Machine Learning-Based Prediction of Stroke in Emergency Departments.

Background: Stroke misdiagnosis, associated with poor outcomes, is estimated to occur in 9% of all stroke patients. Objectives: We hypothesized that machine learning (ML) could assist in the diagnosis of ischemic stroke in emergency departments (EDs). Design: The study was conducted and reported according to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis guidelines. We performed model development and prospective temporal validation, using data from pre- and post-COVID periods; we also performed a case study on a small cohort of previously misdiagnosed stroke patients. Methods: We used structured and unstructured electronic health records (EHRs) of 56,452 patient encounters from 13 hospitals in Pennsylvania, from September 2003 to January 2021. ML pipelines, including natural language processing, were created using pre-event clinical data and provider notes in the EDs. Results: Using pre-event information, our model's area under the receiver operating characteristics curve (AUROC) ranged from 0.88 to 0.92 with a similar range accuracy (0.87-0.90). Using provider notes, we identified five models that reached a balanced performance in terms of AUROC, sensitivity, and specificity. Model AUROC ranged from 0.93 to 0.99. Model sensitivity and specificity reached 0.90 and 0.99, respectively. Four of the top five performing models were based on the post-COVID provider notes; however, no performance difference between models tested on pre- and post-COVID was observed. Conclusion: This study leveraged pre-event and at-encounter level EHR for stroke prediction. The results indicate that available clinical information can be used for building EHR-based stroke prediction models and ED stroke alert systems.

Prevalence and associated factors of cerebral microbleeds in a rural population of the United States.

OBJECTIVE: Cerebral microbleeds (CMBs) can carry an advanced risk for the development and burden of cerebrovascular and cognitive disorders. Large-scale population-based studies are required to identify the at-risk population. METHOD: Ten percent (N = 3,056) of the Geisinger DiscovEHR Initiative Cohort participants who had brain magnetic resonance imaging (MRI) for any indication were randomly selected. Patients with CMBs were compared to an age-, gender-, body mass index-, and hypertension-matched cohort of patients without CMB. The prevalence of comorbidities and use of anticoagulation therapy was investigated in association with CMB presence (binary logistic regression), quantity (ordinal regression), and topography (multinomial regression). RESULTS: Among 3,056 selected participants, 477 (15.6 %) had CMBs in their MRI. Patients with CMBs were older and were more prevalently hypertensive, with ischemic stroke, arrhythmia, dyslipidemia, coronary artery disease, and the use of warfarin. After propensity-score matching, 477 patients with CMBs and 974 without were included for further analyses. Predictors of ≥5 CMBs were ischemic stroke (OR, 1.6; 95 % CI, 1.2 -2.0), peripheral vascular disease (OR, 1.6; 95 % CI, 1.1-2.3), and thrombocytopenia (OR, 1.9; 95 % CI, 1.2-2.9). Ischemic stroke was associated with strictly lobar CMBs more strongly than deep/infra-tentorial CMBs (OR, 2.1; 95 % CI, 1.5-3.1; vs. OR, 1.4; CI, 1.1-1.8). CONCLUSIONS: CMBs were prevalent in our white population. Old age, hypertension, anticoagulant treatment, thrombocytopenia, and a history of vascular diseases including stroke, were associated with CMBs.

An integrated pipeline for prediction of Clostridioides difficile infection.

With the expansion of electronic health records(EHR)-linked genomic data comes the development of machine learning-enable models. There is a pressing need to develop robust pipelines to evaluate the performance of integrated models and minimize systemic bias. We developed a prediction model of symptomatic Clostridioides difficile infection(CDI) by integrating common EHR-based and genetic risk factors(rs2227306/IL8). Our pipeline includes (1) leveraging phenotyping algorithm to minimize temporal bias, (2) performing simulation studies to determine the predictive power in samples without genetic information, (3) propensity score matching to control for the confoundings, (4) selecting machine learning algorithms to capture complex feature interactions, (5) performing oversampling to address data imbalance, and (6) optimizing models and ensuring proper bias-variance trade-off. We evaluate the performance of prediction models of CDI when including common clinical risk factors and the benefit of incorporating genetic feature(s) into the models. We emphasize the importance of building a robust integrated pipeline to avoid systemic bias and thoroughly evaluating genetic features when integrated into the prediction models in the general population and subgroups.

Defining the Age of Young Ischemic Stroke Using Data-Driven Approaches.

Introduction: The cut-point for defining the age of young ischemic stroke (IS) is clinically and epidemiologically important, yet it is arbitrary and differs across studies. In this study, we leveraged electronic health records (EHRs) and data science techniques to estimate an optimal cut-point for defining the age of young IS. Methods: Patient-level EHRs were extracted from 13 hospitals in Pennsylvania, and used in two parallel approaches. The first approach included ICD9/10, from IS patients to group comorbidities, and computed similarity scores between every patient pair. We determined the optimal age of young IS by analyzing the trend of patient similarity with respect to their clinical profile for different ages of index IS. The second approach used the IS cohort and control (without IS), and built three sets of machine-learning models-generalized linear regression (GLM), random forest (RF), and XGBoost (XGB)-to classify patients for seventeen age groups. After extracting feature importance from the models, we determined the optimal age of young IS by analyzing the pattern of comorbidity with respect to the age of index IS. Both approaches were completed separately for male and female patients. Results: The stroke cohort contained 7555 ISs, and the control included 31,067 patients. In the first approach, the optimal age of young stroke was 53.7 and 51.0 years in female and male patients, respectively. In the second approach, we created 102 models, based on three algorithms, 17 age brackets, and two sexes. The optimal age was 53 (GLM), 52 (RF), and 54 (XGB) for female, and 52 (GLM and RF) and 53 (RF) for male patients. Different age and sex groups exhibited different comorbidity patterns. Discussion: Using a data-driven approach, we determined the age of young stroke to be 54 years for women and 52 years for men in our mainly rural population, in central Pennsylvania. Future validation studies should include more diverse populations.

An updated review and meta-analysis of screening tools for stroke in the emergency room and prehospital setting.

BACKGROUND: Stroke screening tools should have good diagnostic performance for early diagnosis and a proper therapeutic plan. This paper describes and compares various diagnostic tools used to identify stroke in emergency departments and prehospital setting. METHODS: The meta-analysis was conducted according to the Preferred Reporting Items for a Systematic Review and Meta-analysis of Diagnostic Test Accuracy Studies (PRISMA-DTA) guidelines. The PubMed and Scopus databases were searched until December 31, 2021, for studies published on stroke screening tools. These tools' diagnostic performance (sensitivity and specificity) was pooled using a bivariate random-effects model whenever appropriate. RESULTS: Eleven screening tools for stroke were identified in 29 different studies. The various tools had a wide range of sensitivity and specificity in different studies. In the meta-analysis, the Cincinnati Pre-hospital Stroke Scale, Face Arm Speech Test, and Recognition of Stroke in the Emergency Room (ROSIER) had sensitivity (between 83 and 91%) but poor specificity (all below 64%). When comparing all the tools, ROSIER had the highest sensitivity 90.5%. Los Angeles Pre-hospital Stroke Screen performed best in terms of specificity 88.7% but had low sensitivity (73.9%). Melbourne Ambulance Stroke Screen had a balanced performance in terms of sensitivity (86%) and specificity (76%). Sensitivity analysis consisting of only prospective studies showed a similar range of sensitivity and specificity. CONCLUSION: All the stroke screening tools included in the review were comparable, but no clear superior screening tool could be identified. Simple screening tools like Cincinnati prehospital stroke scale (CPSS) have similar performance compared to more complex tools.

Long-term mortality in ischemic stroke patients with concomitant chronic obstructive pulmonary disease.

BACKGROUND: Long-term mortality in ischemic stroke patients with concomitant COPD has been largely unexplored. This study aimed to compare long-term all-cause mortality in ischemic stroke patients with and without COPD. METHODS: This was a retrospective cohort study of ischemic stroke patients with and without COPD in the Geisinger Neuroscience Ischemic Stroke database to examine all-cause mortality up to 3 years using Kaplan-Meier estimator and Cox proportional hazards model. RESULTS: Of the 6,589 ischemic stroke patients included in this study, 5,525 (83.9%) did not have COPD (group A). Group B (n=1,006) consisted of patients with COPD diagnosis by ICD-9/10-CM codes. COPD patients in Group C (n=233) were diagnosed by spirometry, and in Group D (n=175) by both ICD-9/10-CM codes and spirometry confirmation. The survival probabilities at three years in Group B, C, and D were significantly lower than in Group A. Group B (HR=1.262, 95% CI 1.122-1.42, p<0.001) and group C (HR=1.251, 95% CI 1.01-1.55, p=0.041) had significantly lower hazard of mortality compared to group A. There was no significant difference in survival between COPD subtypes of chronic bronchitis and emphysema. Patients in Global Initiative for Chronic Obstructive Lung Disease (GOLD) 2 stage had an increased mortality hazard compared to the GOLD 1 stage. CONCLUSIONS: While ischemic stroke patients with preexisting COPD have worse long-term survival than those without COPD, the results largely depended on the definition of COPD used. These results suggest that ischemic stroke patients with COPD need more personalized medical care to decrease long-term mortality.

Social Determinants of Stroke Hospitalization and Mortality in United States' Counties.

(1) Background: Stroke incidence and outcomes are influenced by socioeconomic status. There is a paucity of reported population-level studies regarding these determinants. The goal of this ecological analysis was to determine the county-level associations of social determinants of stroke hospitalization and death rates in the United States. (2) Methods: Publicly available data as of 9 April 2021, for the socioeconomic factors and outcomes, was extracted from the Centers for Disease Control and Prevention. The outcomes of interest were "all stroke hospitalization rates per 1000 Medicare beneficiaries" (SHR) and "all stroke death rates per 100,000 population" (SDR). We used a multivariate binomial generalized linear mixed model after converting the outcomes to binary based on their median values. (3) Results: A total of 3226 counties/county-equivalents of the states and territories in the US were analyzed. Heart disease prevalence (odds ratio, OR = 2.03, p < 0.001), blood pressure medication nonadherence (OR = 2.02, p < 0.001), age-adjusted obesity (OR = 1.24, p = 0.006), presence of hospitals with neurological services (OR = 1.9, p < 0.001), and female head of household (OR = 1.32, p = 0.021) were associated with high SHR while cost of care per capita for Medicare patients with heart disease (OR = 0.5, p < 0.01) and presence of hospitals (OR = 0.69, p < 0.025) were associated with low SHR. Median household income (OR = 0.6, p < 0.001) and park access (OR = 0.84, p = 0.016) were associated with low SDR while no college degree (OR = 1.21, p = 0.049) was associated with high SDR. (4) Conclusions: Several socioeconomic factors (e.g., education, income, female head of household) were found to be associated with stroke outcomes. Additional research is needed to investigate intermediate and potentially modifiable factors that can serve as targeted interventions.

Predictors of Post-Stroke Depression: A Retrospective Cohort Study.

Despite reports of a high incidence and various predictors of post-stroke depression (PSD), the underdiagnosis and undertreatment rates of PSD are still high. This study aimed to examine the incidence of depression in stroke patients and identify factors associated with PSD. This was a retrospective cohort study on ischemic stroke patients from the Geisinger Neuroscience Ischemic Stroke (GNSIS) registry. The following statistical analyses were performed to predict PSD in the studied population: a Kaplan−Meier estimator and a Cox proportional hazards model. A total of 5882 patients were included in the study. The median age at the time of an ischemic stroke was 72 years and 56% were males. A total of 294 patients were diagnosed with PSD within one year of a stroke. The cumulative incidence of depression was found to be 6.4% (95% CI 5.7−7.1%) at one year for the entire cohort. Women were found to have a higher risk of PSD than men (HR for women = 1.47, 95% CI 1.18−1.85, p = 0.001). A history of prior stroke (HR = 1.58, 95% CI 1.18−2.11, p = 0.002) and myocardial infarction (HR = 1.47, 95% CI 1.05−2.06, p = 0.025) were associated with PSD. Medicaid patients had a higher risk for PSD (HR = 2.16, 95% CI 1.5−3.12, p < 0.001) than those with commercial insurance or health maintenance organization plans. Our findings showed that women, patients with a history of prior stroke or myocardial infarction, and with Medicaid insurance were more likely to develop PSD. Through an observational study on the EHR data, we confirmed that chronic stress, including financial and health-related stress, irrespective of age, significantly increased the risk for PSD.

Predicting mortality among ischemic stroke patients using pathways-derived polygenic risk scores.

We aim to determine whether ischemic stroke(IS)-related PRSs are also associated with and further predict 3-year all-cause mortality. 1756 IS patients with European ancestry were randomly split into training (n = 1226) and testing (n = 530) groups with 3-year post-event observations. Univariate Cox proportional hazards regression model (CoxPH) was used for primary screening of individual prognostic PRSs. Only the significantly associated PRSs and clinical risk factors with the same direction for a causal relationship with IS were used to construct a multivariate CoxPH. Feature selection was conducted by the LASSO method. After feature selection, a prediction model with 11 disease-associated pathway-specific PRSs outperformed the base model, as demonstrated by a higher concordance index (0.751, 95%CI [0.693-0.809] versus 0.729, 95%CI [0.676-0.782]) in the testing sample. A PRS derived from endothelial cell apoptosis showed independent predictability in the multivariate CoxPH (Hazard Ratio = 1.193 [1.027-1.385], p = 0.021). These PRSs fine-tuned the model by better stratifying high, intermediate, and low-risk groups. Several pathway-specific PRSs were associated with clinical risk factors in an age-dependent manner and further confirmed some known etiologies of IS and all-cause mortality. In conclusion, Pathway-specific PRSs for IS are associated with all-cause mortality, and the integrated multivariate risk model provides prognostic value in this context.

Comparison of Long-Term Outcomes and Associated Factors between Younger and Older Rural Ischemic Stroke Patients.

Introduction: The rise of ischemic stroke among young adults has stressed the need to understand their risk profiles and outcomes better. This study aimed to examine the five-year ischemic stroke recurrence and survival probability among young patients in rural Pennsylvania. Methods: This retrospective cohort study included first-time ischemic stroke patients from the Geisinger Health System between September 2003 and May 2014. The outcomes included all-cause mortality and ischemic stroke recurrence at five years. Kaplan-Meier estimator, cumulative incidence function, Cox proportional hazards model, and Cause-specific hazard model were used to examine the association of independent variables with the outcomes. Results: A total of 4459 first-time ischemic stroke patients were included in the study, with 664 (14.9%) patients in the 18−55 age group and 3795 (85.1%) patients in the >55 age group. In the 18−55 age group, the five-year survival probability was 87.2%, and the cumulative incidence of recurrence was 8%. Patients in the 18−55 age group had significantly lower hazard for all-cause mortality (HR = 0.37, 95% CI 0.29−0.46, p < 0.001), and non-significant hazard for five-year recurrence (HR = 0.81, 95% CI 0.58−1.12, p = 0.193) compared to the >55 age group. Chronic kidney disease was found to be associated with increased mortality in the 18−55 age group. Conclusion: In our rural population, younger ischemic stroke patients were at the same risk of long-term ischemic stroke recurrence as the older ischemic stroke patients. Identifying the factors and optimizing adequate long-term secondary prevention may reduce the risk of poor outcomes among younger ischemic stroke patients.

A comprehensive review of varicella-zoster virus, herpes simplex virus and cryptococcal infections associated with sphingosine-1-phosphate receptor modulators in multiple sclerosis patients.

Sphingosine-1-phosphate (S1P) receptor modulators are a new class of oral disease-modifying therapies used for Multiple Sclerosis (MS). These are immunomodulatory drugs and can thus increase the risk of certain infections in these patients. This paper summarizes the existing data on the most common opportunistic infections associated with the drugs in this class: Varicella Zoster Virus (VZV), Herpes Simplex Virus (HSV), and Cryptococcus neoformans. A literature review and descriptive analysis of reported cases and clinical phase III study findings on the incidences of these infections were conducted using PubMed and Google Scholar. Results regarding fingolimod, siponimod, ozanimod, and ponesimod were obtained. Overall, the incidence of these infections was found to be extremely low in MS patients treated with S1P receptor modulators. Among the four drugs in this class, the incidence rates of VZV, HSV, and cryptococcal infections were either similar or slightly higher than placebo, with some infections not reported in cases of ozanimod and ponesimod. Most of these resulted in favorable outcomes, with very few disabilities or fatalities. However, this paper highlights the increasing relevance of assessing infectious risk factors to promote the early identification of serious complications related to these drugs. Opportunistic infections should be considered in the differential diagnosis of an MS relapse in the setting of disease-modifying treatment.

Progressive multifocal leukoencephalopathy and sphingosine 1-phosphate receptor modulators used in multiple sclerosis: an updated review of literature.

OBJECTIVE: Progressive multifocal leukoencephalopathy (PML) is a serious viral infection associated with disease-modifying therapies (DMT) for multiple sclerosis (MS) including sphingosine 1-phosphate receptor (S1PR) modulators. The objective of this review was to investigate the characteristics of PML in MS patients associated with drugs of the S1PR modulator. METHODS: We conducted a literature review and analysis of 24 patients from 12 publications in PubMed, SCOPUS and EMBASE. This is a descriptive analysis and study of characteristics of PML associated fingolimod and related S1PR modulator group of DMT. RESULTS: A total of 24 cases of PML in MS patients treated with fingolimod were identified. Of these, 21 cases contained data regarding changes in the expanded disability status scale (EDSS). One case of PML in association with ozanimod treatment in a clinical trial was also identified. In PML cases associated with fingolimod, the mean age at the time of PML diagnosis was 50.91 ± 11.5 years. All patients were treated with fingolimod for more than 24 months. Compared to patients who improved or were stable, in terms of EDSS, after symptomatic management of PML, the non-improved groups were significantly older. There were no fatalities in either group during the reported follow-up period. CONCLUSION: The incidence of PML appears to be extremely low in MS patients treated with S1PR modulators. Risk of PML increases with increase in duration of treatment with S1PR modulators like fingolimod, and increased age at the time of PML diagnosis is associated with worse prognosis.

Imputation of missing values for electronic health record laboratory data.

Laboratory data from Electronic Health Records (EHR) are often used in prediction models where estimation bias and model performance from missingness can be mitigated using imputation methods. We demonstrate the utility of imputation in two real-world EHR-derived cohorts of ischemic stroke from Geisinger and of heart failure from Sutter Health to: (1) characterize the patterns of missingness in laboratory variables; (2) simulate two missing mechanisms, arbitrary and monotone; (3) compare cross-sectional and multi-level multivariate missing imputation algorithms applied to laboratory data; (4) assess whether incorporation of latent information, derived from comorbidity data, can improve the performance of the algorithms. The latter was based on a case study of hemoglobin A1c under a univariate missing imputation framework. Overall, the pattern of missingness in EHR laboratory variables was not at random and was highly associated with patients' comorbidity data; and the multi-level imputation algorithm showed smaller imputation error than the cross-sectional method.

At the Intersection of Gut Microbiome and Stroke: A Systematic Review of the Literature.

Background: Ischemic and hemorrhagic stroke are associated with a high rate of long-term disability and death. Recent investigations focus efforts to better understand how alterations in gut microbiota composition influence clinical outcomes. A key metabolite, trimethylamine N-oxide (TMAO), is linked to multiple inflammatory, vascular, and oxidative pathways. The current biochemical underpinnings of microbial effects on stroke remain largely understudied. The goal of our study is to explore the current literature to explain the interactions between the human gut microbiome and stroke progression, recovery, and outcome. We also provide a descriptive review of TMAO. Methods: A systematic literature search of published articles between January 1, 1990, and March 22, 2020, was performed on the PubMed database to identify studies addressing the role of the microbiome and TMAO in the pathogenesis and recovery of acute stroke. Our initial investigation focused on human subject studies and was further expanded to include animal studies. Relevant articles were included, regardless of study design. The analysis included reviewers classifying and presenting selected articles by study design and sample size in a chart format. Results: A total of 222 titles and abstracts were screened. A review of the 68 original human subject articles resulted in the inclusion of 24 studies in this review. To provide further insight into TMAO as a key player, an additional 40 articles were also reviewed and included. Our findings highlighted that alterations in richness and abundance of gut microbes and increased plasma TMAO play an important role in vascular events and outcomes. Our analysis revealed that restoration of a healthy gut, through targeted TMAO-reducing therapies, could provide alternative secondary prevention for at-risk patients. Discussion: Biochemical interactions between the gut microbiome and inflammation, resulting in metabolic derangements, can affect stroke progression and outcomes. Clinical evidence supports the importance of TMAO in modulating underlying stroke risk factors. Lack of standardization and distinct differences in sample sizes among studies are major limitations.

Lack of Sex Disparity in Oral Anticoagulation in Atrial Fibrillation Patients Presenting with Ischemic Stroke in a Rural Population.

Various studies on oral anticoagulants (OAC) use among atrial fibrillation (AF) patients have shown high rates of undertreatment and the presence of sex disparity. This study used the 'Geisinger Neuroscience Ischemic Stroke' (GNSIS) database to examine sex differences in OAC treatment among ischemic stroke patients with the pre-event diagnosis of AF in rural Pennsylvania between 2004 and 2019. We examined sex disparities in OAC undertreatment and associated risks based on age group and ischemic stroke year. A total of 1062 patients were included in the study and 1015 patients (96%) had CHA2DS2-VASc score ≥ 2, of which 549 (54.1%) were women. Undertreatment rates were not statistically significant between men and women in the overall cohort (50.0% vs. 54.5%, p = 0.18), and male sex was not found to be a significant factor in undertreatment (OR 0.82, 95% CI 0.62-1.09, p = 0.17). The result persisted even when patients were divided into four age groups and two groups based on the study time period. The undertreatment rates in both sex groups remained consistent following the introduction of novel oral anticoagulants. In conclusion, there was no evidence of sex disparity with respect to OAC treatment, even after stratifying the cohort by age and ischemic stroke year.

Predicting short and long-term mortality after acute ischemic stroke using EHR.

OBJECTIVE: Despite improvements in treatment, stroke remains a leading cause of mortality and long-term disability. In this study, we leveraged administrative data to build predictive models of short- and long-term post-stroke all-cause-mortality. METHODS: The study was conducted and reported according to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) guideline. We used patient-level data from electronic health records, three algorithms, and six prediction windows to develop models for post-stroke mortality. RESULTS: We included 7144 patients from which 5347 had survived their ischemic stroke after two years. The proportion of mortality was between 8%(605/7144) within 1-month, to 25%(1797/7144) for the 2-years window. The three most common comorbidities were hypertension, dyslipidemia, and diabetes. The best Area Under the ROC curve(AUROC) was reached with the Random Forest model at 0.82 for the 1-month prediction window. The negative predictive value (NPV) was highest for the shorter prediction windows - 0.91 for the 1-month - and the best positive predictive value (PPV) was reached for the 6-months prediction window at 0.92. Age, hemoglobin levels, and body mass index were the top associated factors. Laboratory variables had higher importance when compared to past medical history and comorbidities. Hypercoagulation state, smoking, and end-stage renal disease were more strongly associated with long-term mortality. CONCLUSION: All the selected algorithms could be trained to predict the short and long-term mortality after stroke. The factors associated with mortality differed depending on the prediction window. Our classifier highlighted the importance of controlling risk factors, as indicated by laboratory measures.

SARS-CoV-2 Is a Culprit for Some, but Not All Acute Ischemic Strokes: A Report from the Multinational COVID-19 Stroke Study Group.

BACKGROUND: SARS-CoV-2 infected patients are suggested to have a higher incidence of thrombotic events such as acute ischemic strokes (AIS). This study aimed at exploring vascular comorbidity patterns among SARS-CoV-2 infected patients with subsequent stroke. We also investigated whether the comorbidities and their frequencies under each subclass of TOAST criteria were similar to the AIS population studies prior to the pandemic. METHODS: This is a report from the Multinational COVID-19 Stroke Study Group. We present an original dataset of SASR-CoV-2 infected patients who had a subsequent stroke recorded through our multicenter prospective study. In addition, we built a dataset of previously reported patients by conducting a systematic literature review. We demonstrated distinct subgroups by clinical risk scoring models and unsupervised machine learning algorithms, including hierarchical K-Means (ML-K) and Spectral clustering (ML-S). RESULTS: This study included 323 AIS patients from 71 centers in 17 countries from the original dataset and 145 patients reported in the literature. The unsupervised clustering methods suggest a distinct cohort of patients (ML-K: 36% and ML-S: 42%) with no or few comorbidities. These patients were more than 6 years younger than other subgroups and more likely were men (ML-K: 59% and ML-S: 60%). The majority of patients in this subgroup suffered from an embolic-appearing stroke on imaging (ML-K: 83% and ML-S: 85%) and had about 50% risk of large vessel occlusions (ML-K: 50% and ML-S: 53%). In addition, there were two cohorts of patients with large-artery atherosclerosis (ML-K: 30% and ML-S: 43% of patients) and cardioembolic strokes (ML-K: 34% and ML-S: 15%) with consistent comorbidity and imaging patterns. Binominal logistic regression demonstrated that ischemic heart disease (odds ratio (OR), 4.9; 95% confidence interval (CI), 1.6-14.7), atrial fibrillation (OR, 14.0; 95% CI, 4.8-40.8), and active neoplasm (OR, 7.1; 95% CI, 1.4-36.2) were associated with cardioembolic stroke. CONCLUSIONS: Although a cohort of young and healthy men with cardioembolic and large vessel occlusions can be distinguished using both clinical sub-grouping and unsupervised clustering, stroke in other patients may be explained based on the existing comorbidities.

Prediction of Long-Term Stroke Recurrence Using Machine Learning Models.

BACKGROUND: The long-term risk of recurrent ischemic stroke, estimated to be between 17% and 30%, cannot be reliably assessed at an individual level. Our goal was to study whether machine-learning can be trained to predict stroke recurrence and identify key clinical variables and assess whether performance metrics can be optimized. METHODS: We used patient-level data from electronic health records, six interpretable algorithms (Logistic Regression, Extreme Gradient Boosting, Gradient Boosting Machine, Random Forest, Support Vector Machine, Decision Tree), four feature selection strategies, five prediction windows, and two sampling strategies to develop 288 models for up to 5-year stroke recurrence prediction. We further identified important clinical features and different optimization strategies. RESULTS: We included 2091 ischemic stroke patients. Model area under the receiver operating characteristic (AUROC) curve was stable for prediction windows of 1, 2, 3, 4, and 5 years, with the highest score for the 1-year (0.79) and the lowest score for the 5-year prediction window (0.69). A total of 21 (7%) models reached an AUROC above 0.73 while 110 (38%) models reached an AUROC greater than 0.7. Among the 53 features analyzed, age, body mass index, and laboratory-based features (such as high-density lipoprotein, hemoglobin A1c, and creatinine) had the highest overall importance scores. The balance between specificity and sensitivity improved through sampling strategies. CONCLUSION: All of the selected six algorithms could be trained to predict the long-term stroke recurrence and laboratory-based variables were highly associated with stroke recurrence. The latter could be targeted for personalized interventions. Model performance metrics could be optimized, and models can be implemented in the same healthcare system as intelligent decision support for targeted intervention.

SARS-CoV-2 and Stroke Characteristics: A Report From the Multinational COVID-19 Stroke Study Group.

[Figure: see text].

Adherence to anticoagulant guideline for atrial fibrillation: A large care gap among stroke patients in a rural population.

OBJECTIVE: This study aimed to investigate the prevalence and factors associated with oral anticoagulant undertreatment of atrial fibrillation (AF) among a cohort of rural patients with stroke outcomes and examine how undertreatment may influence a patient's one-year survival after stroke. METHODS: This retrospective cohort study examined ischemic stroke patients with pre-stroke AF diagnosis from September 2003 to May 2019 and divided them into proper treatment and undertreatment group. Analysis included chi-square test, variance analysis, Kruskal-Wallis test, logistic regression, Kaplan-Meier estimator, and Cox proportional-hazards model. RESULTS: Out of 1062 ischemic stroke patients with a pre-stroke AF diagnosis, 1015 patients had a CHA2DS2-VASc score ≥2, and 532 (52.4%) of those were undertreated. Median time from AF diagnosis to index stroke was significantly lower among undertreated patients (1.9 years vs. 3.6 years, p < 0.001). Other thromboembolism, excluding stroke, TIA, and myocardial infarction (OR 0.41, p < 0.001), the number of encounters per year (OR 0.90, p < 0.001), and the median time between AF diagnosis and stroke event (OR 0.86, p < 0.001) were negatively associated with undertreatment. Kaplan-Meier estimator showed no statistical difference in the one-year survival probability between groups (log-rank test, p = 0.29), while the Cox-Hazard model showed that age (HR 1.05, p < 0.001) and history of congestive heart failure (HR 1.88, p < 0.001) increased the risk of mortality. CONCLUSIONS: More than half of our rural stroke patients with a pre-index AF diagnosis were not on guideline-recommended treatment. The study highlights a large care gap and an opportunity to improve AF management.