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.

Background and purpose: Obesity is an established risk factor for ischemic stroke but the association of increased body mass index (BMI) with survival after ischemic stroke remains controversial. Many studies have shown that increased BMI has a “protective” effect on survival after stroke while other studies have debunked the “obesity paradox”. This study aimed at examining the relationship between BMI and all-cause mortality at one year in first-time ischemic stroke patients using a large dataset extracted from different resources including electronic health records. Methods: This was a retrospective cohort study of consecutive ischemic stroke patients captured in our Geisinger NeuroScience Ischemic Stroke (GNSIS) database. Survival in first-time ischemic stroke patients in different BMI categories was analyzed using Kaplan Meier survival curves. The predictors of mortality at one-year were assessed using a stratified Cox proportional hazards model. Results: Among 6,703 first-time ischemic stroke patients, overweight and obese patients were found to have statistically decreased hazard ratio (HR) compared to the non-overweight patients (overweight patients- HR = 0.61 [95% CI, 0.52–0.72]; obese patients- HR = 0.56 [95% CI, 0.48–0.67]). Predictors with a significant increase in the hazard ratio for one-year mortality were age at the ischemic stroke event, history of neoplasm, atrial fibrillation/flutter, diabetes, myocardial infarction and heart failure. Conclusion: Our study results support the obesity paradox in ischemic stroke patients as shown by a significantly decreased hazard ratio for one-year mortality among overweight and obese patients in comparison to non-overweight patients.

(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.

Objective To determine whether the polygenic risk score (PRS) derived from MEGASTROKE is associated with ischemic stroke (IS) and its subtypes in an independent tertiary health care system and to identify the PRS derived from gene sets of known biological pathways associated with IS. Methods Controls (n = 19,806/7,484, age ≥69/79 years) and cases (n = 1,184/951 for discovery/replication) of acute IS with European ancestry and clinical risk factors were identified by leveraging the Geisinger Electronic Health Record and chart review confirmation. All Geisinger MyCode patients with age ≥69/79 years and without any stroke-related diagnostic codes were included as low risk control. Genetic heritability and genetic correlation between Geisinger and MEGASTROKE (EUR) were calculated using the summary statistics of the genome-wide association study by linkage disequilibrium score regression. All PRS for any stroke (AS), any ischemic stroke (AIS), large artery stroke (LAS), cardioembolic stroke (CES), and small vessel stroke (SVS) were constructed by PRSice-2. Results A moderate heritability (10%–20%) for Geisinger sample as well as the genetic correlation between MEGASTROKE and the Geisinger cohort was identified. Variation of all 5 PRS significantly explained some of the phenotypic variations of Geisinger IS, and the R² increased by raising the cutoff for the age of controls. PRSLAS, PRSCES, and PRSSVS derived from low-frequency common variants provided the best fit for modeling (R² = 0.015 for PRSLAS). Gene sets analyses highlighted the association of PRS with Gene Ontology terms (vascular endothelial growth factor, amyloid precursor protein, and atherosclerosis). The PRSLAS, PRSCES, and PRSSVS explained the most variance of the corresponding subtypes of Geisinger IS suggesting shared etiologies and corroborated Geisinger TOAST subtyping. Conclusions We provide the first evidence that PRSs derived from MEGASTROKE have value in identifying shared etiologies and determining stroke subtypes.

BACKGROUND AND PURPOSE: Current stroke care recommendations for patient selection for mechanical thrombectomy in the extended time window demand advanced imaging to determine the stroke core volume and hypoperfusion mismatch, which may not be available at every center. We aimed to determine outcomes in patients selected for mechanical thrombectomy solely on the basis of noncontrast CT and CTA in the early (<6-hour) and extended (≥6-hour) time windows. MATERIALS AND METHODS: Consecutive mechanical thrombectomies performed for acute large-vessel occlusion ischemic (ICA, M1, M2) stroke between February 2016 and August 2020 were retrospectively reviewed. Eligibility was based solely on demographics and noncontrast CT (ASPECTS) and CTA, due to the limited availability of perfusion imaging during the study period. Propensity score matching was performed to compare outcomes between time windows. RESULTS: Of 417 mechanical thrombectomies performed, 337 met the inclusion criteria, resulting in 205 (60.8%) and 132 (39.2%) patients in the 0- to 6- and 6- to 24-hour time windows, respectively. The ASPECTS was higher in the early time window (9; interquartile range = 8–10) than the extended time window (9; interquartile range = 7–10; P = .005). Propensity score matching yielded 112 well-matched pairs. Equal rates of TICI 2b/3 revascularization and symptomatic intracranial hemorrhage were observed. A favorable functional outcome (mRS 0–2) at 90 days was numerically more frequent in the early window (45.5% versus 33.9%, P = .091). Mortality was numerically more frequent in the early window (25.9% versus 17.0%, P = .096). CONCLUSIONS: Patients selected for mechanical thrombectomy in the extended time window solely on the basis of noncontrast CT and CTA still achieved decent rates of favorable 90-day functional outcomes, not statistically different from patients in the early time window.