Objective To evaluate the efficacy, safety, and tolerability of noninvasive vagus nerve stimulation (nVNS; gammaCore; electroCore, LLC, Basking Ridge, NJ) for the acute treatment of migraine in a multicenter, double-blind, randomized, sham-controlled trial. Methods A total of 248 participants with episodic migraine with/without aura were randomized to receive nVNS or sham within 20 minutes from pain onset. Participants were to repeat treatment if pain had not improved in 15 minutes. Results nVNS (n = 120) was superior to sham (n = 123) for pain freedom at 30 minutes (12.7% vs 4.2%; p = 0.012) and 60 minutes (21.0% vs 10.0%; p = 0.023) but not at 120 minutes (30.4% vs 19.7%; p = 0.067; primary endpoint; logistic regression) after the first treated attack. A post hoc repeated-measures test provided further insight into the therapeutic benefit of nVNS through 30, 60, and 120 minutes (odds ratio 2.3; 95% confidence interval 1.2, 4.4; p = 0.012). nVNS demonstrated benefits across other endpoints including pain relief at 120 minutes and was safe and well-tolerated. Conclusion This randomized sham-controlled trial supports the abortive efficacy of nVNS as early as 30 minutes and up to 60 minutes after an attack. Findings also suggest effective pain relief, tolerability, and practicality of nVNS for the acute treatment of episodic migraine. ClinicalTrials.gov identifier NCT02686034. Classification of evidence This study provides Class I evidence that for patients with an episodic migraine, nVNS significantly increases the probability of having mild pain or being pain-free 2 hours poststimulation (absolute difference 13.2%).

The aim of this study was to determine which supervised machine learning (ML) algorithm can most accurately classify people with Parkinson’s disease (pwPD) from speed-matched healthy subjects (HS) based on a selected minimum set of IMU-derived gait features. Twenty-two gait features were extrapolated from the trunk acceleration patterns of 81 pwPD and 80 HS, including spatiotemporal, pelvic kinematics, and acceleration-derived gait stability indexes. After a three-level feature selection procedure, seven gait features were considered for implementing five ML algorithms: support vector machine (SVM), artificial neural network, decision trees (DT), random forest (RF), and K-nearest neighbors. Accuracy, precision, recall, and F1 score were calculated. SVM, DT, and RF showed the best classification performances, with prediction accuracy higher than 80% on the test set. The conceptual model of approaching ML that we proposed could reduce the risk of overrepresenting multicollinear gait features in the model, reducing the risk of overfitting in the test performances while fostering the explainability of the results.

Introduction: The management of medication-overuse headache (MOH) is often difficult and no specific guidelines are available as regards the most practical and effective approaches. In this study we defined and tested a consensus protocol for the management of MOH on a large population of patients distributed in different countries. Subjects and methods: The protocol was based on evidence from the literature and on consolidated expertise of the members of the consensus group. The study was conducted according to a multicentric interventional design with the enrolment of 376 MOH subjects in four centres from Europe and two centres in Latin America. The majority of patients were treated according to an outpatient detoxification programme. The post-detoxification follow-up lasted six months. Results: At the final evaluation, two-thirds of the subjects were no longer overusers and in 46.5% of subjects headache had reverted back to an episodic pattern of headache. When comparing the subjects who underwent out-patient detoxification vs those treated with in-patient detoxification, both regimens proved effective, although the drop-out rate was higher in the out-patient approach. Conclusions: The present findings support the effectiveness and usability of the proposed consensus protocol in different countries with different health care modalities.

Migraine is a major neurological disorder affecting one in nine adults worldwide with a significant impact on health care and socioeconomic systems. Migraine is more prevalent in women than in men, with 17% of all women meeting the diagnostic criteria for migraine. In women, the frequency of migraine attacks shows variations over the menstrual cycle and pregnancy, and the use of combined hormonal contraception (CHC) or hormone replacement therapy (HRT) can unveil or modify migraine disease. In the general population, 18–25% of female migraineurs display a menstrual association of their headache. Here we present an overview on the evidence supporting the role of reproductive hormones, in particular estrogens, in the pathophysiology of migraine. We also analyze the efficacy and safety of prescribing exogenous estrogens as a potential treatment for menstrual-related migraine. Finally, we point to controversial issues and future research areas in the field of reproductive hormones and migraine.

The interpretability of gait analysis studies in people with rare diseases, such as those with primary hereditary cerebellar ataxia (pwCA), is frequently limited by the small sample sizes and unbalanced datasets. The purpose of this study was to assess the effectiveness of data balancing and generative artificial intelligence (AI) algorithms in generating synthetic data reflecting the actual gait abnormalities of pwCA. Gait data of 30 pwCA (age: 51.6 ± 12.2 years; 13 females, 17 males) and 100 healthy subjects (age: 57.1 ± 10.4; 60 females, 40 males) were collected at the lumbar level with an inertial measurement unit. Subsampling, oversampling, synthetic minority oversampling, generative adversarial networks, and conditional tabular generative adversarial networks (ctGAN) were applied to generate datasets to be input to a random forest classifier. Consistency and explainability metrics were also calculated to assess the coherence of the generated dataset with known gait abnormalities of pwCA. ctGAN significantly improved the classification performance compared with the original dataset and traditional data augmentation methods. ctGAN are effective methods for balancing tabular datasets from populations with rare diseases, owing to their ability to improve diagnostic models with consistent explainability.