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.

Open label experience of repeated OnabotulinumtoxinA injections towards the sphenopalatine ganglion in patients with chronic cluster headache and chronic migraine.

BACKGROUND: A novel technique for injection of OnabotulinumtoxinA (BTA) towards the sphenopalatine ganglion (SPG) has shown promise in refractory chronic migraine (CM) and chronic cluster headache (CCH). Open label safety and efficacy data are presented here. METHODS: Patients with refractory CM or CCH who had received at least one injection and completed headache diaries were included. Efficacy was defined as ≥50% reduction in moderate-to-severe headache days for CM, or ≥50% reduction in attack frequency for CCH, at weeks five to eight. RESULTS: Over 261 injections, there were 123 adverse events (AE), of which one was serious. Most (93%) AEs were mild and all were transient. The 50% response to one injection was 81% for CM and 69% for CCH. The response gradually reduced over subsequent months for CM but stayed between 55% and 67% for CCH. Repeated injections were beneficial. CONCLUSIONS: Injections resulted in improvement for both groups and was maintained with repeated injections. Repeat injection after three months may be beneficial in CM. Adverse events were not uncommon, but universally transient, presumably as a result of the mechanism of action of BTA. Repeated BTA injection towards the SPG could be an effective treatment for refractory CM and CCH. Larger, randomised, placebo-controlled trials are required.

Patterns of migraine medication use in Norway: A nationwide registry-based observational study.

OBJECTIVE: The objective of this study was to describe and discuss patterns of migraine medication use in the entire Norwegian population. METHODS: In this nationwide, observational study, all individuals with a migraine-related prescription between 2010 and 2020 were identified using the Norwegian Prescription Database. The outcomes of interest were the incidence and 1-year prevalence of migraine medication users, as well as individuals with triptan overuse. Patterns of medication use were statistically compared between women and men adjusted for age, year of treatment start, comorbidities and county of residence calculating adjusted odds ratios (aOR) with 95% confidence intervals (CI). RESULTS: We identified 327,904 migraine medication users. The incidence ranged from 0.39% to 0.46%, and the 1-year prevalence increased from 1.99% to 2.99%. Preventive use increased >50% during the study period. Preventives were significantly more often prescribed to women than to men (39.72% vs. 33.75%; aOR 1.41, 95% CI 1.38 to 1.44). Triptan overuse was significantly more common among women, but women with overuse were more often using preventives, as compared to men (56.64% vs 52.69%; aOR = 1.43, 95% CI 1.37 to 1.49). CONCLUSION: The prevalence of medically treated migraine is low. Overuse of triptans is frequent, especially among women. Clinicians should be encouraged to try out different triptans, recognize triptan overuse, and prescribe preventives when indicated.

What predicts citation counts and translational impact in headache research? A machine learning analysis.

BACKGROUND: We aimed to develop the first machine learning models to predict citation counts and the translational impact, defined as inclusion in guidelines or policy documents, of headache research, and assess which factors are most predictive. METHODS: Bibliometric data and the titles, abstracts, and keywords from 8600 publications in three headache-oriented journals from their inception to 31 December 2017 were used. A series of machine learning models were implemented to predict three classes of 5-year citation count intervals (0-5, 6-14 and, >14 citations); and the translational impact of a publication. Models were evaluated out-of-sample with area under the receiver operating characteristics curve (AUC). RESULTS: The top performing gradient boosting model predicted correct citation count class with an out-of-sample AUC of 0.81. Bibliometric data such as page count, number of references, first and last author citation counts and h-index were among the most important predictors. Prediction of translational impact worked optimally when including both bibliometric data and information from the title, abstract and keywords, reaching an out-of-sample AUC of 0.71 for the top performing random forest model. CONCLUSION: Citation counts are best predicted by bibliometric data, while models incorporating both bibliometric data and publication content identifies the translational impact of headache research.

Migraine and risk of atrial fibrillation: A 9-year follow-up based on the Trøndelag Health Study.

BACKGROUND: Data from some population-based studies have indicated an increased risk of atrial fibrillation (AF) among patients with migraine, particularly among individuals with migraine with aura. The present study aimed to assess the association between primary headache disorders and AF. METHODS: In a population-based 9-year follow-up design, we evaluated the questionnaire-based headache diagnosis, migraine and tension-type headache (TTH) included, collected in the Trøndelag Health Study (HUNT3) conducted in 2006-2008, and the subsequent risk of AF in the period until December 2015. The population at risk consisted of 39,340 individuals ≥20 years without AF at HUNT3 baseline who answered headache questionnaire during HUNT3. The prospective association was evaluated by multivariable Cox proportional hazard models with 95% confidence intervals (CIs). RESULTS: Among the 39,340 participants, 1524 (3.8%) developed AF during the 9-year follow up, whereof 91% of these were ≥55 years. In the multivariable analyses, adjusting for known confounders, we did not find any association between migraine or TTH and risk of AF. The adjusted hazard ratios (HRs) were respectively 0.84 (95% CI = 0.64-1.11) for migraine, 1.16 (95% CI = 0.86-1.27) for TTH and 1.04 (95% CI = 0.86-1.27) for unclassified headache. However, in sensitivity analyses of individuals aged ≥55 years, a lower risk of AF was found for migraine (HR = 0.53; 95% CI = 0.39-0.73). CONCLUSIONS: In this large population-based study, no increased risk of AF was found among individuals with migraine or TTH at baseline. Indeed, among individuals aged ≥55 years, migraine was associated with a lower risk for AF.

Frequency and predictors of headache in the first 12 months after traumatic brain injury: results from CENTER-TBI.

BACKGROUND: Headache is a prevalent and debilitating symptom following traumatic brain injury (TBI). Large-scale, prospective cohort studies are needed to establish long-term headache prevalence and associated factors after TBI. This study aimed to assess the frequency and severity of headache after TBI and determine whether sociodemographic factors, injury severity characteristics, and pre- and post-injury comorbidities predicted changes in headache frequency and severity during the first 12 months after injury. METHODS: A large patient sample from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) prospective observational cohort study was used. Patients were stratified based on their clinical care pathway: admitted to an emergency room (ER), a ward (ADM) or an intensive care unit (ICU) in the acute phase. Headache was assessed using a single item from the Rivermead Post-Concussion Symptoms Questionnaire measured at baseline, 3, 6 and 12 months after injury. Mixed-effect logistic regression analyses were applied to investigate changes in headache frequency and associated predictors. RESULTS: A total of 2,291 patients responded to the headache item at baseline. At study enrolment, 59.3% of patients reported acute headache, with similar frequencies across all strata. Female patients and those aged up to 40 years reported a higher frequency of headache at baseline compared to males and older adults. The frequency of severe headache was highest in patients admitted to the ICU. The frequency of headache in the ER stratum decreased substantially from baseline to 3 months and remained from 3 to 6 months. Similar trajectory trends were observed in the ICU and ADM strata across 12 months. Younger age, more severe TBI, fatigue, neck pain and vision problems were among the predictors of more severe headache over time. More than 25% of patients experienced headache at 12 months after injury. CONCLUSIONS: Headache is a common symptom after TBI, especially in female and younger patients. It typically decreases in the first 3 months before stabilising. However, more than a quarter of patients still experienced headache at 12 months after injury. Translational research is needed to advance the clinical decision-making process and improve targeted medical treatment for headache. TRIAL REGISTRATION: ClinicalTrials.gov NCT02210221.

Preventive treatment of migraine: Non-specific oral agents.

Migraine headache is highly prevalent and the most common neurologic disorder, affecting one billion people worldwide. It is also the most disabling condition in people under 50, with a huge impact on working ability, family, and social life. Access to effective preventive medication is important and may be considered if the patient has 6 or more migraine days per month, ineffective abortive agents, or disability on 2 or more days per month. Propranolol, metoprolol, candesartan, topiramate, divalproex, lisinopril, amitriptyline, and venlafaxine have the strongest evidence to support for use. Flunarizine and pizotifen may also be effective. Selection of preventive treatments is based on individual characteristics, comorbid conditions, efficacy, contraindications, side effects, cost, compliance, and drug. An adequate trial of migraine prophylaxis is usually 2 months at the target dose, and it is always important to re-evaluate indication for prophylactic use after a period of time.

Visual migraine aura iconography: A multicentre, cross-sectional study of individuals with migraine with aura.

INTRODUCTION: Visual disturbances are the most common symptoms of migraine aura. These symptoms can be described systematically by subdividing them into elementary visual symptoms. Since visual symptoms of migraine aura are not easy to describe verbally, we developed a collection of images illustrating previously reported elementary visual symptoms. OBJECTIVES: To test a standardised visual migraine aura iconography in a large population of migraine with aura patients and to improve it based on the participants' feedback. METHODS: We created a set of images representing 25 elementary visual symptoms and a web-based survey where participants could report whether they recognised these images as part of their visual aura. Elementary visual symptoms could also be recognised via a corresponding text description or described in a free text by participants. Individuals with migraine aura recruited from four tertiary headache centres (in Switzerland, Denmark, Norway and Italy) were invited to complete the survey. RESULTS: Two hundred and fifteen participants completed the study (78.9% women, median age 36). They recognised a total of 1645 elementary visual symptoms from our predefined list. Of those, 1291 (78.4%) where recognised via standardised iconography images. A new type of elementary visual symptom was reported by one participant. CONCLUSION: Most elementary visual symptoms experienced by participants were recognised via the standardised iconography. This tool can be useful for clinical as well as research purposes.

Transient ischemic attack or migraine with aura? / Transitorisk iskemisk attakk eller migreneaura?

Migraine or migraine-like symptoms can contribute to a delayed stroke diagnosis. However, migraine with aura is a common stroke mimic and often the basis for acute thrombolytic therapy. It is probably also the reason why many patients are misdiagnosed with a transient ischemic attack. In this clinical review, we explain the factors that could differentiate a transient ischemic attack from a migraine with aura.

Current treatment options for cluster headache: limitations and the unmet need for better and specific treatments-a consensus article.

AIM: Treatment for cluster headache is currently based on a trial-and-error approach. The available preventive treatment is unspecific and based on few and small studies not adhering to modern standards. Therefore, the authors collaborated to discuss acute and preventive treatment in cluster headache, addressing the unmet need of safe and tolerable preventive medication from the perspectives of people with cluster headache and society, headache specialist and cardiologist. FINDINGS: The impact of cluster headache on personal life is substantial. Mean annual direct and indirect costs of cluster headache are more than 11,000 Euros per patient. For acute treatment, the main problems are treatment response, availability, costs and, for triptans, contraindications and the maximum use allowed. Intermediate treatment with steroids and greater occipital nerve blocks are effective but cannot be used continuously. Preventive treatment is sparsely studied and overall limited by relatively low efficacy and side effects. Neurostimulation is a relevant option for treatment-refractory chronic patients. From a cardiologist's perspective use of verapamil and triptans may be worrisome and regular follow-up is essential when using verapamil and lithium. CONCLUSION: We find that there is a great and unmet need to pursue novel and targeted preventive modalities to suppress the horrific pain attacks for people with cluster headache.

Phenotype of new daily persistent headache: subtypes and comparison to transformed chronic daily headache.

BACKGROUND: It is unknown whether new daily persistent headache (NDPH) is a single disorder or heterogenous group of disorders, and whether it is a unique disorder from chronic migraine and chronic tension-type headache. We describe a large group of patients with primary NDPH, compare its phenotype to transformed chronic daily headache (T-CDH), and use cluster analysis to reveal potential sub-phenotypes in the NDPH group. METHODS: We performed a case-control study using prospectively collected clinical data in patients with primary NDPH and T-CDH (encompassing chronic migraine and chronic tension-type headache). We used logistic regression with propensity score matching to compare demographics, phenotype, comorbidities, and treatment responses between NDPH and T-CDH. We used K-means cluster analysis with Gower distance to identify sub-clusters in the NDPH group based on a combination of demographics, phenotype, and comorbidities. RESULTS: We identified 366 patients with NDPH and 696 with T-CDH who met inclusion criteria. Patients with NDPH were less likely to be female (62.6% vs. 73.3%, p < 0.001). Nausea, vomiting, photophobia, phonophobia, motion sensitivity, vertigo, and cranial autonomic symptoms were all significantly less frequent in NDPH than T-CDH (p value for all < 0.001). Acute treatments appeared less effective in NDPH than T-CDH, and medication overuse was less common (16% vs. 42%, p < 0.001). Response to most classes of oral preventive treatments was poor in both groups. The most effective treatment in NDPH was doselupin in 45.7% patients (95% CI 34.8-56.5%). Cluster analysis identified three subgroups of NDPH. Cluster 1 was older, had a high proportion of male patients, and less severe headaches. Cluster 2 was predominantly female, had severe headaches, and few associated symptoms. Cluster 3 was predominantly female with a high prevalence of migrainous symptoms and headache triggers. CONCLUSIONS: Whilst there is overlap in the phenotype of NDPH and T-CDH, the differences in migrainous, cranial autonomic symptoms, and vulnerability to medication overuse suggest that they are not the same disorder. NDPH may be fractionated into three sub-phenotypes, which require further investigation.

Onabotulinum toxin A block of the sphenopalatine ganglion in patients with persistent idiopathic facial pain: a randomized, triple-blind, placebo-controlled, exploratory, cross-over study.

OBJECTIVE: To investigate the efficacy and safety of injecting onabotulinum toxin A (BTA) towards the sphenopalatine ganglion (SPG) using the MultiGuide® in patients with persistent idiopathic facial pain (PIFP). METHODS: This cross-over, exploratory study compared the injection of 25 units BTA versus placebo in patients who met modified ICDH-3 criteria for PIFP. Daily pain diaries were registered for a 4-week baseline, a 12-week follow-up after each injection, and an 8-week conceptual washout period in between. The primary efficacy endpoint was the change from baseline to weeks 5-8 in average pain intensity using a numeric rating scale. Adverse events were recorded. RESULTS: Of 30 patients who were randomized to treatment, 29 were evaluable. In weeks 5-8, there was no statistically significant difference in average pain intensity between BTA versus placebo (0.00; 95% CI = -0.57 to 0.57) (P = 0.996). Following both BTA and placebo injections, five participants reported at least a 30% reduction in average pain during weeks 5-8 (P = 1.000). No serious adverse events were reported. Post-hoc analyses indicated a possible carry-over effect. CONCLUSIONS: Injection of BTA toward the SPG with the MultiGuide® did not appear to provide a reduction in pain reduction at 5-8 weeks, although this finding may be influenced by a carry-over effect. The injection appears to otherwise be safe and well-tolerated in patients with PIFP.Trial Registration: The study protocol is registered in ClinicalTrial.gov (NCT03462290) and EUDRACT (number: 2017-002518-30).

Forecasting migraine with machine learning based on mobile phone diary and wearable data.

INTRODUCTION: Triggers, premonitory symptoms and physiological changes occur in the preictal migraine phase and may be used in models for forecasting attacks. Machine learning is a promising option for such predictive analytics. The objective of this study was to explore the utility of machine learning to forecast migraine attacks based on preictal headache diary entries and simple physiological measurements. METHODS: In a prospective development and usability study 18 patients with migraine completed 388 headache diary entries and self-administered app-based biofeedback sessions wirelessly measuring heart rate, peripheral skin temperature and muscle tension. Several standard machine learning architectures were constructed to forecast headache the subsequent day. Models were scored with area under the receiver operating characteristics curve. RESULTS: Two-hundred-and-ninety-five days were included in the predictive modelling. The top performing model, based on random forest classification, achieved an area under the receiver operating characteristics curve of 0.62 in a hold-out partition of the dataset. DISCUSSION: In this study we demonstrate the utility of using mobile health apps and wearables combined with machine learning to forecast headache. We argue that high-dimensional modelling may greatly improve forecasting and discuss important considerations for future design of forecasting models using machine learning and mobile health data.

An open-label observational study and meta-analysis of non-invasive vagus nerve stimulation in medically refractory chronic cluster headache.

Background: Many patients with cluster headache (CH) are inadequately controlled by current treatment options. Non-invasive vagus nerve stimulation (nVNS) is reported to be effective in the management of CH though some studies suggest that it is ineffective. Objective: To assess the safety and efficacy of nVNS in chronic cluster headache (CCH) patients. Method: We prospectively analysed data from 40 patients with refractory CCH in this open-label, observational study. Patients were seen in tertiary headache clinics at the National Hospital for Neurology and Neurosurgery and trained to use nVNS as preventative therapy. Patients were reivewed at one month and then three-monthly from onset. The primary endpoint was number of patients achieving ≥50% reduction in attack frequency at 3 months. A meta-analysis of all published studies evaluating the efficacy of nVNS in CCH was also conducted. We searched MEDLINE and EMBASE for all studies investigating the use of nVNS as a preventive or adjunctive treatment for CCH with five or more participants. Combined mean difference and responder proportions with 95% confidence intervals (CI) were calculated from the included studies. Results: 17/40 patients (43%) achieved ≥50% reduction in attack frequency at 3 months. There was a significant reduction in monthly attack frequency from a baseline of 124 (±67) attacks to 79 (±63) attacks in month 3 (mean difference 44.7; 95% CI 25.1 to 64.3; p < 0.001). In month 3, there was also a 1.2-point reduction in average severity from a baseline Verbal Rating Scale of 8/10 (95% CI 0.5 to 1.9; p = 0.001). Four studies, along with the present study, were deemed eligible for meta-analysis, which showed a responder proportion of 0.35 (95% CI 0.07 to 0.69, n = 137) and a mean reduction in headache frequency of 35.3 attacks per month (95% CI 11.0 to 59.6, n = 108), from a baseline of 105 (±22.7) attacks per month. Conclusion: This study highlights the potential benefit of nVNS in CCH, with significant reductions in headache frequency and severity. To better characterise the effect, randomised sham-controlled trials are needed to confirm the beneficial response of VNS reported in some, but not all, open-label studies.

Randomized controlled studies evaluating Topiramate, Botulinum toxin type A, and mABs targeting CGRP in patients with chronic migraine and medication overuse headache: A systematic review and meta-analysis.

BACKGROUND: This systematic review focuses on chronic migraine patients with medication overuse headache using, respectively, topiramate, botulinum toxin type A, and human monoclonal antibodies targeting calcitonin gene-related peptide or its receptor. METHODS: A systematic search was conducted in the databases CENTRAL, MEDLINE, Embase and Web of Science until May 2022. We included randomized controlled trials reporting the outcomes of change in monthly headache/migraine days, ≥50% response rates and change in medication overuse status. Studies were excluded if response rates were not reported. Risk of bias assessment was performed using the Cochrane RoB2 tool. The quality of evidence for outcomes across included studies was evaluated according to the five factors outlined in Cochrane GRADE approach. FINDINGS: The initial search resulted in 1599 records. Following screening, 10 studies met our inclusion criteria, while seven studies with sufficient data were included in the meta-analysis. Studies assessing Botulinum toxin type A included 1139 patients and showed a mean reduction in headache frequency by 1.92 days per month compared to placebo (-1.92; 95% CI -2.68 to -1.16). Studies assessing human monoclonal antibodies included 1982 patients, and showed significant positive effect compared to placebo for all measured outcomes. The overall odds ratio for the ≥50% response rate was 2.90 (95% CI, 2.23 to 3.78). No significant difference was observed in the frequency of adverse effect for both Botulinum toxin type A and low dose of human monoclonal antibodies compared to placebo. There is currently insufficient evidence to determine the impact of topiramate in chronic migraine patients with medication overuse headache. INTERPRETATION: Botulinum toxin type A and human monoclonal antibodies targeting calcitonin gene-related peptide receptor were beneficial in reducing monthly migraine days and ≥50% response rate, but uncertainties remained for Botulinum toxin type A regarding response rate. The effect size for human monoclonal antibodies was greater with relatively lower drop-out rate. High-quality randomized trials are required to evaluate the effect of topiramate in chronic migraine patients with medication overuse headache.

Continuous positive airway pressure in cluster headache: A randomized, placebo-controlled, triple-blind, crossover study.

BACKGROUND: Oxygen inhalation aborts cluster headache attacks, and case reports show the effect of continuous positive airway pressure. The aim of this study was to investigate the prophylactic effect of continuous positive airway pressure in chronic cluster headache. METHODS: This was a randomized placebo-controlled triple-blind crossover study using active and sham continuous positive airway pressure treatment for chronic cluster headache. Patients entered a one month's baseline period before randomly being assigned to two months' active continuous positive airway pressure treatment followed by a four weeks' washout period and two months' sham continuous positive airway pressure or vice versa. Primary outcome measure was number of cluster headache attacks/week. RESULTS: Of the 30 included participants (12 males, median age 49.5 years, min-max 20-66 years), 25 completed both treatment/sham cycles (two discontinued, three lost to follow-up). The median number of cluster headache attacks per week was reduced from 8.25 (0.75-89.75) attacks to 6.25 (0-56.00) attacks for active continuous positive airway pressure and to 7.50 (0.50-43.75) attacks for sham continuous positive airway pressure, but there was no difference in active versus sham (p = 0.904). One patient had a serious adverse event during active treatment, none occurred during sham treatment. CONCLUSIONS: Continuous positive airway pressure treatment did not reduce the number of cluster headache attacks compared to sham treatment in chronic cluster headache patients. TRIAL REGISTRATION CLINICALTRIALS.GOV: NCT03397563.

Effect of Spinal Cord Burst Stimulation vs Placebo Stimulation on Disability in Patients With Chronic Radicular Pain After Lumbar Spine Surgery: A Randomized Clinical Trial.

Importance: The use of spinal cord stimulation for chronic pain after lumbar spine surgery is increasing, yet rigorous evidence of its efficacy is lacking. Objective: To investigate the efficacy of spinal cord burst stimulation, which involves the placement of an implantable pulse generator connected to electrodes with leads that travel into the epidural space posterior to the spinal cord dorsal columns, in patients with chronic radiculopathy after surgery for degenerative lumbar spine disorders. Design, Setting, and Participants: This placebo-controlled, crossover, randomized clinical trial in 50 patients was conducted at St Olavs University Hospital in Norway, with study enrollment from September 5, 2018, through April 28, 2021. The date of final follow-up was May 20, 2022. Interventions: Patients underwent two 3-month periods with spinal cord burst stimulation and two 3-month periods with placebo stimulation in a randomized order. Burst stimulation consisted of closely spaced, high-frequency electrical stimuli delivered to the spinal cord. The stimulus consisted of a 40-Hz burst mode of constant-current stimuli with 4 spikes per burst and an amplitude corresponding to 50% to 70% of the paresthesia perception threshold. Main Outcomes and Measures: The primary outcome was difference in change from baseline in the self-reported Oswestry Disability Index (ODI; range, 0 points [no disability] to 100 points [maximum disability]; the minimal clinically important difference was 10 points) score between periods with burst stimulation and placebo stimulation. The secondary outcomes were leg and back pain, quality of life, physical activity levels, and adverse events. Results: Among 50 patients who were randomized (mean age, 52.2 [SD, 9.9] years; 27 [54%] were women), 47 (94%) had at least 1 follow-up ODI score and 42 (84%) completed all stimulation randomization periods and ODI measurements. The mean ODI score at baseline was 44.7 points and the mean changes in ODI score were -10.6 points for the burst stimulation periods and -9.3 points for the placebo stimulation periods, resulting in a mean between-group difference of -1.3 points (95% CI, -3.9 to 1.3 points; P = .32). None of the prespecified secondary outcomes showed a significant difference. Nine patients (18%) experienced adverse events, including 4 (8%) who required surgical revision of the implanted system. Conclusions and Relevance: Among patients with chronic radicular pain after lumbar spine surgery, spinal cord burst stimulation, compared with placebo stimulation, after placement of a spinal cord stimulator resulted in no significant difference in the change from baseline in self-reported back pain-related disability. Trial Registration: ClinicalTrials.gov Identifier: NCT03546738.

Surgery for degenerative cervical myelopathy in patients with rheumatoid arthritis and ankylosing spondylitis: a nationwide registry-based study with patient-reported outcomes.

PURPOSE: To compare patient-reported outcomes (PROMs) following surgery for degenerative cervical myelopathy (DCM) among patients with rheumatoid arthritis (RA) or ankylosing spondylitis (AS) versus those without rheumatic diseases. METHODS: Data were obtained from the Norwegian Registry for Spine Surgery. The primary outcome was change in the Neck Disability Index (NDI) at 1 year. Secondary endpoints included the European Myelopathy Score (EMS), quality of life (EuroQoL-5D [EQ-5D]), numeric rating scales (NRS) for headache, neck pain, and arm pain, and complications. RESULTS: Among 905 participants operated between 2012 and 2018, 35 had RA or AS. There were significant improvements in all PROMs at 1 year and no statistically significant difference between the cohorts in mean change in NDI (- 0.64, 95% CI - 8.1 to 6.8, P = .372), EQ-5D (0.10, 95% CI - 0.04 to 0.24, P = .168), NRS neck pain (- 0.8, 95% CI - 2.0 to 0.4, P = .210), NRS arm pain (- 0.6, 95% CI - 1.9 to 0.7, P = .351), and NRS headache (- 0.5, 95% CI - 1.7 to 0.8, P = .460). DISCUSSION AND CONCLUSION: Our study adds to the limited available evidence that surgical treatment cannot only arrest further progression of myelopathy but also improve functional status, neurological outcomes, and quality of life in patients with rheumatic disease.

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.