Investigating the effects of weather on headache occurrence using a smartphone application and artificial intelligence: A retrospective observational cross-sectional study

Profiling chronic migraine patients according to clinical characteristics: a cluster analysis approach

Background

To group the characteristics of chronic migraine (CM) by headache characteristics.

Methods

We performed a retrospective analysis of the medical records of 821 adult CM patients who visited a specialized outpatient clinic for headaches. Using the headache characteristics, we performed Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering to group CM patients. The burdens to their lives, monthly headache days (MHD), monthly acute medication intake days (AMD), and treatment outcomes were evaluated among the clusters.

Results

Through a cluster analysis based on headache characteristics, our findings indicated the potential existence of three distinct types of CM: cluster 1 (predominantly female with CM resembling migraine), cluster 2 (higher age, higher BMI, smoker), and cluster 3 (mostly female with CM that have fewer migraine characteristics). The impact on quality of life was significant in cluster 1 compared to cluster 3. However, there were no differences in treatment outcomes, initial MHD, AMD, the years of migraine, or treatment sensitivity among these three clusters.

Conclusion

Cluster analysis mathematically divided CM patients into three groups, with predominant differences in the degree of disruption to their lives and their characteristics; further research is needed on the diagnostic criteria for CM and its characteristics.

Artificial Intelligence and Predictive Modeling in the Management and Treatment of Episodic Migraine

PURPOSE OF REVIEW

Artificial intelligence (AI) has impacted different aspects of headache medicine, from history taking and diagnosis to drug development. AI has been shown to have predictive modeling in helping diagnose migraine and assist with patient care. Additionally, this technology has been adapted to help non-headache specialists with headache management. Similar practices have expanded to help diagnose cluster headache. AI has also been used to help streamline patient visits, and identify new drug targets.

RECENT FINDINGS

Various forms of AI models have been implemented in headache medicine; these have ranged from diagnosis engines to models helping track headache triggers. Additionally, AI has been used to assist in clinical trials and to help predict placebo responses to different medications. There are still several limitations with AI in setting of headache medicine. AI and diagnosis models have a role to play in headache medicine. However, technology is still in its infancy and limitations do exist.

Time-dynamic associations between symptom-related expectations, self-management experiences and somatic symptom severity in everyday life: an ecological momentary assessment study with university students

OBJECTIVE

The present study investigated the associations between symptom-related expectations, self-management experiences and expectation framing on somatic symptom severity in university students in two conditions (positive or standard expectation framing). We hypothesised that symptom-related expectations are significantly associated with concurrent and subsequent levels of somatic symptom depending on expectation framing.

DESIGN

A smartphone-based micro-longitudinal ecological momentary assessment study with randomisation to one of two expectation framing groups (positive vs negative) was carried out. Multilevel mixed-effects linear regression analyses were conducted for data analysis.

SETTING

Data was collected in real-time from university students via smartphones, with three predetermined assessments per day over seven consecutive days.

PARTICIPANTS

A total of 104 students (63.5% male, 0% diverse) who were 18 years or older, possessing sufficient German language skills and had access to an Android-powered smartphone were included.

INTERVENTIONS

Participants were randomised to one of two different expectation framing groups, either receiving questionnaires for the expected impairment due to somatic symptoms (negative framing) or for the expected freedom from impairment due to somatic symptoms (positive framing).

PRIMARY OUTCOME MEASURES

Somatic symptom severity was assessed using an adapted version of the Patient Health Questionnaire, with 11-point instead of 3-point Likert-scales. Symptom-related expectations were assessed using 11-point Numerical Rating Scales and self-management experiences were assessed using binary variables.

RESULTS

Concurrent analysis revealed a significant association between symptom-related expectations and symptom severity (β=0.934, p<0.001), but no significant associations between self-management experiences and symptom severity. Regarding expectation framing, participants in the negative group reported higher symptom severity levels than those in the positive group (β=-0.071, p<0.001). Results indicated a stronger association between symptom-related expectations and symptom severity in the negative framing group (β=-0.088, p<0.001). Time-lagged analysis showed higher levels of symptom-related expectations predicted higher subsequent symptom severity levels (β=0.502, p<0.001), whereas preceding symptom severity levels or self-management experiences did not predict subsequent symptom severity levels. Negative framing was associated with higher subsequent symptom severity levels (β=-0.158, p<0.001). The effect of symptom-related expectations on subsequent symptom severity levels was independent of expectation framing.

CONCLUSIONS

Our findings highlight the impact of expectations and expectation framing on somatic symptom severity among university students and expand the knowledge needed for the development of expectation management techniques.

TRIAL REGISTRATION NUMBER

ISRCTN36251388.

Influence of next-generation artificial intelligence on headache research, diagnosis and treatment: the junior editorial board members' vision - part 2

Part 2 explores the transformative potential of artificial intelligence (AI) in addressing the complexities of headache disorders through innovative approaches, including digital twin models, wearable healthcare technologies and biosensors, and AI-driven drug discovery. Digital twins, as dynamic digital representations of patients, offer opportunities for personalized headache management by integrating diverse datasets such as neuroimaging, multiomics, and wearable sensor data to advance headache research, optimize treatment, and enable virtual trials. In addition, AI-driven wearable devices equipped with next-generation biosensors combined with multi-agent chatbots could enable real-time physiological and biochemical monitoring, diagnosing, facilitating early headache attack forecasting and prevention, disease tracking, and personalized interventions. Furthermore, AI-driven advances in drug discovery leverage machine learning and generative AI to accelerate the identification of novel therapeutic targets and optimize treatment strategies for migraine and other headache disorders. Despite these advances, challenges such as data standardization, model explainability, and ethical considerations remain pivotal. Collaborative efforts between clinicians, biomedical and biotechnological engineers, AI scientists, legal representatives and bioethics experts are essential to overcoming these barriers and unlocking AI's full potential in transforming headache research and healthcare. This is a call to action in proposing novel frameworks for integrating AI-based technologies into headache care.

Artificial intelligence terminology, methodology, and critical appraisal: A primer for headache clinicians and researchers

OBJECTIVE

The goal is to provide an overview of artificial intelligence (AI) and machine learning (ML) methodology and appraisal tailored to clinicians and researchers in the headache field to facilitate interdisciplinary communications and research.

BACKGROUND

The application of AI to the study of headache and other healthcare challenges is growing rapidly. It is critical that these findings be accurately interpreted by headache specialists, but this can be difficult for non-AI specialists.

METHODS

This paper is a narrative review of the fundamentals required to understand ML/AI headache research. Using guidance from key leaders in the field of headache medicine and AI, important references were reviewed and cited to provide a comprehensive overview of the terminology, methodology, applications, pitfalls, and bias of AI.

RESULTS

We review how AI models are created, common model types, methods for evaluation, and examples of their application to headache medicine. We also highlight potential pitfalls relevant when consuming AI research, and discuss ethical issues of bias, privacy and abuse generated by AI. Additionally, we highlight recent related research from across headache-related applications.

CONCLUSION

Many promising current and future applications of ML and AI exist in the field of headache medicine. Understanding the fundamentals of AI will allow readers to understand and critically appraise AI-related research findings in their proper context. This paper will increase the reader's comfort in consuming AI/ML-based research and will prepare them to think critically about related research developments.

Molecular and Cellular Neurobiology of Spreading Depolarization/Depression and Migraine: A Narrative Review

Migraine is a prevalent neurological disorder, particularly among individuals aged 20-50 years, with significant social and economic impacts. Despite its high prevalence, the pathogenesis of migraine remains unclear. In this review, we provide a comprehensive overview of cortical spreading depolarization/depression (CSD) and its close association with migraine aura, focusing on its role in understanding migraine pathogenesis and therapeutic interventions. We discuss historical studies that have demonstrated the role of CSD in the visual phenomenon of migraine aura, along with modern imaging techniques confirming its propagation across the occipital cortex. Animal studies are examined to indicate that CSD is not exclusive to migraines; it also occurs in other neurological conditions. At the cellular level, we review how CSD is characterized by ionic changes and excitotoxicity, leading to neuronal and glial responses. We explore how CSD activates the trigeminal nervous system and upregulates the expression of calcitonin gene-related peptides (CGRP), thereby contributing to migraine pain. Factors such as genetics, obesity, and environmental conditions that influence the CSD threshold are discussed, suggesting potential therapeutic targets. Current treatments for migraine, including prophylactic agents and CGRP-targeting drugs, are evaluated in the context of their expected effects on suppressing CSD activity. Additionally, we highlight emerging therapies such as intranasal insulin-like growth factor 1 and vagus nerve stimulation, which have shown promise in reducing CSD susceptibility and frequency. By elucidating the molecular and cellular mechanisms of CSD, this review aims to enhance the understanding of migraine pathogenesis and support the development of targeted therapeutic strategies.

Application of Artificial Intelligence in the Headache Field

PURPOSE OF REVIEW

Headache disorders are highly prevalent worldwide. Rapidly advancing capabilities in artificial intelligence (AI) have expanded headache-related research with the potential to solve unmet needs in the headache field. We provide an overview of AI in headache research in this article.

RECENT FINDINGS

We briefly introduce machine learning models and commonly used evaluation metrics. We then review studies that have utilized AI in the field to advance diagnostic accuracy and classification, predict treatment responses, gather insights from various data sources, and forecast migraine attacks. Furthermore, given the emergence of ChatGPT, a type of large language model (LLM), and the popularity it has gained, we also discuss how LLMs could be used to advance the field. Finally, we discuss the potential pitfalls, bias, and future directions of employing AI in headache medicine. Many recent studies on headache medicine incorporated machine learning, generative AI and LLMs. A comprehensive understanding of potential pitfalls and biases is crucial to using these novel techniques with minimum harm. When used appropriately, AI has the potential to revolutionize headache medicine.

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

PURPOSE OF REVIEW

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

RECENT FINDINGS

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

The Ethical Stewardship of Artificial Intelligence in Chronic Pain and Headache: A Narrative Review

PURPOSE OF REVIEW

As artificial intelligence (AI) and machine learning (ML) are becoming more pervasive in medicine, understanding their ethical considerations for chronic pain and headache management is crucial for optimizing their safety.

RECENT FINDINGS

We reviewed thirty-eight editorial and original research articles published between 2018 and 2023, focusing on the application of AI and ML to chronic pain or headache. The core medical principles of beneficence, non-maleficence, autonomy, and justice constituted the evaluation framework. The AI applications addressed topics such as pain intensity prediction, diagnostic aides, risk assessment for medication misuse, empowering patients to self-manage their conditions, and optimizing access to care. Virtually all AI applications aligned both positively and negatively with specific medical ethics principles. This review highlights the potential of AI to enhance patient outcomes and physicians' experiences in managing chronic pain and headache. We emphasize the importance of carefully considering the advantages, disadvantages, and unintended consequences of utilizing AI tools in chronic pain and headache, and propose the four core principles of medical ethics as an evaluation framework.

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.

Sex-related differences regarding headache triggered by low barometric pressure in Japan

PURPOSE

The prevalence of migraine headache is higher in women. Low barometric pressure is a factor in headache triggering, but sex-related differences have not been identified. The purpose of this study was to examine sex-related differences in headache triggered by low barometric pressure.

METHODS

Study subjects aged 20-49 years were randomly selected from a research company's (Macromill, Inc.) web panel. Those with chronic migraine or tension-type headache invited to complete a web-based self-administered questionnaire. Logistic regression analysis was performed with the objective variable as the Headache Impact Test-6 (HIT-6) high scores (56 or more) or headache triggered by low barometric pressure.

RESULTS

Participants were 332 women and 337 men in the headache population. HIT-6 high scores were associated with age at headache occurrence 20 years or younger (OR: odds ratio 1.85, 95% CI: confidence interval 1.15-2.99, p = 0.012) and headache triggered by low barometric pressure (OR 2.11, 95%CI 1.51-2.94, p < 0.001). Headache triggered by low barometric pressure was significantly associated with women (OR 2.92, 95%CI 2.12-4.02, p < 0.001).

CONCLUSIONS

Headache triggered by low barometric pressure were related to sex-related differences. It was suggested that a sex-specific treatment approach for headache triggering is needed.

Current status and future prospects of Chinese mobile apps for hypertension management

OBJECTIVE

This study aimed to evaluate the current situation of Chinese mobile apps for hypertension management and explore patients' real requirements for app use, providing a theoretical basis for the future improvement of hypertension apps.

METHODS

We reviewed hypertension management apps from mobile app platforms, and summarized their functional characteristics. In addition, we conducted an online survey among 1000 hypertensive patients, collected valid responses, and analyzed the feedback data.

RESULTS

Forty hypertension management apps were analyzed, with 72.5% offering no more than six functions, indicating limited coverage of advanced and comprehensive functionalities. Among the 934 valid survey responses, patients emphasized four main functions in apps for hypertension management: long-term dynamic blood pressure monitoring, scientific lifestyle management, strict medication management and systematic health knowledge delivering.

CONCLUSION

The existing hypertension management apps mainly serve as "Digital Health" tools with unclear clinical efficacy. The future development of these apps lies in how they transition to "Digital Therapeutics" solutions to better meet patients' needs and provide clear clinical advantages.

Whether Weather Matters with Migraine

PURPOSE OF REVIEW

Many patients with migraine report their attacks are triggered by various weather anomalies. Studies have shown mixed results regarding the association of migraine to weather changes. The purpose of the current review is to compile the most up-to-date research studies on how weather may affect migraine. In addition, we explore the association between weather and other inflammatory disease states as well as neurotransmitters.

RECENT FINDINGS

Migraine attacks can be related to weather variables such as barometric pressure, humidity, and wind. However, the results of recent studies are inconsistent; weathers' effect on migraine attacks is around 20%. However, very strong weather factors have a more significant effect on migraine attack variables. Many individuals identify weather as a migraine attack trigger, yet we see no causative relationship between weather and migraine patterns. The outcomes of studies indicate mixed results and reflect individual variation in how weather can impact migraine patterns. Similar relationships can be seen with other rheumatologic and pain conditions in general. Overall, the combination of weather plus other factors appears to be a more significant migraine trigger.

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.

Oxybutynin for Primary Palmer Hyperhidrosis Attenuates Migraine Attacks and Burdens

Migraine is a neurological disorder with recurrent headaches accompanied by burdens in social life. Primary palmar hyperhidrosis is a chronic condition with excessive sweating of the palms that can significantly impair quality of life. Primary hyperhidrosis can cause anxiety, and stress, including anxiety, is the most common inducer of migraine headaches. Recently, oxybutynin has been used for primary palmar hyperhidrosis. We herein describe a 26-year-old female migraine patient with primary palmar hyperhidrosis whose migraine attacks and burdens were attenuated after the prescription of an oxybutynin lotion formula. The patient's monthly headache days (MHD) and monthly acute medication intake days (AMD) at the first visit were 10 and 9. Headache Impact Score 6 (HIT-6) at the initial visit was 63. After the prescription of Japanese herbal kampo medicine Goreisan (TJ-17), Goshuyuto (TJ-31), and 200 mg of valproic acid, MHD, AMD, and HIT-6 decreased gradually. However, these parameters could not improve sufficiently at nine months: MHD 4, AMD 4, and HIT-6 52. We first prescribed a lotion formulation of 20% oxybutynin hydrochloride at nine months. After this, migraine was further attenuated, and stress related to primary palmar hyperhidrosis was reduced; at 12 months, the patient had achieved MHD 2, AMD 2, and HIT-6 48. She will continue receiving primary palmar hyperhidrosis treatment while tapering off migraine prophylaxis. While the exact mechanisms connecting migraine and primary hyperhidrosis remain uncertain, this case raises important questions about the potential interplay between stress, sweating, and migraine triggers.

Developing an artificial intelligence-based diagnostic model of headaches from a dataset of clinic patients' records

OBJECTIVE

We developed an artificial intelligence (AI)-based headache diagnosis model using a large questionnaire database from a headache-specializing clinic.

BACKGROUND

Misdiagnosis of headache disorders is a serious issue and AI-based headache diagnosis models are scarce.

METHODS

We developed an AI-based headache diagnosis model and conducted internal validation based on a retrospective investigation of 6058 patients (4240 training dataset for model development and 1818 test dataset for internal validation) diagnosed by a headache specialist. The ground truth was the diagnosis by the headache specialist. The diagnostic performance of the AI model was evaluated.

RESULTS

The dataset included 4829/6058 (79.7%) patients with migraine, 834/6058 (13.8%) with tension-type headache, 78/6058 (1.3%) with trigeminal autonomic cephalalgias, 38/6058 (0.6%) with other primary headache disorders, and 279/6058 (4.6%) with other headaches. The mean (standard deviation) age was 34.7 (14.5) years, and 3986/6058 (65.8%) were female. The model's micro-average accuracy, sensitivity (recall), specificity, precision, and F-values for the test dataset were 93.7%, 84.2%, 84.2%, 96.1%, and 84.2%, respectively. The diagnostic performance for migraine was high, with a sensitivity of 88.8% and c-statistics of 0.89 (95% confidence interval 0.87-0.91).

CONCLUSIONS

Our AI model demonstrated high diagnostic performance for migraine. If secondary headaches can be ruled out, the model can be a powerful tool for diagnosing migraine; however, further data collection and external validation are required to strengthen the performance, ensure the generalizability in other outpatients, and demonstrate its utility in real-world settings.

Developing an Artificial Intelligence-Based Pediatric and Adolescent Migraine Diagnostic Model

Introduction Misdiagnosis of pediatric and adolescent migraine is a significant problem. The first artificial intelligence (AI)-based pediatric migraine diagnosis model was made utilizing a database of questionnaires obtained from a previous epidemiological study, the Itoigawa Benizuwaigani Study. Methods The AI-based headache diagnosis model was created based on the internal validation based on a retrospective investigation of 909 patients (636 training dataset for model development and 273 test dataset for internal validation) aged six to 17 years diagnosed based on the International Classification of Headache Disorders 3rd edition. The diagnostic performance of the AI model was evaluated. Results The dataset included 234/909 (25.7%) pediatric or adolescent patients with migraine. The mean age was 11.3 (standard deviation 3.17) years. The model's accuracy, sensitivity (recall), specificity, precision, and F-values for the test dataset were 94.5%, 88.7%, 96.5%, 90.0%, and 89.4%, respectively. Conclusions The AI model exhibited high diagnostic performance for pediatric and adolescent migraine. It holds great potential as a powerful tool for diagnosing these conditions, especially when secondary headaches are ruled out. Nonetheless, further data collection and external validation are necessary to enhance the model's performance and ensure its applicability in real-world settings.

Migraine triggers in Asian countries: a narrative review

Background

Migraine is one of the most common neurological disorders worldwide. Clinical characteristics of migraine may be somewhat different across ethnic groups. Although factors such as stress, lack of sleep, and fasting are known as migraine triggers, the discussion about geographical differences of migraine triggers in Asia is lacking.

Methods

In this study, we performed a narrative review on migraine triggers in Asia. We searched PubMed for relevant papers published between January 2000 and February 2022.

Results

Forty-two papers from 13 Asian countries were included. Stress and sleep are the most frequently reported migraine triggers in Asia. There were some differences in migraine triggers in Asian countries: fatigue and weather common in Eastern Asia and fasting common in Western Asia.

Conclusion

Majority of the common triggers reported by patients with migraine in Asia were stress and sleep, similar to those reported globally, thus showing they are universally important. Some triggers linked to internal homeostasis are influenced by culture (e.g., alcohol, food/eating habit), and triggers related to environmental homeostasis, such as weather, are highly heterogenous between regions.