Artificial intelligence and headache

BACKGROUND AND METHODS

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

RESULTS

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

CONCLUSIONS

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

Exploring potential neuroimaging biomarkers for the response to non-steroidal anti-inflammatory drugs in episodic migraine

BACKGROUND

Non-steroidal anti-inflammatory drugs (NSAIDs) are considered first-line medications for acute migraine attacks. However, the response exhibits considerable variability among individuals. Thus, this study aimed to explore a machine learning model based on the percentage of amplitude oscillations (PerAF) and gray matter volume (GMV) to predict the response to NSAIDs in migraine treatment.

METHODS

Propensity score matching was adopted to match patients having migraine with response and nonresponse to NSAIDs, ensuring consistency in clinical characteristics and migraine-related features. Multimodal magnetic resonance imaging was employed to extract PerAF and GMV, followed by feature selection using the least absolute shrinkage and selection operator regression and recursive feature elimination algorithms. Multiple predictive models were constructed and the final model with the smallest predictive residuals was chosen. The model performance was evaluated using the area under the receiver operating characteristic (ROCAUC) curve, area under the precision-recall curve (PRAUC), balance accuracy (BACC), sensitivity, F1 score, positive predictive value (PPV), and negative predictive value (NPV). External validation was performed using a public database. Then, correlation analysis was performed between the neuroimaging predictors and clinical features in migraine.

RESULTS

One hundred eighteen patients with migraine (59 responders and 59 non-responders) were enrolled. Six features (PerAF of left insula and left transverse temporal gyrus; and GMV of right superior frontal gyrus, left postcentral gyrus, right postcentral gyrus, and left precuneus) were observed. The random forest model with the lowest predictive residuals was selected and model metrics (ROCAUC, PRAUC, BACC, sensitivity, F1 score, PPV, and NPV) in the training and testing groups were 0.982, 0.983, 0.927, 0.976, 0.930, 0.889, and 0.973; and 0.711, 0.648, 0.639, 0.667,0.649, 0.632, and 0.647, respectively. The model metrics of external validation were 0.631, 0.651, 0.611, 0.808, 0.656, 0.553, and 0.706. Additionally, a significant positive correlation was found between the GMV of the left precuneus and attack time in non-responders.

CONCLUSIONS

Our findings suggest the potential of multimodal neuroimaging features in predicting the efficacy of NSAIDs in migraine treatment and provide novel insights into the neural mechanisms underlying migraine and its optimized treatment strategy.

Parkinson's disease diagnosis using deep learning: A bibliometric analysis and literature review

Parkinson's Disease (PD) is a progressive neurodegenerative illness triggered by decreased dopamine secretion. Deep Learning (DL) has gained substantial attention in PD diagnosis research, with an increase in the number of published papers in this discipline. PD detection using DL has presented more promising outcomes as compared with common machine learning approaches. This article aims to conduct a bibliometric analysis and a literature review focusing on the prominent developments taking place in this area. To achieve the target of the study, we retrieved and analyzed the available research papers in the Scopus database. Following that, we conducted a bibliometric analysis to inspect the structure of keywords, authors, and countries in the surveyed studies by providing visual representations of the bibliometric data using VOSviewer software. The study also provides an in-depth review of the literature focusing on different indicators of PD, deployed approaches, and performance metrics. The outcomes indicate the firm development of PD diagnosis using DL approaches over time and a large diversity of studies worldwide. Additionally, the literature review presented a research gap in DL approaches related to incremental learning, particularly in relation to big data analysis.

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

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

Machine learning approach for Migraine Aura Complexity Score prediction based on magnetic resonance imaging data

BACKGROUND

Previous studies have developed the Migraine Aura Complexity Score (MACS) system. MACS shows great potential in studying the complexity of migraine with aura (MwA) pathophysiology especially when implemented in neuroimaging studies. The use of sophisticated machine learning (ML) algorithms, together with deep profiling of MwA, could bring new knowledge in this field. We aimed to test several ML algorithms to study the potential of structural cortical features for predicting the MACS and therefore gain a better insight into MwA pathophysiology.

METHODS

The data set used in this research consists of 340 MRI features collected from 40 MwA patients. Average MACS score was obtained for each subject. Feature selection for ML models was performed using several approaches, including a correlation test and a wrapper feature selection methodology. Regression was performed with the Support Vector Machine (SVM), Linear Regression, and Radial Basis Function network.

RESULTS

SVM achieved a 0.89 coefficient of determination score with a wrapper feature selection. The results suggest a set of cortical features, located mostly in the parietal and temporal lobes, that show changes in MwA patients depending on aura complexity.

CONCLUSIONS

The SVM algorithm demonstrated the best potential in average MACS prediction when using a wrapper feature selection methodology. The proposed method achieved promising results in determining MwA complexity, which can provide a basis for future MwA studies and the development of MwA diagnosis and treatment.

Quantitative electroencephalography as a potential biomarker in migraine

OBJECTIVE

The aim of this study was to investigate the utility of quantitative electroencephalography (QEEG) as a diagnostic tool for migraine and as an indicator of treatment response by comparing QEEG characteristics between migraine patients and controls, and monitoring changes in these characteristics alongside clinical symptoms in response to treatment BACKGROUND: We hypothesized that patients with migraine exhibit distinctive characteristics in QEEG measurements, which could be used as potential diagnostic biomarkers and as a tool for monitoring treatment response.

METHODS

A total of 720 patients were included in the study, comprising 619 patients with migraine and 101 subjects as a control group. QEEG measurements were analyzed for absolute power across specific frequency bands: delta wave (0.5-4 Hz), theta wave (4-8 Hz), alpha wave (8-12 Hz), beta wave (12-25 Hz), and high beta wave (25-30 Hz). The absolute power was normalized against a normative dataset from NeuroGuide, with electrodes being highlighted for significance if they exceeded 1.96. Clinical symptoms were also monitored for correlation with QEEG changes.

RESULTS

Our analysis showed that patients with migraine exhibited significantly higher absolute power across all frequencies, most markedly within the high beta frequency range. When considering electrodes with z-scores exceeding the threshold of 1.96 in the high beta range, a significant association with migraine diagnosis was observed (per 1 electrode increase, OR 1.06; 95% CI 1.01-1.11; p = .012). Moreover, pre- and posttreatment changes in QEEG measurements corresponded with changes in clinical symptoms.

CONCLUSION

Patients with migraine have distinctive QEEG measurements, particularly regarding absolute power and the number of electrodes that surpassed the z-score threshold in high beta wave activity. These findings suggest the potential of QEEG as a diagnostic biomarker and as a tool for monitoring treatment response in migraine patients, warranting further large-scale studies for confirmation and expansion.

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.

Migraine Aura-Catch Me If You Can with EEG and MRI-A Narrative Review

Roughly one-third of migraine patients suffer from migraine with aura, characterized by transient focal neurological symptoms or signs such as visual disturbance, sensory abnormalities, speech problems, or paresis in association with the headache attack. Migraine with aura is associated with an increased risk for stroke, epilepsy, and with anxiety disorder. Diagnosis of migraine with aura sometimes requires exclusion of secondary causes if neurological deficits present for the first time or are atypical. It was the aim of this review to summarize EEG an MRI findings during migraine aura in the context of pathophysiological concepts. This is a narrative review based on a systematic literature search. During visual auras, EEG showed no consistent abnormalities related to aura, although transient focal slowing in occipital regions has been observed in quantitative studies. In contrast, in familial hemiplegic migraine (FHM) and migraine with brain stem aura, significant EEG abnormalities have been described consistently, including slowing over the affected hemisphere or bilaterally or suppression of EEG activity. Epileptiform potentials in FHM are most likely attributable to associated epilepsy. The initial perfusion change during migraine aura is probably a short lasting hyperperfusion. Subsequently, perfusion MRI has consistently demonstrated cerebral hypoperfusion usually not restricted to one vascular territory, sometimes associated with vasoconstriction of peripheral arteries, particularly in pediatric patients, and rebound hyperperfusion in later phases. An emerging potential MRI signature of migraine aura is the appearance of dilated veins in susceptibility-weighted imaging, which may point towards the cortical regions related to aura symptoms ("index vein"). Conclusions: Cortical spreading depression (CSD) cannot be directly visualized but there are probable consequences thereof that can be captured Non-invasive detection of CSD is probably very challenging in migraine. Future perspectives will be elaborated based on the studies summarized.

Levcromakalim provokes an acute rapid-onset migraine-like phenotype without inducing cortical spreading depolarization

BACKGROUND

Migraine headache attacks and accompanying sensory augmentation can be induced by several agents including levcromakalim (LVC), that is also capable of provoking aura-like symptoms in migraineurs. We investigated whether single LVC injection causes acute migraine-like phenotype in rats and induces/modulates cortical spreading depolarization (CSD), a rodent model of migraine aura.

METHODS

Wistar rats were administered LVC (1 mg/kg, i.p.) and compared to control (CTRL, vehicle, i.p.) and nitroglycerin (NTG, 10 mg/kg, i.p.) groups. Von Frey filaments were used to examine the periorbital and hind paw mechanical allodynia. Dark-light box (DLB), elevated plus maze (EPM), and open field arena (OFA) were used to evaluate light sensitivity and anxiety-related behaviors. The effects of LVC on CSD parameters, somatosensory evoked potentials, and baseline dural EEG (electroencephalography) were investigated. Possible CSD-induced c-fos expression was studied with Western Blot. Blood-brain barrier integrity in cortex was examined with Evans blue assay.

RESULTS

LVC and NTG administration robustly reduced periorbital mechanical thresholds in rats and induced anxiety-like behaviors and photophobia within 30 and 120 min, respectively. LVC induced migraine-like phenotype recovered in 2 h while NTG group did not fully recover before 4 h. Both LVC and NTG did not provoke DC (direct current) shift, EEG alterations or cortical c-fos expression characteristic to CSD. LVC did not induce de novo CSD and affect KCl (potassium chloride)-induced CSD parameters except for an increase in propagation failure. However, NTG significantly increased both CSD susceptibility and propagation failure. Somatosensory evoked potential (SSEP) configurations were not altered in both LVC and NTG groups, but SSEP latencies were prolonged after CSD. Acute LVC or NTG injection did not increase cortical BBB permeability.

CONCLUSIONS

Single LVC administration induced the fastest manifestation and recovery of acute migraine-like phenotype which was not mediated by CSD waves in the cerebral cortex. We suppose LVC triggered rapid-onset migraine-like symptoms are probably related to functional alterations in the trigeminal nociceptive system and K⁺ channel opening properties of LVC. Understanding the neurobiological mechanisms of this nociceptive window, may provide a novel target in migraine treatment.

The Objective Assessment of Event-Related Potentials: An Influence of Chronic Pain on ERP Parameters

The article presents an original method for the automatic assessment of the quality of event-related potentials (ERPs), based on the calculation of the coefficient ε, which describes the compliance of recorded ERPs with some statistically significant parameters. This method was used to analyze the neuropsychological EEG monitoring of patients suffering from migraines. The frequency of migraine attacks was correlated with the spatial distribution of the coefficients ε, calculated for EEG channels. More than 15 migraine attacks per month was accompanied by an increase in calculated values in the occipital region. Patients with infrequent migraines exhibited maximum quality in the frontal areas. The automatic analysis of spatial maps of the coefficient ε demonstrated a statistically significant difference between the two analyzed groups with different means of migraine attack numbers per month.

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.

NeuralTree: A 256-Channel 0.227-μJ/Class Versatile Neural Activity Classification and Closed-Loop Neuromodulation SoC

Closed-loop neural interfaces with on-chip machine learning can detect and suppress disease symptoms in neurological disorders or restore lost functions in paralyzed patients. While high-density neural recording can provide rich neural activity information for accurate disease-state detection, existing systems have low channel counts and poor scalability, which could limit their therapeutic efficacy. This work presents a highly scalable and versatile closed-loop neural interface SoC that can overcome these limitations. A 256-channel time-division multiplexed (TDM) front-end with a two-step fast-settling mixed-signal DC servo loop (DSL) is proposed to record high-spatial-resolution neural activity and perform channel-selective brain-state inference. A tree-structured neural network (NeuralTree) classification processor extracts a rich set of neural biomarkers in a patient- and disease-specific manner. Trained with an energy-aware learning algorithm, the NeuralTree classifier detects the symptoms of underlying disorders (e.g., epilepsy and movement disorders) at an optimal energy-accuracy trade-off. A 16-channel high-voltage (HV) compliant neurostimulator closes the therapeutic loop by delivering charge-balanced biphasic current pulses to the brain. The proposed SoC was fabricated in 65nm CMOS and achieved a 0.227μJ/class energy efficiency in a compact area of 0.014mm2/channel. The SoC was extensively verified on human electroencephalography (EEG) and intracranial EEG (iEEG) epilepsy datasets, obtaining 95.6%/94% sensitivity and 96.8%/96.9% specificity, respectively. In-vivo neural recordings using soft μECoG arrays and multi-domain biomarker extraction were further performed on a rat model of epilepsy. In addition, for the first time in literature, on-chip classification of rest-state tremor in Parkinson's disease (PD) from human local field potentials (LFPs) was demonstrated.

Machine prescription for chronic migraine

Responsive to treatment individually, chronic migraine remains strikingly resistant collectively, incurring the second-highest population burden of disability worldwide. A heterogeneity of responsiveness, requiring prolonged-currently heuristic-individual evaluation of available treatments, may reflect a diversity of causal mechanisms, or the failure to identify the most important, single causal factor. Distinguishing between these possibilities, now possible through the application of complex modelling to large-scale data, is critical to determine the optimal approach to identify new interventions in migraine and making the best use of existing ones. Examining a richly phenotyped cohort of 1446 consecutive unselected patients with chronic migraine, here we use causal multitask Gaussian process models to estimate individual treatment effects across 10 classes of preventatives. Such modelling enables us to quantify the accessibility of heterogeneous responsiveness to high-dimensional modelling, to infer the likely scale of the underlying causal diversity. We calculate the treatment effects in the overall population, and the conditional treatment effects among those modelled to respond and compare the true response rates between these two groups. Identifying a difference in response rates between the groups supports a diversity of causal mechanisms. Moreover, we propose a data-driven machine prescription policy, estimating the time-to-response when sequentially trialling preventatives by individualized treatment effects and comparing it to expert guideline sequences. All model performances are quantified out-of-sample. We identify significantly higher true response rates among individuals modelled to respond, compared with the overall population (mean difference of 0.034; 95% confidence interval 0.003-0.065; P = 0.033), supporting significant heterogeneity of responsiveness and diverse causal mechanisms. The machine prescription policy yields an estimated 35% reduction in time-to-response (3.750 months; 95% confidence interval 3.507-3.993; P < 0.0001) compared with expert guidelines, with no substantive increase in expense per patient. We conclude that the highly distributed mode of causation in chronic migraine necessitates high-dimensional modelling for optimal management. Machine prescription should be considered an essential clinical decision-support tool in the future management of chronic migraine.

Fast and accurate decoding of finger movements from ECoG through Riemannian features and modern machine learning techniques

Objective: Accurate decoding of individual finger movements is crucial for advanced prosthetic control. In this work, we introduce the use of Riemannian-space features and temporal dynamics of electrocorticography (ECoG) signal combined with modern machine learning tools to improve the motor decoding accuracy at the level of individual fingers. Approach: We selected a set of informative biomarkers that correlated with finger movements and evaluated the performance of state-of-the-art machine learning algorithms on the BCI competition IV dataset (ECoG, three subjects) and a second ECoG dataset with a similar recording paradigm (Stanford, 9 subjects). We further explored the temporal concatenation of features to effectively capture the history of ECoG signal, which led to a significant improvement over single-epoch decoding in both classification (p<0.01) and regression tasks (p<0.01). Main results: Using feature concatenation and gradient boosted trees (the top-performing model), we achieved a classification accuracy of 77.0% in detecting individual finger movements (6-class task, including rest state), improving over the state-of-the-art conditional random fields (CRF) by 11.7% on the 3 BCI competition subjects. In continuous decoding of movement trajectory, our approach resulted in an average Pearson's correlation coefficient (r) of 0.537 across subjects and fingers, outperforming both the BCI competition winner and the state-of-the-art approach reported on the same dataset (CNN+LSTM). Furthermore, our proposed method features a low time complexity, with only <17.2s required for training and <50ms for inference. This enables about 250× speed-up in training compared to previously reported deep learning method with state-of-the-art performance. Significance: The proposed techniques enable fast, reliable, and high-performance prosthetic control through minimally-invasive cortical signals.

Closed-Loop Neural Prostheses With On-Chip Intelligence: A Review and a Low-Latency Machine Learning Model for Brain State Detection

The application of closed-loop approaches in systems neuroscience and therapeutic stimulation holds great promise for revolutionizing our understanding of the brain and for developing novel neuromodulation therapies to restore lost functions. Neural prostheses capable of multi-channel neural recording, on-site signal processing, rapid symptom detection, and closed-loop stimulation are critical to enabling such novel treatments. However, the existing closed-loop neuromodulation devices are too simplistic and lack sufficient on-chip processing and intelligence. In this paper, we first discuss both commercial and investigational closed-loop neuromodulation devices for brain disorders. Next, we review state-of-the-art neural prostheses with on-chip machine learning, focusing on application-specific integrated circuits (ASIC). System requirements, performance and hardware comparisons, design trade-offs, and hardware optimization techniques are discussed. To facilitate a fair comparison and guide design choices among various on-chip classifiers, we propose a new energy-area (E-A) efficiency figure of merit that evaluates hardware efficiency and multi-channel scalability. Finally, we present several techniques to improve the key design metrics of tree-based on-chip classifiers, both in the context of ensemble methods and oblique structures. A novel Depth-Variant Tree Ensemble (DVTE) is proposed to reduce processing latency (e.g., by 2.5× on seizure detection task). We further develop a cost-aware learning approach to jointly optimize the power and latency metrics. We show that algorithm-hardware co-design enables the energy- and memory-optimized design of tree-based models, while preserving a high accuracy and low latency. Furthermore, we show that our proposed tree-based models feature a highly interpretable decision process that is essential for safety-critical applications such as closed-loop stimulation.

Predicting task performance from biomarkers of mental fatigue in global brain activity

Objective.

Detection and early prediction of mental fatigue (i.e. shifts in vigilance), could be used to adapt neuromodulation strategies to effectively treat patients suffering from brain injury and other indications with prominent chronic mental fatigue.

Approach.

In this study, we analyzed electrocorticography (ECoG) signals chronically recorded from two healthy non-human primates (NHP) as they performed a sustained attention task over extended periods of time. We employed a set of spectrotemporal and connectivity biomarkers of the ECoG signals to identify periods of mental fatigue and a gradient boosting classifier to predict performance, up to several seconds prior to the behavioral response.

Main results.

Wavelet entropy and the instantaneous amplitude and frequency were among the best single features across sessions in both NHPs. The classification performance using higher order spectral-temporal (HOST) features was significantly higher than that of conventional spectral power features in both NHPs. Across the 99 sessions analyzed, average F1 scores of 77.5%±8.2% and 91.2%±3.6%, and accuracy of 79.5%±8.9% and 87.6%±3.9 % for the classifier were obtained for each animal, respectively.

Significance.

Our results here demonstrate the feasibility of predicting performance and detecting periods of mental fatigue by analyzing ECoG signals, and that this general approach, in principle, could be used for closed-loop control of neuromodulation strategies.

Somatosensory Gating Responses Are Associated with Prognosis in Patients with Migraine

Sensory gating, a habituation-related but more basic protective mechanism against brain sensory overload, is altered in patients with migraine and linked to headache severity. This study investigated whether somatosensory (SI) gating responses determined 3-months treatment outcomes in patients with episodic migraine (EM) and chronic migraine (CM). A 306-channel magnetoencephalography (MEG) with paired-pulse stimulation paradigm was used to record their neuromagnetic responses. To calculate the peak amplitude and latency and compute the gating ratios (second vs. first amplitude), the first and second responses to the paired stimuli from the primary somatosensory cortex were obtained. All patients were assigned to subgroups labeled good or poor according to their headache frequency at baseline compared with at the third month of treatment. The gating ratio in the CM group (n = 37) was significantly different between those identified as good and poor (p = 0.009). In the EM group (n = 30), the latency in the second response differed by treatment outcomes (p = 0.007). In the receiver operating characteristic analysis, the areas under the curve for the CM and EM groups were 0.737 and 0.761, respectively. Somatosensory gating responses were associated with treatment outcomes in patients with migraine; future studies with large patient samples are warranted.

How does the brain change in chronic migraine? Developing disease biomarkers

BACKGROUND

Validated chronic migraine biomarkers could improve diagnostic, prognostic, and predictive abilities for clinicians and researchers, as well as increase knowledge on migraine pathophysiology.

OBJECTIVE

The objective of this narrative review is to summarise and interpret the published literature regarding the current state of development of chronic migraine biomarkers.

FINDINGS

Data from functional and structural imaging, neurophysiological, and biochemical studies have been utilised towards the development of chronic migraine biomarkers. These biomarkers could contribute to chronic migraine classification/diagnosis, prognosticating patient outcomes, predicting response to treatment, and measuring treatment responses early after initiation. Results show promise for using measures of brain structure and function, evoked potentials, and sensory neuropeptide concentrations for the development of chronic migraine biomarkers, yet further optimisation and validation are still required.

CONCLUSIONS

Imaging, neurophysiological, and biochemical changes that occur with the progression from episodic to chronic migraine could be utilised for developing chronic migraine biomarkers that might assist with diagnosis, prognosticating individual patient outcomes, and predicting responses to migraine therapies. Ultimately, validated biomarkers could move us closer to being able to practice precision medicine in the field and thus improve patient care.

Machine learning-based automated classification of headache disorders using patient-reported questionnaires

Classification of headache disorders is dependent on a subjective self-report from patients and its interpretation by physicians. We aimed to apply objective data-driven machine learning approaches to analyze patient-reported symptoms and test the feasibility of the automated classification of headache disorders. The self-report data of 2162 patients were analyzed. Headache disorders were merged into five major entities. The patients were divided into training (n = 1286) and test (n = 876) cohorts. We trained a stacked classifier model with four layers of XGBoost classifiers. The first layer classified between migraine and others, the second layer classified between tension-type headache (TTH) and others, and the third layer classified between trigeminal autonomic cephalalgia (TAC) and others, and the fourth layer classified between epicranial and thunderclap headaches. Each layer selected different features from the self-reports by using least absolute shrinkage and selection operator. In the test cohort, our stacked classifier obtained accuracy of 81%, sensitivity of 88%, 69%, 65%, 53%, and 51%, and specificity of 95%, 55%, 46%, 48%, and 51% for migraine, TTH, TAC, epicranial headache, and thunderclap headaches, respectively. We showed that a machine-learning based approach is applicable in analyzing patient-reported questionnaires. Our result could serve as a baseline for future studies in headache research.

ResOT: Resource-Efficient Oblique Trees for Neural Signal Classification

Classifiers that can be implemented on chip with minimal computational and memory resources are essential for edge computing in emerging applications such as medical and IoT devices. This paper introduces a machine learning model based on oblique decision trees to enable resource-efficient classification on a neural implant. By integrating model compression with probabilistic routing and implementing cost-aware learning, our proposed model could significantly reduce the memory and hardware cost compared to state-of-the-art models, while maintaining the classification accuracy. We trained the resource-efficient oblique tree with power-efficient regularization (ResOT-PE) on three neural classification tasks to evaluate the performance, memory, and hardware requirements. On seizure detection task, we were able to reduce the model size by 3.4× and the feature extraction cost by 14.6× compared to the ensemble of boosted trees, using the intracranial EEG from 10 epilepsy patients. In a second experiment, we tested the ResOT-PE model on tremor detection for Parkinson's disease, using the local field potentials from 12 patients implanted with a deep-brain stimulation (DBS) device. We achieved a comparable classification performance as the state-of-the-art boosted tree ensemble, while reducing the model size and feature extraction cost by 10.6× and 6.8×, respectively. We also tested on a 6-class finger movement detection task using ECoG recordings from 9 subjects, reducing the model size by 17.6× and feature computation cost by 5.1×. The proposed model can enable a low-power and memory-efficient implementation of classifiers for real-time neurological disease detection and motor decoding.

The visual system as target of non-invasive brain stimulation for migraine treatment: Current insights and future challenges

The visual network is crucially implicated in the pathophysiology of migraine. Several lines of evidence indicate that migraine is characterized by an altered visual cortex excitability both during and between attacks. Visual symptoms, the most common clinical manifestation of migraine aura, are likely the result of cortical spreading depression originating from the extrastriate area V3A. Photophobia, a clinical hallmark of migraine, is linked to an abnormal sensory processing of the thalamus which is converged with the non-image forming visual pathway. Finally, visual snow is an increasingly recognized persistent visual phenomenon in migraine, possibly caused by increased perception of subthreshold visual stimuli. Emerging research in non-invasive brain stimulation (NIBS) has vastly developed into a diversity of areas with promising potential. One of its clinical applications is the single-pulse transcranial magnetic stimulation (sTMS) applied over the occipital cortex which has been approved for treating migraine with aura, albeit limited evidence. Studies have also investigated other NIBS techniques, such as repetitive TMS (rTMS) and transcranial direct current stimulation (tDCS), for migraine prophylaxis but with conflicting results. As a dynamic brain disorder with widespread pathophysiology, targeting migraine with NIBS is challenging. Furthermore, unlike the motor cortex, evidence suggests that the visual cortex may be less plastic. Controversy exists as to whether the same fundamental principles of NIBS, based mainly on findings in the motor cortex, can be applied to the visual cortex. This review aims to explore existing literature surrounding NIBS studies on the visual system of migraine. We will first provide an overview highlighting the direct implication of the visual network in migraine. Next, we will focus on the rationale behind using NIBS for migraine treatment, including its effects on the visual cortex, and the shortcomings of currently available evidence. Finally, we propose a broader perspective of how novel approaches, the concept of brain networks and the integration of multimodal imaging with computational modeling, can help refine current NIBS methods, with the ultimate goal of optimizing a more individualized treatment for migraine.

Machine learning approach to predict medication overuse in migraine patients

Machine learning (ML) is largely used to develop automatic predictors in migraine classification but automatic predictors for medication overuse (MO) in migraine are still in their infancy. Thus, to understand the benefits of ML in MO prediction, we explored an automated predictor to estimate MO risk in migraine. To achieve this objective, a study was designed to analyze the performance of a customized ML-based decision support system that combines support vector machines and Random Optimization (RO-MO). We used RO-MO to extract prognostic information from demographic, clinical and biochemical data. Using a dataset of 777 consecutive migraine patients we derived a set of predictors with discriminatory power for MO higher than that observed for baseline SVM. The best four were incorporated into the final RO-MO decision support system and risk evaluation on a five-level stratification was performed. ROC analysis resulted in a c-statistic of 0.83 with a sensitivity and specificity of 0.69 and 0.87, respectively, and an accuracy of 0.87 when MO was predicted by at least three RO-MO models. Logistic regression analysis confirmed that the derived RO-MO system could effectively predict MO with ORs of 5.7 and 21.0 for patients classified as probably (3 predictors positive), or definitely at risk of MO (4 predictors positive), respectively. In conclusion, a combination of ML and RO - taking into consideration clinical/biochemical features, drug exposure and lifestyle - might represent a valuable approach to MO prediction in migraine and holds the potential for improving model precision through weighting the relative importance of attributes.

Improved detection of Parkinsonian resting tremor with feature engineering and Kalman filtering

OBJECTIVE

Accurate and reliable detection of tremor onset in Parkinson's disease (PD) is critical to the success of adaptive deep brain stimulation (aDBS) therapy. Here, we investigated the potential use of feature engineering and machine learning methods for more accurate detection of rest tremor in PD.

METHODS

We analyzed the local field potential (LFP) recordings from the subthalamic nucleus region in 12 patients with PD (16 recordings). To explore the optimal biomarkers and the best performing classifier, the performance of state-of-the-art machine learning (ML) algorithms and various features of the subthalamic LFPs were compared. We further used a Kalman filtering technique in feature domain to reduce the false positive rate.

RESULTS

The Hjorth complexity showed a higher correlation with tremor, compared to other features in our study. In addition, by optimal selection of a maximum of five features with a sequential feature selection method and using the gradient boosted decision trees as the classifier, the system could achieve an average F1 score of up to 88.7% and a detection lead of 0.52 s. The use of Kalman filtering in feature space significantly improved the specificity by 17.0% (p = 0.002), thereby potentially reducing the unnecessary power dissipation of the conventional DBS system.

CONCLUSION

The use of relevant features combined with Kalman filtering and machine learning improves the accuracy of tremor detection during rest.

SIGNIFICANCE

The proposed method offers a potential solution for efficient on-demand stimulation for PD tremor.

Electrophysiological Characteristics of the Migraine Brain: Current Knowledge and Perspectives

BACKGROUND

Despite pain being its most prominent feature, migraine is primarily a disorder of sensory processing. Electrophysiology-based research in the field has consistently developed over the last fifty years.

OBJECTIVE

To summarize the current knowledge on the electrophysiological characteristics of the migraine brain, and discuss perspectives.

METHODS

We critically reviewed the literature on the topic to present and discuss articles selected on the basis of their significance and/or novelty.

RESULTS

Physiologic fluctuations within time, between-subject differences, and methodological issues account as major limitations of electrophysiological research in migraine. Nonetheless, several abnormalities revealed through different approaches have been described in the literature. Altogether, these results are compatible with an abnormal state of sensory processing.

PERSPECTIVES

The greatest contribution of electrophysiological testing in the future will most probably be the characterization of sub-groups of migraine patients sharing specific electrophysiological traits. This should serve as strategy towards personalized migraine treatment. Incorporation of novel methods of analysis would be worthwhile.