Cerebral Microbleeds in an Acute Ischemic Stroke as a Predictor of Hemorrhagic Transformation

Neuro-imaging in intracerebral hemorrhage: updates and knowledge gaps

Intracerebral hemorrhage (ICH) is characterized by hematoma development within the brain's parenchyma, contributing significantly to the burden of stroke. While non-contrast head computed tomography (CT) remains the gold standard for initial diagnosis, this review underscores the pivotal role of magnetic resonance imaging (MRI) in ICH management. Beyond diagnosis, MRI offers invaluable insights into ICH etiology, prognosis, and treatment. Utilizing echo-planar gradient-echo or susceptibility-weighted sequences, MRI demonstrates exceptional sensitivity and specificity in identifying ICH, aiding in differentiation of primary and secondary causes. Moreover, MRI facilitates assessment of hemorrhage age, recognition of secondary lesions, and evaluation of perihematomal edema progression, thus guiding tailored therapeutic strategies. This comprehensive review discusses the multifaceted utility of MRI in ICH management, highlighting its indispensable role in enhancing diagnostic accuracy as well as aiding in prognostication. As MRI continues to evolve as a cornerstone of ICH assessment, future research should explore its nuanced applications in personalized care paradigms.

Predictive Values of the CHA2DS2-VASc Score and Left Atrial Diameter for Cerebral Small Vessel Disease in Geriatric Patients With Atrial Fibrillation

Objective The objective of this study was to determine whether the CHA2DS2-VASc (congestive heart failure, hypertension, age, diabetes mellitus, stroke, vascular disease, age, sex) score and left atrial diameter (LAD) could predict the presence of cerebral small vessel disease (cSVD) in patients older than 65 years with atrial fibrillation as the cause of ischemic stroke. Materials and methods In this study, we included patients over 65 years of age who had suffered an ischemic stroke caused by atrial fibrillation within 30 days after the onset of symptoms. The data recorded included demographics, electrocardiograms, Holter monitors, and echocardiography reports. The anteroposterior LAD, determined by transthoracic echocardiography, was analyzed. Each patient's CHA2DS2-VASc score was calculated. Brain magnetic resonance imaging (MRI) assessed white matter hyperintensities (WMH) on fluid-attenuated inversion recovery (FLAIR) images and cerebral microbleeds (CMBs) on susceptibility-weighted sequences. The Fazekas score, based on WMH on MRI, was used to grade the severity of gliosis. Participants were categorized into three groups according to their quantitative CMB burden. Findings The study included 60 participants, with a mean age of 80 years (range 65-99), and 43.3% (n = 26) were male. The CHA2DS2-VASc score had a mean value of 4.21 (range 2-8), and the mean LAD was 4.17 (range 2.6-5.3) cm. The CHA2DS2-VASc score did not predict CMBs (OR, 1.389; 95% CI, 0.961-2.008, p = 0.08) in geriatric stroke patients with atrial fibrillation. However, in the subgroup of patients with diabetes mellitus, the CHA2DS2-VASc score was higher in those with CMB 1-4 and CMB ≥ 5 than in those without CMB. Additionally, the risk of CMBs 1-4 increased with higher LAD compared to patients without LAD. Conclusion The LAD and CHA2DS2-VASc scores were not significantly associated with CMB prediction in elderly stroke patients with atrial fibrillation. In a diabetes mellitus subgroup, the CHA2DS2-VASc score was indicative of CMB. An increased LAD elevates the risk of CMBs in patients with coronary artery disease.

Machine learning approach for hemorrhagic transformation prediction: Capturing predictors' interaction

Background and purpose

Patients with ischemic stroke frequently develop hemorrhagic transformation (HT), which could potentially worsen the prognosis. The objectives of the current study were to determine the incidence and predictors of HT, to evaluate predictor interaction, and to identify the optimal predicting models.

Methods

A prospective study included 360 patients with ischemic stroke, of whom 354 successfully continued the study. Patients were subjected to thorough general and neurological examination and T2 diffusion-weighted MRI, at admission and 1 week later to determine the incidence of HT. HT predictors were selected by a filter-based minimum redundancy maximum relevance (mRMR) algorithm independent of model performance. Several machine learning algorithms including multivariable logistic regression classifier (LRC), support vector classifier (SVC), random forest classifier (RFC), gradient boosting classifier (GBC), and multilayer perceptron classifier (MLPC) were optimized for HT prediction in a randomly selected half of the sample (training set) and tested in the other half of the sample (testing set). The model predictive performance was evaluated using receiver operator characteristic (ROC) and visualized by observing case distribution relative to the models' predicted three-dimensional (3D) hypothesis spaces within the testing dataset true feature space. The interaction between predictors was investigated using generalized additive modeling (GAM).

Results

The incidence of HT in patients with ischemic stroke was 19.8%. Infarction size, cerebral microbleeds (CMB), and the National Institute of Health stroke scale (NIHSS) were identified as the best HT predictors. RFC (AUC: 0.91, 95% CI: 0.85-0.95) and GBC (AUC: 0.91, 95% CI: 0.86-0.95) demonstrated significantly superior performance compared to LRC (AUC: 0.85, 95% CI: 0.79-0.91) and MLPC (AUC: 0.85, 95% CI: 0.78-0.92). SVC (AUC: 0.90, 95% CI: 0.85-0.94) outperformed LRC and MLPC but did not reach statistical significance. LRC and MLPC did not show significant differences. The best models' 3D hypothesis spaces demonstrated non-linear decision boundaries suggesting an interaction between predictor variables. GAM analysis demonstrated a linear and non-linear significant interaction between NIHSS and CMB and between NIHSS and infarction size, respectively.

Conclusion

Cerebral microbleeds, NIHSS, and infarction size were identified as HT predictors. The best predicting models were RFC and GBC capable of capturing nonlinear interaction between predictors. Predictor interaction suggests a dynamic, rather than, fixed cutoff risk value for any of these predictors.

Cerebral Microbleed Burden in Ischemic Stroke Patients on Aspirin: Prospective Cohort of Intracranial Hemorrhage

Objective: This investigation aimed at studying the prevalence of cerebral microbleeds (CMBs), including risk factors and the correlation of CMBs to ischemic stroke (IS) patient end results.

Methods: Four hundred and fifty-nine acute IS cases were recruited between April 2014 and December 2016. Cerebral microbleeds were analyzed using susceptibility-weighted imaging (SWI) brain MRI scan. The enrolled patients with acute IS were followed up for 12–24 months, with a median follow-up time of 19 months. The follow-up endpoint events including recurrent ischemic stroke (RIS), intracranial hemorrhage (ICH), transient ischemic attack (TIA), mortality, and cardiovascular events. The associations between vascular risk factors and CMBs in IS patients were analyzed using univariate and multivariate logistic regression analysis. Cox regression model was employed for evaluating CMB impact on clinical outcome.

Results: Among 459 enrolled patients, 187 (40.7%) had CMBs and 272 (59.2%) had no CMB. In comparison with patients with no CMBs, age was higher and hypertension was more frequent in patients with CMBs. Multivariate logistic regression analyses revealed age and hypertension were independently associated with the presence of CMBs. Among the patient cohort, 450 cases completed the follow-up. During the follow-up period, 22 (4.9%) of patients developed ICH, 12 (2.7%) developed TIA, 68 (15.1%) developed RIS, cardiovascular events occurred in 20 (4.44%), and 13 (2.89%) cases were mortalities. Compared with patients without CMBs, IS patients with CMBs have an increased prevalence of ICH (p < 0.05). However, no statistically valid variations regarding other outcome incidences between both groups was identified (p > 0.05). The incidence of ICH was elevated in tandem with elevations in number of CMBs. Following adjusting for age, multivariate Cox proportional-hazards regression analysis revealed that CMBs ≥10 were independent predictors of ICH in acute IS patients.

Conclusion: Age and hypertension are independently associated with the presence of CMBs. Intracranial hemorrhage incidence rate was increased with the number of CMBs, and the number of CMBs ≥10 were independent predictors of ICH in acute stroke patients.