Prediction of aneurysmal subarachnoid hemorrhage in comparison with other stroke types using routine care data.

Aneurysmal subarachnoid hemorrhage (aSAH) can be prevented by early detection and treatment of intracranial aneurysms in high-risk individuals. We investigated whether individuals at high risk of aSAH in the general population can be identified by developing an aSAH prediction model with electronic health records (EHR) data. To assess the aSAH model's relative performance, we additionally developed prediction models for acute ischemic stroke (AIS) and intracerebral hemorrhage (ICH) and compared the discriminative performance of the models. We included individuals aged ≥35 years without history of stroke from a Dutch routine care database (years 2007-2020) and defined outcomes aSAH, AIS and ICH using International Classification of Diseases (ICD) codes. Potential predictors included sociodemographic data, diagnoses, medications, and blood measurements. We cross-validated a Cox proportional hazards model with an elastic net penalty on derivation cohorts and reported the c-statistic and 10-year calibration on validation cohorts. We examined 1,040,855 individuals (mean age 54.6 years, 50.9% women) for a total of 10,173,170 person-years (median 11 years). 17,465 stroke events occurred during follow-up: 723 aSAH, 14,659 AIS, and 2,083 ICH. The aSAH model's c-statistic was 0.61 (95%CI 0.57-0.65), which was lower than the c-statistic of the AIS (0.77, 95%CI 0.77-0.78) and ICH models (0.77, 95%CI 0.75-0.78). All models were well-calibrated. The aSAH model identified 19 predictors, of which the 10 strongest included age, female sex, population density, socioeconomic status, oral contraceptive use, gastroenterological complaints, obstructive airway medication, epilepsy, childbirth complications, and smoking. Discriminative performance of the aSAH prediction model was moderate, while it was good for the AIS and ICH models. We conclude that it is currently not feasible to accurately identify individuals at increased risk for aSAH using EHR data.

Development and validation of a prediction model for failure of the transfemoral approach of endovascular treatment for large vessel occlusion acute ischemic stroke.

INTRODUCTION: Extracranial vascular characteristics determine the accessibility of the large vessel intracranial occlusion for endovascular treatment (EVT) in acute ischemic stroke. We developed and validated a prediction model for failure of the transfemoral approach to aid clinical decision making regarding EVT. METHODS: A prediction model was developed from data of patients included in the Dutch multicenter MR CLEAN Registry (March 18th 2014 until June 15th 2016) with penalized logistic regression. Predictor variables were available prior to the EVT procedure and included age, hypertension and extracranial vascular characteristics assessed on baseline CTA. The prediction model was internally validated, temporally validated within a second MR CLEAN Registry cohort (June 15th 2016 until November 1st 2017) and updated by re-estimating the coefficients using the combined cohort. RESULTS: Failure of the transfemoral approach occurred in 7% of patients, in both cohorts (derivation cohort: n=887, median age 71 years, interquartile range [IQR] 60-80, 52% men; validation cohort: n=1111, median age 73 years, IQR 62-81, 51% men). The prediction model had a c-statistic of 0.81 (95%CI: 0.76-0.86) in the derivation cohort, 0.69 (95%CI: 0.62-0.75) at temporal validation, and 0.75 (95%CI: 0.71-0.79) in the final prediction model, with the following penalized ß-coefficients for predictors age (per decade): 0.26, hypertension: -0.16, severe aortic arch elongation: 1.45, bovine aortic arch: 0.44, elongation of the supra-aortic arteries: 0.72, cervical ICA elongation: 0.44, and high-grade stenosis of the cervical ICA: 0.78. CONCLUSION: Our prediction model showed good performance for prediction of failure to reach the intracranial occlusion by the transfemoral approach.

Added Predictive Value of Female-Specific Factors and Psychosocial Factors for the Risk of Stroke in Women Under 50.

BACKGROUND AND OBJECTIVES: Female-specific factors and psychosocial factors may be important in the prediction of stroke but are not included in prediction models that are currently used. We investigated whether addition of these factors would improve the performance of prediction models for the risk of stroke in women younger than 50 years. METHODS: We used data from the Stichting Informatievoorziening voor Zorg en Onderzoek, population-based, primary care database of women aged 20-49 years without a history of cardiovascular disease. Analyses were stratified by 10-year age intervals at cohort entry. Cox proportional hazards models to predict stroke risk were developed, including traditional cardiovascular factors, and compared with models that additionally included female-specific and psychosocial factors. We compared the risk models using the c-statistic and slope of the calibration curve at a follow-up of 10 years. We developed an age-specific stroke risk prediction tool that may help communicating the risk of stroke in clinical practice. RESULTS: We included 409,026 women with a total of 3,990,185 person-years of follow-up. Stroke occurred in 2,751 women (incidence rate 6.9 [95% CI 6.6-7.2] per 10,000 person-years). Models with only traditional cardiovascular factors performed poorly to moderately in all age groups: 20-29 years: c-statistic: 0.617 (95% CI 0.592-0.639); 30-39 years: c-statistic: 0.615 (95% CI 0.596-0.634); and 40-49 years: c-statistic: 0.585 (95% CI 0.573-0.597). After adding the female-specific and psychosocial risk factors to the reference models, the model discrimination increased moderately, especially in the age groups 30-39 (Δc-statistic: 0.019) and 40-49 years (Δc-statistic: 0.029) compared with the reference models, respectively. DISCUSSION: The addition of female-specific factors and psychosocial risk factors improves the discriminatory performance of prediction models for stroke in women younger than 50 years.

SCORE2 cardiovascular risk prediction models in an ethnic and socioeconomic diverse population in the Netherlands: an external validation study.

Background: Socioeconomic status and ethnicity are not explicitly incorporated as risk factors in the four SCORE2 cardiovascular disease (CVD) risk models developed for country-wide implementation across Europe (low, moderate, high and very-high model). The aim of this study was to evaluate the performance of the four SCORE2 CVD risk prediction models in an ethnic and socioeconomic diverse population in the Netherlands. Methods: The SCORE2 CVD risk models were externally validated in socioeconomic and ethnic (by country of origin) subgroups, from a population-based cohort in the Netherlands, with GP, hospital and registry data. In total 155,000 individuals, between 40 and 70 years old in the study period from 2007 to 2020 and without previous CVD or diabetes were included. Variables (age, sex, smoking status, blood pressure, cholesterol) and outcome first CVD event (stroke, myocardial infarction, CVD death) were consistent with SCORE2. Findings: 6966 CVD events were observed, versus 5495 events predicted by the CVD low-risk model (intended for use in the Netherlands). Relative underprediction was similar in men and women (observed/predicted (OE-ratio), 1.3 and 1.2 in men and women, respectively). Underprediction was larger in low socioeconomic subgroups of the overall study population (OE-ratio 1.5 and 1.6 in men and women, respectively), and comparable in Dutch and the combined "other ethnicities" low socioeconomic subgroups. Underprediction in the Surinamese subgroup was largest (OE-ratio 1.9, in men and women), particularly in the low socioeconomic Surinamese subgroups (OE-ratio 2.5 and 2.1 in men and women). In the subgroups with underprediction in the low-risk model, the intermediate or high-risk SCORE2 models showed improved OE-ratios. Discrimination showed moderate performance in all subgroups and the four SCORE2 models, with C-statistics between 0.65 and 0.72, similar to the SCORE2 model development study. Interpretation: The SCORE 2 CVD risk model for low-risk countries (as the Netherlands are) was found to underpredict CVD risk, particularly in low socioeconomic and Surinamese ethnic subgroups. Including socioeconomic status and ethnicity as predictors in CVD risk models and implementing CVD risk adjustment within countries is desirable for adequate CVD risk prediction and counselling. Funding: Leiden University Medical Centre and Leiden University.

Cardiovascular Risk Prediction in Men and Women Aged Under 50 Years Using Routine Care Data.

Background Prediction models for risk of cardiovascular events generally do not include young adults, and cardiovascular risk factors differ between women and men. Therefore, this study aimed to develop prediction models for first-ever cardiovascular event risk in men and women aged 30 to 49 years. Methods and Results We included patients aged 30 to 49 years without cardiovascular disease from a Dutch routine care database. Outcome was defined as first-ever cardiovascular event. Our reference models were sex-specific Cox proportional hazards models based on traditional cardiovascular predictors, which we compared with models using 2 predictor subsets with the 20 or 50 most important predictors based on the Cox elastic net model regularization coefficients. We assessed the C-index and calibration curve slopes at 10 years of follow-up. We stratified our analyses based on 30- to 39-year and 40- to 49-year age groups at baseline. We included 542 141 patients (mean age 39.7, 51% women). During follow-up, 10 767 cardiovascular events occurred. Discrimination of reference models including traditional cardiovascular predictors was moderate (women: C-index, 0.648 [95% CI, 0.645-0.652]; men: C-index, 0.661 [95%CI, 0.658-0.664]). In women and men, the Cox proportional hazard models including 50 most important predictors resulted in an increase in C-index (0.030 and 0.012, respectively), and a net correct reclassification of 3.7% of the events in women and 1.2% in men compared with the reference model. Conclusions Sex-specific electronic health record-derived prediction models for first-ever cardiovascular events in the general population aged <50 years have moderate discriminatory performance. Data-driven predictor selection leads to identification of nontraditional cardiovascular predictors, which modestly increase performance of models.

Sex differences in onset to hospital arrival time, prestroke disability, and clinical symptoms in patients with a large vessel occlusion: a MR CLEAN Registry substudy.

BACKGROUND: Women have been reported to have worse outcomes after endovascular treatment (EVT), despite a similar treatment effect in non-clinical trial populations. We aimed to assess sex differences at hospital presentation with respect to workflow metrics, prestroke disability, and presenting clinical symptoms. METHODS: We included consecutive patients from the Multicentre Randomised Controlled Trial of Endovascular Treatment for Acute Ischaemic Stroke in The Netherlands (MR CLEAN) Registry (2014-2018) who received EVT for anterior circulation large vessel occlusion (LVO). We assessed sex differences in workflow metrics, prestroke disability (modified Rankin Scale (mRS) score ≥1), and stroke severity and symptoms according to the National Institutes of Health Stroke Scale (NIHSS) score on hospital admission with logistic and linear regression analyses and calculated the adjusted OR (aOR). RESULTS: We included 4872 patients (47.6% women). Compared with men, women were older (median age 76 vs 70 years) and less often achieved good functional outcome at 90 days (mRS ≤2: 35.2% vs 46.4%, aOR 0.70, 95% CI 0.60 to 0.82). Mean onset-to-door time was longer in women (2 hours 16 min vs 2 hours 7 min, adjusted delay 9 min, 95% CI 4 to 13). This delay contributed to longer onset-to-groin times (3 hours 26 min in women vs 3 hours 13 min in men, adjusted delay 13 min, 95% CI 9 to 17). Women more often had prestroke disability (mRS ≥1: 41.1% vs 29.1%, aOR 1.57, 95% CI 1.36 to 1.82). NIHSS on admission was essentially similar in men and women (mean 15±6 vs 15±6, NIHSS <10 vs ≥10, aOR 0.91, 95% CI 0.78 to 1.06). There were no clear sex differences in the occurrence of specific stroke symptoms. CONCLUSION: Women with LVO had longer onset-to-door times and more often prestroke disability than men. Raising awareness of these differences at hospital presentation and investigating underlying causes may help to improve outcome after EVT in women.

Population health interventions for cardiometabolic diseases in primary care: a scoping review and RE-AIM evaluation of current practices.

Introduction: Cardiometabolic diseases (CMD) are the leading cause of death in high-income countries and are largely attributable to modifiable risk factors. Population health management (PHM) can effectively identify patient subgroups at high risk of CMD and address missed opportunities for preventive disease management. Guided by the Reach, Efficacy, Adoption, Implementation and Maintenance (RE-AIM) framework, this scoping review of PHM interventions targeting patients in primary care at increased risk of CMD aims to describe the reported aspects for successful implementation. Methods: A comprehensive search was conducted across 14 databases to identify papers published between 2000 and 2023, using Arksey and O'Malley's framework for conducting scoping reviews. The RE-AIM framework was used to assess the implementation, documentation, and the population health impact score of the PHM interventions. Results: A total of 26 out of 1,100 studies were included, representing 21 unique PHM interventions. This review found insufficient reporting of most RE-AIM components. The RE-AIM evaluation showed that the included interventions could potentially reach a large audience and achieve their intended goals, but information on adoption and maintenance was often lacking. A population health impact score was calculated for six interventions ranging from 28 to 62%. Discussion: This review showed the promise of PHM interventions that could reaching a substantial number of participants and reducing CMD risk factors. However, to better assess the generalizability and scalability of these interventions there is a need for an improved assessment of adoption, implementation processes, and sustainability.

Delayed Cerebral Ischemia After Aneurysmal Subarachnoid Hemorrhage in Young Patients With a History of Migraine.

BACKGROUND: Young patients with aneurysmal subarachnoid hemorrhage (aSAH) and a history of migraine may have an increased risk of delayed cerebral ischemia. We investigated this potential association in a prospective cohort of aSAH patients under 50 years of age. METHODS: In our prospective cohort study, we included patients with aSAH under 50 years of age from 3 hospitals in the Netherlands. We assessed lifetime migraine history with a short screener. Delayed cerebral ischemia was defined as neurological deterioration lasting >1 hour not attributable to other causes by diagnostic workup. Adjustments were made for possible confounders in multivariable Cox regression analyses, and adjusted hazard ratios were calculated. RESULTS: We included 236 young aSAH patients (mean age, 41 years; 64% women) of whom 44 (19%) had a history of migraine (16 with aura). Patients with aSAH and a history of migraine were not at increased risk of developing delayed cerebral ischemia compared with patients without migraine (25% versus 20%; adjusted hazard ratio, 1.16 [95% CI, 0.57-2.35]). Additionally, no increased risk was found in migraine patients with aura (adjusted hazard ratio, 0.85 [95% CI, 0.30-2.44]) or in women (adjusted hazard ratio, 1.24 [95% CI, 0.58-2.68]). CONCLUSIONS: Patients with aSAH under the age of 50 years with a history of migraine are not at increased risk of delayed cerebral ischemia.

Clarifying responsibility: professional digital health in the doctor-patient relationship, recommendations for physicians based on a multi-stakeholder dialogue in the Netherlands.

BACKGROUND: Implementation of digital health (eHealth) generally involves adapting pre-established and carefully considered processes or routines, and still raises multiple ethical and legal dilemmas. This study aimed to identify challenges regarding responsibility and liability when prescribing digital health in clinical practice. This was part of an overarching project aiming to explore the most pressing ethical and legal obstacles regarding the implementation and adoption of digital health in the Netherlands, and to propose actionable solutions. METHODS: A series of multidisciplinary focus groups with stakeholders who have relevant digital health expertise were analysed through thematic analysis. RESULTS: The emerging general theme was 'uncertainty regarding responsibilities' when adopting digital health. Key dilemmas take place in clinical settings and within the doctor-patient relationship ('professional digital health'). This context is particularly challenging because different stakeholders interact. In the absence of appropriate legal frameworks and codes of conduct tailored to digital health, physicians' responsibility is to be found in their general duty of care. In other words: to do what is best for patients (not causing harm and doing good). Professional organisations could take a leading role to provide more clarity with respect to physicians' responsibility, by developing guidance describing physicians' duty of care in the context of digital health, and to address the resulting responsibilities. CONCLUSIONS: Although legal frameworks governing medical practice describe core ethical principles, rights and obligations of physicians, they do not suffice to clarify their responsibilities in the setting of professional digital health. Here we present a series of recommendations to provide more clarity in this respect, offering the opportunity to improve quality of care and patients' health. The recommendations can be used as a starting point to develop professional guidance and have the potential to be adapted to other healthcare professionals and systems.

Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review.

While the opportunities of ML and AI in healthcare are promising, the growth of complex data-driven prediction models requires careful quality and applicability assessment before they are applied and disseminated in daily practice. This scoping review aimed to identify actionable guidance for those closely involved in AI-based prediction model (AIPM) development, evaluation and implementation including software engineers, data scientists, and healthcare professionals and to identify potential gaps in this guidance. We performed a scoping review of the relevant literature providing guidance or quality criteria regarding the development, evaluation, and implementation of AIPMs using a comprehensive multi-stage screening strategy. PubMed, Web of Science, and the ACM Digital Library were searched, and AI experts were consulted. Topics were extracted from the identified literature and summarized across the six phases at the core of this review: (1) data preparation, (2) AIPM development, (3) AIPM validation, (4) software development, (5) AIPM impact assessment, and (6) AIPM implementation into daily healthcare practice. From 2683 unique hits, 72 relevant guidance documents were identified. Substantial guidance was found for data preparation, AIPM development and AIPM validation (phases 1-3), while later phases clearly have received less attention (software development, impact assessment and implementation) in the scientific literature. The six phases of the AIPM development, evaluation and implementation cycle provide a framework for responsible introduction of AI-based prediction models in healthcare. Additional domain and technology specific research may be necessary and more practical experience with implementing AIPMs is needed to support further guidance.

Sex Differences in Presentation of Stroke: A Systematic Review and Meta-Analysis.

BACKGROUND AND PURPOSE: Women have worse outcomes than men after stroke. Differences in presentation may lead to misdiagnosis and, in part, explain these disparities. We investigated whether there are sex differences in clinical presentation of acute stroke or transient ischemic attack. METHODS: We conducted a systematic review and meta-analysis according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement. Inclusion criteria were (1) cohort, cross-sectional, case-control, or randomized controlled trial design; (2) admission for (suspicion of) ischemic or hemorrhagic stroke or transient ischemic attack; and (3) comparisons possible between sexes in ≥1 nonfocal or focal acute stroke symptom(s). A random-effects model was used for our analyses. We performed sensitivity and subanalyses to help explain heterogeneity and used the Newcastle-Ottawa Scale to assess bias. RESULTS: We included 60 studies (n=582 844; 50% women). In women, headache (pooled odds ratio [OR], 1.24 [95% CI, 1.11-1.39]; I2=75.2%; 30 studies) occurred more frequently than in men with any type of stroke, as well as changes in consciousness/mental status (OR, 1.38 [95% CI, 1.19-1.61]; I2=95.0%; 17 studies) and coma/stupor (OR, 1.39 [95% CI, 1.25-1.55]; I2=27.0%; 13 studies). Aspecific or other neurological symptoms (nonrotatory dizziness and non-neurological symptoms) occurred less frequently in women (OR, 0.96 [95% CI, 0.94-0.97]; I2=0.1%; 5 studies). Overall, the presence of focal symptoms was not associated with sex (pooled OR, 1.03) although dysarthria (OR, 1.14 [95% CI, 1.04-1.24]; I2=48.6%; 11 studies) and vertigo (OR, 1.23 [95% CI, 1.13-1.34]; I2=44.0%; 8 studies) occurred more frequently, whereas symptoms of paresis/hemiparesis (OR, 0.73 [95% CI, 0.54-0.97]; I2=72.6%; 7 studies) and focal visual disturbances (OR, 0.83 [95% CI, 0.70-0.99]; I2=62.8%; 16 studies) occurred less frequently in women compared with men with any type of stroke. Most studies contained possible sources of bias. CONCLUSIONS: There may be substantive differences in nonfocal and focal stroke symptoms between men and women presenting with acute stroke or transient ischemic attack, but sufficiently high-quality studies are lacking. More studies are needed to address this because sex differences in presentation may lead to misdiagnosis and undertreatment.

Developing Clinical Prediction Models Using Primary Care Electronic Health Record Data: The Impact of Data Preparation Choices on Model Performance.

Objective: To quantify prediction model performance in relation to data preparation choices when using electronic health records (EHR). Study Design and Setting: Cox proportional hazards models were developed for predicting the first-ever main adverse cardiovascular events using Dutch primary care EHR data. The reference model was based on a 1-year run-in period, cardiovascular events were defined based on both EHR diagnosis and medication codes, and missing values were multiply imputed. We compared data preparation choices based on (i) length of the run-in period (2- or 3-year run-in); (ii) outcome definition (EHR diagnosis codes or medication codes only); and (iii) methods addressing missing values (mean imputation or complete case analysis) by making variations on the derivation set and testing their impact in a validation set. Results: We included 89,491 patients in whom 6,736 first-ever main adverse cardiovascular events occurred during a median follow-up of 8 years. Outcome definition based only on diagnosis codes led to a systematic underestimation of risk (calibration curve intercept: 0.84; 95% CI: 0.83-0.84), while complete case analysis led to overestimation (calibration curve intercept: -0.52; 95% CI: -0.53 to -0.51). Differences in the length of the run-in period showed no relevant impact on calibration and discrimination. Conclusion: Data preparation choices regarding outcome definition or methods to address missing values can have a substantial impact on the calibration of predictions, hampering reliable clinical decision support. This study further illustrates the urgency of transparent reporting of modeling choices in an EHR data setting.

Sex Differences in Risk Profile, Stroke Cause and Outcome in Ischemic Stroke Patients With and Without Migraine.

Background: An increased risk of stroke in patients with migraine has been primarily found for women. The sex-dependent mechanisms underlying the migraine-stroke association, however, remain unknown. This study aims to explore these sex differences to improve our understanding of pathophysiological mechanisms behind the migraine-stroke association. Methods: We included 2,492 patients with ischemic stroke from the prospective multicenter Dutch Parelsnoer Institute Initiative study, 425 (17%) of whom had a history of migraine. Cardiovascular risk profile, stroke cause (TOAST classification), and outcome [modified Rankin scale (mRS) at 3 months] were compared with both sexes between patients with and without migraine. Results: A history of migraine was not associated with sex differences in the prevalence of conventional cardiovascular risk factors. Women with migraine had an increased risk of stroke at young age (onset < 50 years) compared with women without migraine (RR: 1.7; 95% CI: 1.3-2.3). Men with migraine tended to have more often stroke in the TOAST category other determined etiology (RR: 1.7; 95% CI: 1.0-2.7) in comparison with men without migraine, whereas this increase was not found in women with migraine. Stroke outcome was similar for women with or without migraine (mRS ≥ 3 RR 1.1; 95% CI 0.7-1.5), whereas men seemed to have a higher risk of poor outcome compared with their counterparts without migraine (mRS ≥ 3 RR: 1.5; 95% CI: 1.0-2.1). Conclusion: Our results indicate possible sex differences in the pathophysiology underlying the migraine-stroke association, which are unrelated to conventional cardiovascular risk factors. Further research in larger cohorts is needed to validate these findings.

Predicting Poor Outcome Before Endovascular Treatment in Patients With Acute Ischemic Stroke.

Background: Although endovascular treatment (EVT) has greatly improved outcomes in acute ischemic stroke, still one third of patients die or remain severely disabled after stroke. If we could select patients with poor clinical outcome despite EVT, we could prevent futile treatment, avoid treatment complications, and further improve stroke care. We aimed to determine the accuracy of poor functional outcome prediction, defined as 90-day modified Rankin Scale (mRS) score ≥5, despite EVT treatment. Methods: We included 1,526 patients from the MR CLEAN Registry, a prospective, observational, multicenter registry of ischemic stroke patients treated with EVT. We developed machine learning prediction models using all variables available at baseline before treatment. We optimized the models for both maximizing the area under the curve (AUC), reducing the number of false positives. Results: From 1,526 patients included, 480 (31%) of patients showed poor outcome. The highest AUC was 0.81 for random forest. The highest area under the precision recall curve was 0.69 for the support vector machine. The highest achieved specificity was 95% with a sensitivity of 34% for neural networks, indicating that all models contained false positives in their predictions. From 921 mRS 0-4 patients, 27-61 (3-6%) were incorrectly classified as poor outcome. From 480 poor outcome patients in the registry, 99-163 (21-34%) were correctly identified by the models. Conclusions: All prediction models showed a high AUC. The best-performing models correctly identified 34% of the poor outcome patients at a cost of misclassifying 4% of non-poor outcome patients. Further studies are necessary to determine whether these accuracies are reproducible before implementation in clinical practice.

Delayed Cerebral Ischemia After Aneurysmal Subarachnoid Hemorrhage in Patients With a History of Migraine.

BACKGROUND AND PURPOSE: Delayed cerebral ischemia (DCI) is a major contributor to the high morbidity in patients with aneurysmal subarachnoid hemorrhage (aSAH). Spreading depolarizations may play a role in DCI pathophysiology. Because patients with migraine are probably more susceptible to spreading depolarizations, we investigated whether patients with aneurysmal subarachnoid hemorrhage with migraine are at increased risk for DCI. METHODS: We included patients with aneurysmal subarachnoid hemorrhage from 3 hospitals in the Netherlands. We assessed lifetime migraine history with a short screener. DCI was defined as neurological deterioration lasting >1 hour not attributable to other causes by diagnostic work-up. Adjustments were made for possible confounders in multivariable Cox regression analyses and adjusted hazard ratios (aHR) were calculated. We assessed the interaction effects of age and sex. RESULTS: We included 582 patients (mean age 57 years, 71% women) mostly with mild to moderate aneurysmal subarachnoid hemorrhage of whom 108 (19%) had a history of migraine (57 with aura). Patients with migraine were not at increased risk of developing DCI compared with patients without migraine (22% versus 24%, aHR, 0.89 [95% CI, 0.56-1.43]). Additionally, no increased risk was found in patients with migraine with possible aura (aHR, 0.74 [95% CI, 0.39-1.43]), in women (aHR, 0.88 [95% CI, 0.53-1.45], Pinteraction=0.859), or in young patients aged <50 years (aHR, 1.59 [95% CI, 0.72-3.49]), although numbers in these subgroups were limited. We found an interaction between migraine and age with an increased risk of DCI among young patients with migraine (Pinteraction=0.075). CONCLUSIONS: Patients with migraine are in general not at increased risk of DCI. Future studies should focus in particular on young SAH patients, in whom there might be an association between migraine history and development of DCI.

Telemonitoring for Patients With COVID-19: Recommendations for Design and Implementation.

Despite significant efforts, the COVID-19 pandemic has put enormous pressure on health care systems around the world, threatening the quality of patient care. Telemonitoring offers the opportunity to carefully monitor patients with a confirmed or suspected case of COVID-19 from home and allows for the timely identification of worsening symptoms. Additionally, it may decrease the number of hospital visits and admissions, thereby reducing the use of scarce resources, optimizing health care capacity, and minimizing the risk of viral transmission. In this paper, we present a COVID-19 telemonitoring care pathway developed at a tertiary care hospital in the Netherlands, which combined the monitoring of vital parameters with video consultations for adequate clinical assessment. Additionally, we report a series of medical, scientific, organizational, and ethical recommendations that may be used as a guide for the design and implementation of telemonitoring pathways for COVID-19 and other diseases worldwide.

Intrinsic Coagulation Pathway, History of Headache, and Risk of Ischemic Stroke.

Background and Purpose- Hypercoagulable states in migraine patients may play a role in the pathophysiology underlying the association between migraine and ischemic stroke. This study aims to provide more insight into the potential association of headache, ischemic stroke, and the intrinsic coagulation pathway. Methods- We included patients from the RATIO study (Risk of Arterial Thrombosis in Relation to Oral Contraceptives), a Dutch population-based case-control study including young women (age <50) with ischemic stroke and healthy controls. We defined a headache group based on a questionnaire on headache history. Intrinsic coagulation proteins were measured through both antigen levels (FXII, FXI, prekallikrein, HK [high molecular weight kininogen]) and protein activation, determined by measuring activated protein complex with C1esterase-inhibitor (FXIIa-C1-INH, FXIa-C1-INH, Kallikrein-C1-INH) or antitrypsin-inhibitor (FXIa-AT-INH). We calculated adjusted odds ratios and performed an interaction analysis assessing the increase in stroke risk associated with high levels of intrinsic coagulation and history of headache. Results- We included 113 ischemic stroke cases and 598 healthy controls. In total, 134 (19%) patients had a history of headache, of whom 38 were cases and 96 controls. The combination of headache and high intrinsic coagulation protein levels (all but FXII antigen level and both FXIa-inhibitors) was associated with an increase in ischemic stroke risk higher than was expected based on their individual effects (adjusted odds ratio FXI antigen level alone: 1.7, 95% CI, 1.0-2.9; adjusted odds ratio headache alone: 2.0, 95% CI, 1.1-3.7; combination: 5.2, 95% CI, 2.3-11.6) Conclusions- Headache and high intrinsic coagulation protein levels may biologically interact, increasing risk for ischemic stroke.

Predicting Outcome of Endovascular Treatment for Acute Ischemic Stroke: Potential Value of Machine Learning Algorithms.

Background: Endovascular treatment (EVT) is effective for stroke patients with a large vessel occlusion (LVO) of the anterior circulation. To further improve personalized stroke care, it is essential to accurately predict outcome after EVT. Machine learning might outperform classical prediction methods as it is capable of addressing complex interactions and non-linear relations between variables. Methods: We included patients from the Multicenter Randomized Clinical Trial of Endovascular Treatment for Acute Ischemic Stroke in the Netherlands (MR CLEAN) Registry, an observational cohort of LVO patients treated with EVT. We applied the following machine learning algorithms: Random Forests, Support Vector Machine, Neural Network, and Super Learner and compared their predictive value with classic logistic regression models using various variable selection methodologies. Outcome variables were good reperfusion (post-mTICI ≥ 2b) and functional independence (modified Rankin Scale ≤2) at 3 months using (1) only baseline variables and (2) baseline and treatment variables. Area under the ROC-curves (AUC) and difference of mean AUC between the models were assessed. Results: We included 1,383 EVT patients, with good reperfusion in 531 (38%) and functional independence in 525 (38%) patients. Machine learning and logistic regression models all performed poorly in predicting good reperfusion (range mean AUC: 0.53-0.57), and moderately in predicting 3-months functional independence (range mean AUC: 0.77-0.79) using only baseline variables. All models performed well in predicting 3-months functional independence using both baseline and treatment variables (range mean AUC: 0.88-0.91) with a negligible difference of mean AUC (0.01; 95%CI: 0.00-0.01) between best performing machine learning algorithm (Random Forests) and best performing logistic regression model (based on prior knowledge). Conclusion: In patients with LVO machine learning algorithms did not outperform logistic regression models in predicting reperfusion and 3-months functional independence after endovascular treatment. For all models at time of admission radiological outcome was more difficult to predict than clinical outcome.

Migraine and Cerebrovascular Atherosclerosis in Patients With Ischemic Stroke.

BACKGROUND AND PURPOSE: Migraine is a well-established risk factor for ischemic stroke, but migraine is also related to other vascular diseases. This study aims to investigate the association between migraine and cerebrovascular atherosclerosis in patients with acute ischemic stroke. METHODS: We retrieved data on patients with ischemic stroke from the DUST (Dutch Acute Stroke Study). Migraine history was assessed with a migraine screener and confirmed by telephone interview based on the ICHD criteria (International Classification of Headache Disorders). We assessed intra- and extracranial atherosclerotic changes and quantified intracranial internal carotid artery calcifications as measure of atherosclerotic burden on noncontrast computed tomography and computed tomographic angiography. We calculated risk ratios with adjustments for possible confounders with multivariable Poisson regression analyses. RESULTS: We included 656 patients, aged 18 to 99 years, of whom 53 had a history of migraine (29 with aura). Patients with migraine did not have more frequent atherosclerotic changes in intracranial (51% versus 74%; adjusted risk ratio, 0.82; 95% confidence interval, 0.64-1.05) or extracranial vessels (62% versus 79%; adjusted risk ratio, 0.93; 95% confidence interval, 0.77-1.12) than patients without migraine and had comparable internal carotid artery calcification volumes (largest versus medium and smallest volume tertile, 23% versus 35%; adjusted risk ratio, 0.93; 95% confidence interval, 0.57-1.52). CONCLUSIONS: Migraine is not associated with excess atherosclerosis in large vessels in patients with acute ischemic stroke. Our findings suggest that the biological mechanisms by which migraine results in ischemic stroke are not related to macrovascular cerebral atherosclerosis.