Chiang, Chia-Chun

Abstract Objective To develop machine learning models using patient and migraine features that can predict treatment responses to commonly used migraine preventive medications. Background Currently, there is no accurate way to predict response to migraine preventive medications, and the standard trial‐and‐error approach is inefficient. Methods In this cohort study, we analyzed data from the Mayo Clinic Headache database prospectively collected from 2001 to December 2023. Adult patients with migraine completed questionnaires during their initial headache consultation to record detailed clinical features and then at each follow‐up to track preventive medication changes and monthly headache days. We included patients treated with at least one of the following migraine preventive medications: topiramate, beta‐blockers (propranolol, metoprolol, atenolol, nadolol, timolol), tricyclic antidepressants (amitriptyline, nortriptyline), verapamil, gabapentin, onabotulinumtoxinA, and calcitonin gene‐related peptide (CGRP) monoclonal antibodies (mAbs) (erenumab, fremanezumab, galcanezumab, eptinezumab). We pre‐trained a deep neural network, “TabNet,” using 145 variables, then employed TabNet‐embedded data to construct prediction models for each medication to predict binary outcomes (responder vs. non‐responder). A treatment responder was defined as having at least a 30% reduction in monthly headache days from baseline. All model performances were evaluated, and metrics were reported in the held‐out test set (train 85%, test 15%). SHapley Additive exPlanations (SHAP) were conducted to determine variable importance. Results Our final analysis included 4260 patients. The responder rate for each medication ranged from 28.7% to 34.9%, and the mean time to treatment outcome for each medication ranged from 151.3 to 209.5 days. The CGRP mAb prediction model achieved a high area under the receiver operating characteristics curve (AUC) of 0.825 (95% confidence interval [CI] 0.726, 0.920) and an accuracy of 0.80 (95% CI 0.70, 0.88). The AUCs of prediction models for beta‐blockers, tricyclic antidepressants, topiramate, verapamil, gabapentin, and onabotulinumtoxinA were: 0.664 (95% CI 0.579, 0.745), 0.611 (95% CI 0.562, 0.682), 0.605 (95% CI 0.520, 0.688), 0.673 (95% CI 0.569, 0.724), 0.628 (0.533, 0.661), and 0.581 (95% CI 0.550, 0.632), respectively. Baseline monthly headache days, age, body mass index (BMI), duration of migraine attacks, responses to previous medication trials, cranial autonomic symptoms, family history of headache, and migraine attack triggers were among the most important variables across all models. A variable could have different contributions; for example, lower BMI predicts responsiveness to CGRP mAbs and beta‐blockers, while higher BMI predicts responsiveness to onabotulinumtoxinA, topiramate, and gabapentin. Conclusion We developed an accurate prediction model for CGRP mAbs treatment response, leveraging detailed migraine features gathered from a headache questionnaire before starting treatment. Employing the same methods, the model performances for other medications were less impressive, though similar to the machine learning models reported in the literature for other diseases. This may be due to CGRP mAbs being migraine‐specific. Incorporating medical comorbidities, genomic, and imaging factors might enhance the model performance. We demonstrated that migraine characteristics are important in predicting treatment responses and identified the most crucial predictors for each of the seven types of preventive medications. Our results suggest that precision migraine treatment is feasible.

Abstract Objective To develop a natural language processing (NLP) algorithm that can accurately extract headache frequency from free‐text clinical notes. Background Headache frequency, defined as the number of days with any headache in a month (or 4 weeks), remains a key parameter in the evaluation of treatment response to migraine preventive medications. However, due to the variations and inconsistencies in documentation by clinicians, significant challenges exist to accurately extract headache frequency from the electronic health record (EHR) by traditional NLP algorithms. Methods This was a retrospective cross‐sectional study with patients identified from two tertiary headache referral centers, Mayo Clinic Arizona and Mayo Clinic Rochester. All neurology consultation notes written by 15 specialized clinicians (11 headache specialists and 4 nurse practitioners) between 2012 and 2022 were extracted and 1915 notes were used for model fine‐tuning (90%) and testing (10%). We employed four different NLP frameworks: (1) ClinicalBERT (Bidirectional Encoder Representations from Transformers) regression model, (2) Generative Pre‐Trained Transformer‐2 (GPT‐2) Question Answering (QA) model zero‐shot, (3) GPT‐2 QA model few‐shot training fine‐tuned on clinical notes, and (4) GPT‐2 generative model few‐shot training fine‐tuned on clinical notes to generate the answer by considering the context of included text. Results The mean (standard deviation) headache frequency of our training and testing datasets were 13.4 (10.9) and 14.4 (11.2), respectively. The GPT‐2 generative model was the best‐performing model with an accuracy of 0.92 (0.91, 0.93, 95% confidence interval [CI]) and R 2 score of 0.89 (0.87, 0.90, 95% CI), and all GPT‐2–based models outperformed the ClinicalBERT model in terms of exact matching accuracy. Although the ClinicalBERT regression model had the lowest accuracy of 0.27 (0.26, 0.28), it demonstrated a high R 2 score of 0.88 (0.85, 0.89), suggesting the ClinicalBERT model can reasonably predict the headache frequency within a range of ≤ ± 3 days, and the R 2 score was higher than the GPT‐2 QA zero‐shot model or GPT‐2 QA model few‐shot training fine‐tuned model. Conclusion We developed a robust information extraction model based on a state‐of‐the‐art large language model, a GPT‐2 generative model that can extract headache frequency from EHR free‐text clinical notes with high accuracy and R 2 score. It overcame several challenges related to different ways clinicians document headache frequency that were not easily achieved by traditional NLP models. We also showed that GPT‐2–based frameworks outperformed ClinicalBERT in terms of accuracy in extracting headache frequency from clinical notes. To facilitate research in the field, we released the GPT‐2 generative model and inference code with open‐source license of community use in GitHub. Additional fine‐tuning of the algorithm might be required when applied to different health‐care systems for various clinical use cases.

Abstract Objectives/Background Treatment of migraine in the setting of either renal or hepatic disease can be daunting for clinicians. Not only does the method of metabolism have to be considered, but also the method of elimination/excretion of the parent drug and any active or toxic metabolites. Furthermore, it is difficult to think about liver or kidney disease in isolation, as liver disease can sometimes contribute to impaired renal function and renal disease can sometimes impair hepatic metabolism, through the cytochrome P450 system. Methods A detailed search for terms related to liver disease, renal disease, and migraine management was performed in PubMed, Ovid Medline, Embase, and the Cochrane Library.For each medication, product labels were retrieved and reviewed using the US FDA website, with additional review of IBM Micromedex, LiverTox, and the Renal Drug Handbook. Results This manuscript provides an overview of migraine drug metabolism and how it can be affected by liver and renal impairment. It reviews the standard terminology recommended by the US Food and Drug Administration for the different stages of hepatic and renal failure. The available evidence regarding the use of abortive and preventative medicines in the setting of organ failure is discussed in detail, including more recent therapies such as lasmiditan, gepants, and calcitonin gene‐related peptide antibodies. Conclusions For acute therapy, the use of NSAIDS should be limited, as these carry risk for both severe hepatic and renal disease. Triptans can be selectively used, often with dose guideline adjustments. Ubrogepant may be used in severe hepatic disease with dose adjustment and lasmiditan can be used in end stage renal disease. Though non‐medicine strategies may be the most reasonable initial approach, many preventative medications can be used in the setting of hepatic and renal disease, often with dose adjustment. This review provides tables of guidelines, including reduced dosing recommendations, for the use of abortive and preventative migraine medications in hepatic and renal failure.

Abstract Objective To provide an overview of the current available literature on peripheral nerve blocks for the management of migraine and other headache disorders in adults. Background Peripheral nerve blocks have been commonly performed in the headache practice for migraine, cluster headache, occipital neuralgia, and other headache disorders, despite a paucity of evidence supporting their use historically. In the past decade, there has been an effort to explore the efficacy and safety of peripheral nerve blocks for the management of headache, with the greatest interest centered around greater occipital blocks. Design We performed a search in PubMed using key words including “occipital nerve blocks,” “peripheral nerve blocks,” “occipital nerve,” “migraine,” “cluster headache,” and “neuralgia.” We reviewed the randomized controlled trials (RCTs), observational studies, and case series, and summarized the anatomy, techniques, and the evidence for the use of peripheral nerve blocks in different headache disorders, with particular focus on available RCTs. Case reports were included for a detail review of adverse events. Results Of 12 RCTs examining the use of greater occipital nerve blocks for migraine, all but one demonstrate efficacy with reduction in headache frequency, intensity, and/or duration compared to placebo. Studies have not demonstrated a difference in clinical outcomes with the use of corticosteroids for nerve blocks compared to blocks with local anesthetic in the treatment of migraine. There are two RCTs supporting the use of greater occipital blockade for cluster headache, both showing benefit of suboccipitally injected corticosteroid. One RCT suggests benefit of greater occipital nerve blocks for cervicogenic headache. Observational studies and case series/reports show that greater occipital nerve block may be effective in prolonged migraine aura, status migrainosus, post‐dural puncture headache, and occipital neuralgia. Overall, peripheral nerve blocks are well tolerated. Serious side effects are rare but have been reported, including acute cerebellar syndrome and infection. Conclusions Peripheral nerve blocks, especially occipital nerve blocks, are a viable treatment option for migraine and may be helpful in cluster headache as a transitional therapy or rescue therapy. Additional prospective studies are needed to investigate the efficacy and safety of occipital nerve blocks for long‐term migraine prevention, as well as for other headache disorders, such as occipital neuralgia.

Abstract Objective To compare the artificial intelligence‐enabled electrocardiogram (AI‐ECG) atrial fibrillation (AF) prediction model output in patients with migraine with aura (MwA) and migraine without aura (MwoA). Background MwA is associated with an approximately twofold risk of ischemic stroke. Longitudinal cohort studies showed that patients with MwA have a higher incidence of developing AF compared to those with MwoA. The Mayo Clinic Cardiology team developed an AI‐ECG algorithm that calculates the probability of concurrent paroxysmal or impending AF in ECGs with normal sinus rhythm (NSR). Methods Adult patients with an MwA or MwoA diagnosis and at least one NSR ECG within the past 20 years at Mayo Clinic were identified. Patients with an ECG‐confirmed diagnosis of AF were excluded. For each patient, the ECG with the highest AF prediction model output was used as the index ECG. Comparisons between MwA and MwoA were conducted in the overall group (including men and women of all ages), women only, and men only in each age range (18 to <35, 35 to <55, 55 to <75, ≥75 years), and adjusted for age, sex, and six common vascular comorbidities that increase risk for AF. Results The final analysis of our cross‐sectional study included 40,002 patients (17,840 with MwA, 22,162 with MwoA). The mean (SD) age at the index ECG was 48.2 (16.0) years for MwA and 45.9 (15.0) years for MwoA ( p < 0.001). The AF prediction model output was significantly higher in the MwA group compared to MwoA (mean [SD] 7.3% [15.0%] vs. 5.6% [12.4%], mean difference [95% CI] 1.7% [1.5%, 2.0%], p < 0.001). After adjusting for vascular comorbidities, the difference between MwA and MwoA remained significant in the overall group (least square means of difference [95% CI] 0.7% [0.4%, 0.9%], p < 0.001), 18 to <35 (0.4% [0.1%, 0.7%], p = 0.022), and 35 to <55 (0.5% [0.2%, 0.8%], p < 0.001), women of all ages (0.6% [0.3%, 0.8%], p < 0.001), men of all ages (1.0% [0.4%, 1.6%], p = 0.002), women 35 to <55 (0.6% [0.3%, 0.9%], p < 0.001), and men 18 to <35 (1.2% [0.3%, 2.1%], p = 0.008). Conclusions Utilizing a novel AI‐ECG algorithm on a large group of patients, we demonstrated that patients with MwA have a significantly higher AF prediction model output, implying a higher probability of concurrent paroxysmal or impending AF, compared to MwoA in both women and men. Our results suggest that MwA is an independent risk factor for AF, especially in patients <55 years old, and that AF‐mediated cardioembolism may play a role in the migraine–stroke association for some patients.

Background: Patients with cerebral or spinal cavernous malformations (CM) and a primary headache disorder are often limited in medication options due to concern for bleeding risk. Methods: From a prospective cohort of CM patients (2015–2020), demographics, mode of clinical presentation, and radiographic data were collected. Follow up of patients was performed with electronic medical record review, in person visits and/or written surveys. Select medication use was ascertained from the time of the CM diagnosis to a censor date of first prospective symptomatic hemorrhage, complete surgical excision of sporadic form CM, or death. The influence of non-aspirin NSAID (NA-NSAID), triptan, or OnabotulinumtoxinA on prospective hemorrhage risk was assessed. Results: As of August 20, 2020, 329 patients with spinal or cerebral CM (58% female; 20.1% familial; 42.2% initial presentation due to hemorrhage; 27.4% brainstem) were included. During a follow-up of 1799.9 patient years, 92 prospective hemorrhages occurred. Use of NA-NSAIDs, triptans, and OnabotulinumtoxinA after the diagnosis of CM was unassociated with an increased risk of prospective hemorrhage. Conclusions: Use of triptans and NA-NSAIDs, does not precipitate CM hemorrhage. Similarly, we did not find that OnabotulinumtoxinA precipitated CM hemorrhage in a limited number of patients at doses <200 units per session.