCA) coefficients of this DEC variability were positively correlated with Migraine-Specific Quality of Life Questionnaire scores and negatively correlated with the frequency of migraine attacks and visual analog scale (VAS) scores after 12th acupuncture sessions. Our results were analyzed by a longitudinal fMRI in the absence of a sham acupuncture control group and provided insight into the dynamic alterations of brain activity and effective connectivity in patients with MwoA after acupuncture intervention. Acupuncture might relieve MwoA by increasing the effective connectivity of RVM, Cerebellum_Crus1_L, and PCUN.R to make up for the decreased dALFF variability in these brain areas.

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.

Artificial intelligence-directed acupuncture: a review

Acupuncture is widely used around the whole world nowadays and exhibits significant efficacy against many chronic diseases, especially in pain-related diseases. With the rapid development of artificial intelligence (AI), its implementation into acupuncture has achieved a series of significant breakthroughs in many areas of acupuncture practice, such as acupoints selection and prescription, acupuncture manipulation identification, acupuncture efficacy prediction, and so on. The paper will discuss the significant theoretical and technical achievements in AI-directed acupuncture. AI-based data mining methods uncovered crucial acupoint combinations for treating various diseases, which provide a scientific basis for acupoints prescription in clinical practice. Furthermore, the rapid development of modern TCM instruments facilitates the integration of modern medical instruments, AI techniques, and acupuncture. This integration significantly improves the quantification, objectification, and standardization of acupuncture as well as the delivery of clinical personalized acupuncture therapy. Machine learning-based clinical efficacy prediction of acupuncture can help doctors screen patients who may benefit from acupuncture treatment. However, the existing challenges require additional work for developing AI-directed acupuncture. Some include a better understanding of ancient Chinese philosophy for AI researchers, TCM acupuncture theory-based explanation of the knowledge discoveries, construction of acupuncture databases, and clinical trials for novel knowledge validation. This review aims to summarize the major contribution of AI techniques to the discovery of novel acupuncture knowledge, the improvement for acupuncture safety and efficacy, the development and inheritance of acupuncture, and the major challenges for the further development of AI-directed acupuncture. The development of acupuncture can progress with the help of AI.

fMRI Findings in Cortical Brain Networks Interactions in Migraine Following Repetitive Transcranial Magnetic Stimulation

Background

Repetitive transcranial magnetic stimulation (rTMS) is one of the high-potential non-pharmacological methods for migraine treatment. The purpose of this study is to define the neuroimaging markers associated with rTMS therapy in patients with migraine based on data from functional MRI (fMRI).

Materials and Methods

A total of 19 patients with episodic migraine without aura underwent a 5-day course of rTMS of the fronto-temporo-parietal junction bilaterally, at 10 Hz frequency and 60% of motor threshold response of 900 pulses. Resting-state functional MRI (1.5 T) and a battery of tests were carried out for each patient to clarify their diagnosis, qualitative and quantitative characteristics of pain, and associated affective symptoms. Changes in functional connectivity (FC) in the brain's neural networks before and after the treatment were identified through independent components analysis.

Results

Over the course of therapy, we observed an increase in FC of the default mode network within it, with pain system components and with structures of the visual network. We also noted a decrease in FC of the salience network with sensorimotor and visual networks, as well as an increase in FC of the visual network. Besides, we identified 5 patients who did not have a positive response to one rTMS course after the first week of treatment according to the clinical scales results, presumably because of an increasing trend of depressive symptoms and neuroimaging criteria for depressive disorder.

Conclusions

Our results show that a 5-day course of rTMS significantly alters the connectivity of brain networks associated with pain and antinociceptive brain systems in about 70% of cases, which may shed light on the neural mechanisms underlying migraine treatment with rTMS.

Effects of a history of headache and migraine treatment on baseline neurocognitive function in young athletes

Objective/background

Despite the prevalence of concussions in young athletes, the impact of headaches on neurocognitive function at baseline is poorly understood. We analyze the effects of a history of headache treatment on baseline ImPACT composite scores in young athletes.

Methods

A total of 11,563 baseline ImPACT tests taken by 7,453 student-athletes ages 12-22 between 2009 and 2019 were reviewed. The first baseline test was included. There were 960 subjects who reported a history of treatment for headache and/or migraine (HA) and 5,715 controls (CT). The HA cohort included all subjects who self-reported a history of treatment for migraine or other type of headache on the standardized questionnaire. Chi-squared tests were used to compare demographic differences. Univariate and multivariate regression analyses were used to assess differences in baseline composite scores between cohorts while controlling for demographic differences and symptom burden.

Results

Unadjusted analyses demonstrated that HA was associated with increased symptoms (β=2.30, 95% CI: 2.18-2.41, p<.0001), decreased visual memory (β=-1.35, 95% CI: -2.62 to -0.43, p=.004), and increased visual motor speed (β=0.71, 95% CI: 0.23-1.19, p=.004) composite scores. Baseline scores for verbal memory, reaction time, and impulse control were not significantly different between cohorts. Adjusted analyses demonstrated similar results with HA patients having greater symptom burden (β=1.40, 95% CI: 1.10-1.70, p<.0001), lower visual memory (β=-1.25, 95% CI: -2.22 to -0.27, p=.01), and enhanced visual motor speed (β=0.60, 95% CI: 0.11-1.10, p=.02) scores.

Conclusion

HA affected symptom, visual motor speed, and visual memory ImPACT composite scores. Visual memory scores and symptom burden were significantly worse in the HA group while visual motor speed scores were better, which may have been due to higher stimulant use in the HA group. The effects of HA on visual motor speed and visual memory scores were independent of the effects of the increased symptom burden.

Supplementary Information

The online version contains supplementary material available at 10.1186/s10194-022-01432-w.

Functional Connectivity Features of Resting-State Functional Magnetic Resonance Imaging May Distinguish Migraine From Tension-Type Headache

Background

Migraineurs often exhibited abnormalities in cognition, emotion, and resting-state functional connectivity (rsFC), whereas patients with tension-type headache (TTH) rarely exhibited these abnormalities. The aim of this study is to explore whether rsFC alterations in brain regions related to cognition and emotion could be used to distinguish patients with migraine from patients with TTH.

Methods

In this study, Montreal Cognitive Assessment (MoCA), Self-Rating Anxiety Scale (SAS), Self-Rating Depression Scale (SDS), and rsFC analyses were used to assess the cognition, anxiety, and depression of 24 healthy controls (HCs), 24 migraineurs, and 24 patients with TTH. Due to their important roles in neuropsychological functions, the bilateral amygdala and hippocampus were chosen as seed regions for rsFC analyses. We further assessed the accuracy of the potential rsFC alterations for distinguishing migraineurs from non-migraineurs (including HCs and patients with TTH) by the receiver operating characteristic (ROC) analysis. Associations between headache characteristics and rsFC features were calculated using a multi-linear regression model. This clinical trial protocol has been registered in the Chinese Clinical Trial Registry (registry number: ChiCTR1900024307, Registered: 5 July 2019-Retrospectively registered, http://www.chictr.org.cn/showproj.aspx?proj=40817).

Results

Migraineurs showed lower MoCA scores (p = 0.010) and higher SAS scores (p = 0.017) than HCs. Migraineurs also showed decreased rsFC in the bilateral calcarine/cuneus, lingual gyrus (seed: left amygdala), and bilateral calcarine/cuneus (seed: left hippocampus) in comparison to HCs and patients with TTH. These rsFC features demonstrated significant distinguishing capabilities and got a sensitivity of 82.6% and specificity of 81.8% with an area under the curve (AUC) of 0.868. rsFC alterations showed a significant correlation with headache frequency in migraineurs (p = 0.001, Pc = 0.020).

Conclusion

The rsFC of amygdala and hippocampus with occipital lobe can be used to distinguish patients with migraine from patients with TTH.

Clinical Trial Registration

[http://www.chictr.org.cn/showproj.aspx?proj=40817], identifier [ChiCTR1900024307].

Machine Learning for Detecting Parkinson's Disease by Resting-State Functional Magnetic Resonance Imaging: A Multicenter Radiomics Analysis

Parkinson's disease (PD) is one of the most common progressive degenerative diseases, and its diagnosis is challenging on clinical grounds. Clinically, effective and quantifiable biomarkers to detect PD are urgently needed. In our study, we analyzed data from two centers, the primary set was used to train the model, and the independent external validation set was used to validate our model. We applied amplitude of low-frequency fluctuation (ALFF)-based radiomics method to extract radiomics features (including first- and high-order features). Subsequently, t-test and least absolute shrinkage and selection operator (LASSO) were harnessed for feature selection and data dimensionality reduction, and grid search method and nested 10-fold cross-validation were applied to determine the optimal hyper-parameter λ of LASSO and evaluate the performance of the model, in which a support vector machine was used to construct the classification model to classify patients with PD and healthy controls (HCs). We found that our model achieved good performance [accuracy = 81.45% and area under the curve (AUC) = 0.850] in the primary set and good generalization in the external validation set (accuracy = 67.44% and AUC = 0.667). Most of the discriminative features were high-order radiomics features, and the identified brain regions were mainly located in the sensorimotor network and lateral parietal cortex. Our study indicated that our proposed method can effectively classify patients with PD and HCs, ALFF-based radiomics features that might be potential biomarkers of PD, and provided further support for the pathological mechanism of PD, that is, PD may be related to abnormal brain activity in the sensorimotor network and lateral parietal cortex.