Preliminary External Validation Results of the Artificial Intelligence-Based Headache Diagnostic Model: A Multicenter Prospective Observational Study.

The misdiagnosis of headache disorders is a serious issue, and AI-based headache model diagnoses with external validation are scarce. We previously developed an artificial intelligence (AI)-based headache diagnosis model using a database of 4000 patients' questionnaires in a headache-specializing clinic and herein performed external validation prospectively. The validation cohort of 59 headache patients was prospectively collected from August 2023 to February 2024 at our or collaborating multicenter institutions. The ground truth was specialists' diagnoses based on the initial questionnaire and at least a one-month headache diary after the initial consultation. The diagnostic performance of the AI model was evaluated. The mean age was 42.55 ± 12.74 years, and 51/59 (86.67%) of the patients were female. No missing values were reported. Of the 59 patients, 56 (89.83%) had migraines or medication-overuse headaches, and 3 (5.08%) had tension-type headaches. No one had trigeminal autonomic cephalalgias or other headaches. The models' overall accuracy and kappa for the ground truth were 94.92% and 0.65 (95%CI 0.21-1.00), respectively. The sensitivity, specificity, precision, and F values for migraines were 98.21%, 66.67%, 98.21%, and 98.21%, respectively. There was disagreement between the AI diagnosis and the ground truth by headache specialists in two patients. This is the first external validation of the AI headache diagnosis model. Further data collection and external validation are required to strengthen and improve its performance in real-world settings.

Effectiveness of fremanezumab treatment in patients with migraine headache.

OBJECTIVE: To evaluate the efficacy and safety of fremanezumab for migraine prevention. DESIGN: Retrospective, single-center, real-world study. SETTING: Regional tertiary headache center in Japan. SUBJECTS: Adult individuals with migraine (n = 165, male = 17, female = 148; average age = 45.5 ± 16.0 years) who received fremanezumab between September 2021 and August 2022. METHODS: Fremanezumab was administered subcutaneously at a monthly dose of 225 mg or quarterly dose of 675 mg based on patient preferences. Patients received fremanezumab treatment for up to 1 year unless it was discontinued. Monthly data were collected on migraine days, headache days, and days requiring acute medication. RESULTS: Of the 165 patients, 125 (75.7%) received fremanezumab as their first anti-calcitonin gene-related peptide-related antibody drug. Significant reductions in monthly migraine days, headache days, and days requiring acute medication were observed in those with episodic and chronic migraines. The baseline monthly headache days was 8.1 ± 4.0 in the episodic migraine group, which reduced to 6.1 ± 4.8, 5.8 ± 4.4, 4.7 ± 3.6, and 4.6 ± 3.3 days at 1, 3, 6, and 12 months, respectively; in the chronic migraine group, the baseline monthly headache days was 20.9 ± 6.1, which reduced to 17.0 ± 8.9, 15.0 ± 9.2, 13.0 ± 7.7, and 12.0 ± 9.1 days at 1, 3, 6, and 12 months, respectively. Treatment benefits were enhanced after 6 months of administering fremanezumab in the chronic migraine group. CONCLUSIONS: In this real-world study of patients with migraine, fremanezumab appears to be effective and safe. Further studies are required to identify additional predictors of treatment success and failure with fremanezumab.

Development and Validation of a Japanese-Language Questionnaire to Screen for Tension-Type Headaches and Migraines.

Introduction Migraine and tension-type headache (TTH) are chronic diseases associated with significant socioeconomic losses and social and psychological impact (current global prevalence: 10% and 38%, respectively). Thus, they require accurate identification and classification. In clinical practice, validated screening tools able to quickly determine migraine and TTH with high sensitivity and specificity help provide an objective and multifaceted understanding of patients' headache symptoms. However, no tool has been developed or validated yet in Japan to ask multifaceted questions about headache-related symptoms in order to identify migraine and TTH and understand these symptoms. This study aimed to develop a questionnaire for screening TTH and migraine. Methods The study was conducted from March to June 2022 at a medical institution in Osaka, Japan. The questionnaire - comprising 24 questions that were generated based on the 3rd edition of the International Classification of Headache Disorders - was used to screen for migraine and TTH, aiming for a deeper understanding of related symptoms. The participants were patients aged ≥18 years with at least one of the following diagnoses: migraine, TTH. The participants were asked to respond in writing or online. The inclusion criteria were age ≥18 years; headache patients attending a hospital; and diagnoses of at least one of the following: migraine, TTH. The informativeness and discriminating ability of the screening items were evaluated using the item response theory. Items with a calculated discrimination ≥1.35 (high or very high) were retained for screening purposes. Basic questions required to screen for primary headaches were retained, despite their limited computational discrimination power. Ultimately, nine and eight screening items were finalized for migraine and TTH, respectively. The previous neurologists' clinical diagnosis of each patient was used as the gold standard reference for calculating sensitivity, specificity, and positive and negative predictive values regarding the screening items. Cohen's kappa coefficients with 95% CIs were also calculated to determine the agreement between the neurologists' clinical diagnosis and the questionnaire results. Results The study population comprised 69 patients aged 19-89 years who were assisted at a hospital division specializing in headache medicine and diagnosed by neurologists. Of these, 22 patients had migraine, 30 had TTH, and 17 had migraine/TTH. Comparing the neurologists' clinical diagnosis with our screening questionnaire results, the sensitivity and specificity were 72.7% and 86.7% for migraine and 50.0% and 86.4% for TTH, respectively. Conclusions Our brief screening tool was highly specific for diagnosing migraine and TTH in individuals with headache symptoms but lacked sufficient sensitivity, especially for TTH. The high specificity for migraine and TTH suggests that the screening tool we developed in this study can correctly identify those who do not have migraine and TTH. The sensitivity was also relatively high for migraine, suggesting that the tool can correctly identify migraine-positive individuals. However, the sensitivity for TTH was low. This tool could help clinicians in providing detailed course assessment of migraine symptoms and TTH symptoms; however, the issue of low sensitivity for TTH needs to be addressed.

Small vessel platelet thrombosis in the peripheral nerves in POEMS syndrome.

INTRODUCTION/AIMS: Vascular thrombosis is prevalent among patients with polyneuropathy, organomegaly, endocrinopathy M-protein, and skin changes (POEMS) syndrome. The endothelial cells in the endoneurium are often hypertrophied and the lumen is frequently occluded. Consequent local hypoxia may increase vascular endothelial growth factor (VEGF), which induces hypercoagulation and vascular permeability. METHODS: This study presents two patients in the fifth decade of life, who had rare nerve biopsy findings of vascular occlusion mainly by platelets. Before the cases presented here, we encountered nine confirmed POEMS patients whose nerve biopsies did not show similar findings. RESULTS: A small artery and a vein were occluded, but no atherosclerotic changes were observed. The endothelial cells that adhered to the packed platelets lost their junctions. DISCUSSION: Platelet aggregation, degranulation, and ischemia may cause a loose endothelial barrier and leak proinflammatory cytokines, such as interleukin-12. This may increase production of VEGF and may cause nerve demyelination. Small vessel platelet thrombosis may contribute to the pathogenesis of this disorder.

Developing an artificial intelligence-based headache diagnostic model and its utility for non-specialists' diagnostic accuracy.

BACKGROUND: Misdiagnoses of headache disorders are a serious issue. Therefore, we developed an artificial intelligence-based headache diagnosis model using a large questionnaire database in a specialized headache hospital. METHODS: Phase 1: We developed an artificial intelligence model based on a retrospective investigation of 4000 patients (2800 training and 1200 test dataset) diagnosed by headache specialists. Phase 2: The model's efficacy and accuracy were validated. Five non-headache specialists first diagnosed headaches in 50 patients, who were then re-diagnosed using AI. The ground truth was the diagnosis by headache specialists. The diagnostic performance and concordance rates between headache specialists and non-specialists with or without artificial intelligence were evaluated. RESULTS: Phase 1: The model's macro-average accuracy, sensitivity (recall), specificity, precision, and F values were 76.25%, 56.26%, 92.16%, 61.24%, and 56.88%, respectively, for the test dataset. Phase 2: Five non-specialists diagnosed headaches without artificial intelligence with 46% overall accuracy and 0.212 kappa for the ground truth. The statistically improved values with artificial intelligence were 83.20% and 0.678, respectively. Other diagnostic indexes were also improved. CONCLUSIONS: Artificial intelligence improved the non-specialist diagnostic performance. Given the model's limitations based on the data from a single center and the low diagnostic accuracy for secondary headaches, further data collection and validation are needed.

[Acemetacin, a Prodrug of Indomethacin, Is Effective for Treatment of Hemicrania Continua: A Japanese Case Report].

A 21-year-old woman reported continuous moderately severe headache in the right frontotemporal region, accompanied by exacerbations with cranial autonomic symptoms and restlessness. The exacerbations appeared several times a week over one to several hours. The patient was diagnosed with hemicrania continua (HC) according to the 3rd edition of the International Classification of Headache Disorders. Because production of the oral indomethacin was discontinued in April 2020, acemetacin, a prodrug of indomethacin, was administered (90 mg/day) and gradually increased to 180 mg/day over 2 months. No recurrence of HC developed. No reports of HC treated with acemetacin have been previously reported in Japan. We suggest that randomized control trials should be performed.

A Combination of Indomethacin Farnesyl and Amitriptyline Is Effective for Continuous Interictal Pain with Probable Chronic Paroxysmal Hemicrania.

A 26-year-old woman with a history of migraine reported right-sided, severe stabbing orbital pain with cranial autonomic symptoms (CASs) for approximately 2 years. The attack duration was approximately 30 minutes, with a frequency of twice per day. Taking loxoprofen was ineffective. Six months earlier, moderate pressing continuous interictal pain without CASs had developed. Indomethacin farnesyl completely resolved the attacks but had no effect on the interictal pain. The patient was diagnosed with probable chronic paroxysmal hemicrania in accordance with the International Classification of Headache Disorders (ICHD-3) (third version). Continuous interictal pain gradually disappeared with a combination of indomethacin farnesyl and amitriptyline.

Adult-onset Repeat Rhabdomyolysis with a Very Long-chain Acyl-CoA Dehydrogenase Deficiency Due to Compound Heterozygous ACADVL Mutations.

Very long-chain acyl-CoA dehydrogenase (VLCAD) deficiency is a genetic disorder of fatty acid beta oxidation that is caused by a defect in ACADVL, which encodes VLCAD. The clinical presentation of VLCAD deficiency is heterogeneous, and either a delayed diagnosis or a misdiagnosis may sometimes occur. We herein describe a difficult-to-diagnose case of the muscle form of adult-onset VLCAD deficiency with compound heterozygous ACADVL mutations including c.790A>G (p.K264E) and c.1246G>A (p.A416T).

[Effective Microvascular Decompression of the Trigeminal Nerve in a Patient with SUNCT].

A 43-year-old man presented with severe, saw-tooth pattern pain around the right eye that started with conjunctival injection, lacrimation and nasal discharge, lasting for about 1 hour, 4 months after the initial onset of lancinating pain in the same area. The patient was diagnosed with SUNCT (short-lasting unilateral neuralgiform headache attacks with conjunctival injection and tearing) according to the International Classification of Headache Disorders 3rd edition (beta version). The symptoms improved in 2 months but recurred 6 months later. He developed a toxic eruption after receiving a variety of antiepileptic agents including lamotrigine, which suggested refractory SUNCT. Head magnetic resonance imaging (MRI) showed neurovascular compression (NVC) involving the right trigeminal nerve. Microvascular decompression (MVD) was performed, and the pain was relieved postoperatively. MVD should be considered when treating refractory SUNCT because NVC may be involved in some cases. (Received February 29, 2016; Accepted April 4, 2016; Published August 1, 2016).

[Successful treatment of hemicrania continua with a combination of low-dose indomethacin and pregabalin: a case report].

A 51-year-old man complained of continuous pain lasting about 3 weeks around his forehead and left orbit-locations where pain may indicate conjunctival injection and lacrimation. Upon arrival to our hospital, his neurological examination was normal, and brain MRI showed no abnormality. The headache disappeared with indomethacin treatment (75 mg/day), and a diagnosis of hemicrania continua (HC) was established according to the International Classification of Headache Disorders, 2nd Edition. The headache returned after reducing the dose of indomethacin. After adding pregabalin (150 mg/day) to his treatment regimen, we could reduce the dose of indomethacin from 75 mg/day to 25 mg/day, which the patient tolerated well. Although HC is one of the indomethacin-responsive headaches, continuous administration can cause side effects including gastrointestinal disorders. Such side effects can decrease the tolerability of indomethacin, and may eventually lead to its reduction or discontinuation. Pregabalin can be an alternative to indomethacin for treating HC.