Predicting cerebrovascular age and its clinical relevance: Modeling using 3D morphological features of brain vessels.

Aging manifests as many phenotypes, among which age-related changes in brain vessels are important, but underexplored. Thus, in the present study, we constructed a model to predict age using cerebrovascular morphological features, further assessing their clinical relevance using a novel pipeline. Age prediction models were first developed using data from a normal cohort (n = 1181), after which their relevance was tested in two stroke cohorts (n = 564 and n = 455). Our novel pipeline adapted an existing framework to compute generic vessel features for brain vessels, resulting in 126 morphological features. We further built various machine learning models to predict age using only clinical factors, only brain vessel features, and a combination of both. We further assessed deviation from healthy aging using the age gap and explored its clinical relevance by correlating the predicted age and age gap with various risk factors. The models constructed using only brain vessel features and those combining clinical factors with vessel features were better predictors of age than the clinical factor-only model (r = 0.37, 0.48, and 0.26, respectively). Predicted age was associated with many known clinical factors, and the associations were stronger for the age gap in the normal cohort. The age gap was also associated with important factors in the pooled cohort atherosclerotic cardiovascular disease risk score and white matter hyperintensity measurements. Cerebrovascular age, computed using the morphological features of brain vessels, could serve as a potential individualized marker for the early detection of various cerebrovascular diseases.

Global intracranial arterial tortuosity is associated with intracranial atherosclerotic burden.

The effect of arterial tortuosity on intracranial atherosclerosis (ICAS) is not well understood. This study aimed to evaluate the effect of global intracranial arterial tortuosity on intracranial atherosclerotic burden in patients with ischemic stroke. We included patients with acute ischemic stroke who underwent magnetic resonance angiography (MRA) and classified them into three groups according to the ICAS burden. Global tortuosity index (GTI) was defined as the standardized mean curvature of the entire intracranial arteries, measured by in-house vessel analysis software. Of the 516 patients included, 274 patients had no ICAS, 140 patients had a low ICAS burden, and 102 patients had a high ICAS burden. GTI increased with higher ICAS burden. After adjustment for age, sex, vascular risk factors, and standardized mean arterial area, GTI was independently associated with ICAS burden (adjusted odds ratio [adjusted OR] 1.33; 95% confidence interval [CI] 1.09-1.62). The degree of association increased when the arterial tortuosity was analyzed limited to the basal arteries (adjusted OR 1.48; 95% CI 1.22-1.81). We demonstrated that GTI is associated with ICAS burden in patients with ischemic stroke, suggesting a role for global arterial tortuosity in ICAS.

Incidence and risk of stroke in Korean patients with congenital heart disease.

OBJECTIVES: The incidence and risk of ischemic stroke (IS) and hemorrhagic stroke (HS) in Korean patients with CHD have not been reported, therefore, we aimed to investigate this. MATERIALS AND METHODS: Participants were selected from the Korean National Health Insurance Service benefit records from 2006-2017. Cases were extracted using diagnosis codes related to CHD. Controls without CHD were selected through age- and sex-matched random sampling at a 1:10 ratio. RESULTS: The case and control groups included 232,203 and 3,024,633 participants, respectively. The median (interquartile range) follow-up period was 7.28 (3.59-8.73) years. The incidence rates of IS and HS per 100,000 person-years were much higher in cases than in controls (IS: 135 vs. 47; HS: 41.7 vs. 24.9). After adjusting for confounders, CHD was a risk factor for IS and HS (subdistribution HR; 1.96 and 1.71, respectively). In patients with CHD, the following risk factors were identified: diabetes, heart failure, and atrial fibrillation for any stroke; hypertension, atrial septal defects, and use of antiplatelet agents for IS only; and coronary artery bypass graft surgery for HS only. CONCLUSIONS: Korean patients with CHD have a high risk of stroke. A personalized preventive approach is needed to reduce the incidence of stroke in this population.

Imaging and clinical predictors of acute constipation in patients with acute ischemic stroke.

Background: Constipation symptoms are highly prevalent in acute ischemic stroke, but the clinical and neuroimaging predictors are unknown. This study aimed to identify lesions and clinical features associated with acute constipation. Methods: Data from patients with acute ischemic stroke registered in a hospital-based stroke registry between January 2018 and December 2019 were analyzed. Clinical, laboratory, and imaging features were examined for associations with acute constipation. Using the topographic lesion on diffusion-weighted images, multivariate support vector regression-based lesion-symptom mapping (SVR-LSM) was conducted and compared between the non-constipation and acute constipation groups. Results: A total of 256 patients (mean age 67 years, men: 64%) were included. Acute constipation was noted in 81 patients (32%). Initial stroke severity, represented by initial National Institutes of Health and Stroke Scale (NIHSS) scores, was associated with acute constipation. Laboratory parameters, including fibrin degradation products (FDP), fibrinogen, D-dimer, lipoprotein (a), and free fatty acid levels, also showed statistically significant differences between the non-constipation and constipation groups. FDP, D-dimer, and free fatty acid levels were independently associated with acute constipation in the logistic regression model after adjusting for initial NIHSS scores and potassium levels. SVR-LSM revealed that bilateral lesions in the precentral gyrus, insula, opercular part of the inferior frontal gyrus, the inferior parietal lobule, and lesions in the right middle frontal gyrus were significantly associated with acute constipation. The results were consistent after controlling for the initial NIHSS scores and poststroke potassium levels. When cardioembolic stroke subjects were excluded, the right insular and prefrontal cortex lesions lost their association with acute constipation. Conclusion: Acute constipation symptoms after acute ischemic stroke are mainly related to bilateral lesions in the insula, precentral gyrus, postcentral gyrus, and inferior parietal lobule. Clinically important predictors of acute constipation include initial neurological severity and thromboembolic markers of stroke.

The effect of intensive statin therapy in non-symptomatic intracranial arteries: The STAMINA-MRI sub-study.

Background and aims: Pleiotropic effects of statins result in the stabilization of symptomatic intracranial arterial plaque. However, little is known about the effect of statins in non-symptomatic cerebral arteries. We hypothesized that intensive statin therapy could produce a change in the non-symptomatic cerebral arteries. Methods: This is a sub-study of a prospective observational study under the title of "Intensive Statin Treatment in Acute Ischemic Stroke Patients with Intracranial Atherosclerosis: a High-Resolution Magnetic Resonance Imaging (HR-MRI) study." Patients with statin-naive acute ischemic stroke who had symptomatic intracranial artery stenosis (above 50%) were recruited for this study. HR-MRI was performed to assess the patients' cerebral arterial status before and 6 months after the statin therapy. To demonstrate the effect of statins in the non-symptomatic segment of intracranial cerebral arteries, we excluded symptomatic segments from the data to be analyzed. We compared the morphological changes using cerebrovascular morphometry. Results: A total of 54 patients (mean age: 62.9 ± 14.4 years, 59.3% women) were included in this study. Intensive statin therapy produced significant morphological changes of overall cerebral arteries. Among the morphological features, the arterial luminal area showed the highest number of significant changes with a range from 5.7 and 6.7%. Systolic blood pressure (SBP) was an independent factor associated with relative changes in posterior circulation bed maximal diameter percentage change (beta -0.21, 95% confidence interval -0.36 to -0.07, p = 0.005). Conclusion: Intensive statin therapy produced a favorable morphological change in cerebral arteries of not only the target arterial segment but also non-symptomatic arterial segments. The change in cerebral arterial luminal diameter was influenced by the baseline SBP and was dependent on the topographic distribution of the cerebral arteries.Clinical Trial Registration: ClinicalTrials.gov, identifier NCT02458755.

Automated in-depth cerebral arterial labelling using cerebrovascular vasculature reframing and deep neural networks.

Identifying the cerebral arterial branches is essential for undertaking a computational approach to cerebrovascular imaging. However, the complexity and inter-individual differences involved in this process have not been thoroughly studied. We used machine learning to examine the anatomical profile of the cerebral arterial tree. The method is less sensitive to inter-subject and cohort-wise anatomical variations and exhibits robust performance with an unprecedented in-depth vessel range. We applied machine learning algorithms to disease-free healthy control subjects (n = 42), patients with stroke with intracranial atherosclerosis (ICAS) (n = 46), and patients with stroke mixed with the existing controls (n = 69). We trained and tested 70% and 30% of each study cohort, respectively, incorporating spatial coordinates and geometric vessel feature vectors. Cerebral arterial images were analyzed based on the 'segmentation-stacking' method using magnetic resonance angiography. We precisely classified the cerebral arteries across the exhaustive scope of vessel components using advanced geometric characterization, redefinition of vessel unit conception, and post-processing algorithms. We verified that the neural network ensemble, with multiple joint models as the combined predictor, classified all vessel component types independent of inter-subject variations in cerebral arterial anatomy. The validity of the categorization performance of the model was tested, considering the control, ICAS, and control-blended stroke cohorts, using the area under the receiver operating characteristic (ROC) curve and precision-recall curve. The classification accuracy rarely fell outside each image's 90-99% scope, independent of cohort-dependent cerebrovascular structural variations. The classification ensemble was calibrated with high overall area rates under the ROC curve of 0.99-1.00 [0.97-1.00] in the test set across various study cohorts. Identifying an all-inclusive range of vessel components across controls, ICAS, and stroke patients, the accuracy rates of the prediction were: internal carotid arteries, 91-100%; middle cerebral arteries, 82-98%; anterior cerebral arteries, 88-100%; posterior cerebral arteries, 87-100%; and collections of superior, anterior inferior, and posterior inferior cerebellar arteries, 90-99% in the chunk-level classification. Using a voting algorithm on the queued classified vessel factors and anatomically post-processing the automatically classified results intensified quantitative prediction performance. We employed stochastic clustering and deep neural network ensembles. Ma-chine intelligence-assisted prediction of vessel structure allowed us to personalize quantitative predictions of various types of cerebral arterial structures, contributing to precise and efficient decisions regarding the cerebrovascular disease.

Major Adverse Cardiovascular Events in Korean Congenital Heart Disease Patients: A Nationwide Age- and Sex-Matched Case-Control Study.

PURPOSE: Congenital heart disease (CHD) is a known risk factor for acquired cardiovascular and cerebrovascular diseases. However, available evidence on CHD is limited mostly to Western populations. This study aimed to evaluate the prevalence of vascular events and all-cause mortality in Korean patients with CHD and to further corroborate CHD as a predictor of vascular events and all-cause mortality. MATERIALS AND METHODS: The claims data of the Korean National Health Insurance Service (NHIS) were retrospectively reviewed. Information regarding diagnostic codes, comorbidities, medical services, income level, and residential area was also collected. Outcomes of interest included stroke, myocardial infarction (MI), all-cause mortality, and major adverse cardiovascular events (MACE). RESULTS: We included 232203 patients with CHD and 3024633 individuals without CHD as a control group through age- and sex-matched 1:10 random sampling. The prevalences of hypertension, congestive heart failure, ischemic heart disease, hyperlipidemia, and atrial fibrillation were significantly higher in the CHD group, which had a more than two-fold higher incidence of vascular events and all-cause mortality, than in the group without CHD. Multivariable models demonstrated that CHD was a significant risk factor for stroke, MI, all-cause mortality, and MACE. CONCLUSION: In conclusion, this nationwide study demonstrates that Korean patients with CHD have a high incidence of comorbidities, vascular events, and mortality. CHD has been established as an important predictor of cardiovascular events. Further studies are warranted to identify high-risk patients with CHD and related factors to prevent vascular events.