MRI-based Algorithm for Acute Ischemic Stroke Subtype Classification

Background and Purpose— In Japan, nearly half of ischemic stroke patients receive edaravone for acute treatment. The purpose of this study was to assess the effect of edaravone on neurological symptoms in patients with ischemic stroke stratified by stroke subtype. Methods— Study subjects were 61 048 patients aged 18 years or older who were hospitalized ≤14 days after onset of an acute ischemic stroke and were registered in the Japan Stroke Data Bank, a hospital-based multicenter stroke registration database, between June 2001 and July 2013. Patients were stratified according to ischemic stroke subtype (large-artery atherosclerosis, cardioembolism, small-vessel occlusion, and cryptogenic/undetermined) and then divided into 2 groups (edaravone-treated and no edaravone). Neurological symptoms were evaluated using the National Institutes of Health Stroke Scale (NIHSS). The primary outcome was changed in neurological symptoms during the hospital stay (ΔNIHSS=NIHSS score at discharge−NIHSS score at admission). Data were analyzed using multivariate linear regression with inverse probability of treatment weighting after adjusting for the following confounding factors: age, gender, and systolic and diastolic blood pressure at the start of treatment, NIHSS score at admission, time from stroke onset to hospital admission, infarct size, comorbidities, concomitant medication, clinical department, history of smoking, alcohol consumption, and history of stroke. Results— After adjusting for potential confounders, the improvement in NIHSS score from admission to discharge was greater in the edaravone-treated group than in the no edaravone group for all ischemic stroke subtypes (mean [95% CI] difference in ΔNIHSS: −0.46 [−0.75 to −0.16] for large-artery atherosclerosis, −0.64 [−1.09 to −0.2] for cardioembolism, and −0.25 [−0.4 to −0.09] for small-vessel occlusion). Conclusions— For any ischemic stroke subtype, edaravone use (compared with no use) was associated with a greater improvement in neurological symptoms, although the difference was small (<1 point NIHSS) and of limited clinical significance.

Download Full-text

Relationship between augmentation index and acute ischemic stroke subtype

Journal of Clinical Neuroscience ◽

10.1016/j.jocn.2013.10.032 ◽

2014 ◽

Vol 21 (7) ◽

pp. 1220-1224 ◽

Cited By ~ 3

Author(s):

Dae Sup Byun ◽

Sang Won Han ◽

Joong Hyun Park ◽

Jeong Yeon Kim ◽

Jong Sam Baik ◽

...

Keyword(s):

Ischemic Stroke ◽

Acute Ischemic Stroke ◽

Augmentation Index ◽

Stroke Subtype ◽

Ischemic Stroke Subtype

Download Full-text

Association of Prestroke Glycemic Control With Vascular Events During 1-Year Follow-up

Neurology ◽

10.1212/wnl.0000000000012729 ◽

2021 ◽

pp. 10.1212/WNL.0000000000012729

Author(s):

Jun Young Chang ◽

Wook-Joo Kim ◽

Jee Hyun Kwon ◽

Ji Sung Lee ◽

Beom Joon Kim ◽

...

Keyword(s):

Myocardial Infarction ◽

Ischemic Stroke ◽

Acute Ischemic Stroke ◽

Multivariable Analysis ◽

Large Artery ◽

Stroke Subtype ◽

Vascular Events ◽

Vascular Death ◽

Ischemic Stroke Subtype

ObjectiveWe evaluated the association between admission HbA1c and subsequent risk of composite vascular events, including stroke, myocardial infarction, and vascular death, in patients with acute ischemic stroke and diabetes.MethodsPatients who had a transient ischemic attack or an acute ischemic stroke within 7 days of symptom onset, and diabetes were included in a retrospective cohort design using the stroke registry of the Clinical Research Center for Stroke in Korea. The association between admission HbA1c and composite vascular events, including stroke, myocardial infarction (MI), and vascular death, during one-year follow-up was estimated using the Fine-Gray model. The risk of composite vascular events according to the ischemic stroke subtype was explored using fractional polynomial and linear-quadratic models.ResultsOf the 18567 patients, 1437 developed composite vascular events during follow-up. In multivariable analysis using HbA1c as a categorical variable, the risk significantly increased at a threshold of 6.8%–7.0%. The influence of admission HbA1c level on the risk of composite vascular events was pronounced particularly among those in whom fasting glucose at admission was ≤130 mg/dL. The optimal ranges of the HbA1c associated with minimal risks for composite vascular events was the lowest for the small vessel occlusion subtype (6.6, [95% confidence internal [CI], 6.3–6.9]), compared to the large artery atherosclerosis (7.3 [95% CI, 6.8–7.9]) or the cardioembolic subtype (7.4[95% CI, 6.3–8.5]).ConclusionIn patients with ischemic stroke and diabetes, the risks of composite vascular events were significantly associated with admission HbA1c. The optimal range of the admission HbA1c was below 6.8%–7.0%, and were different according to the ischemic stroke subtype.

Download Full-text

Automating Ischemic Stroke Subtype Classification Using Machine Learning and Natural Language Processing

Journal of Stroke and Cerebrovascular Diseases ◽

10.1016/j.jstrokecerebrovasdis.2019.02.004 ◽

2019 ◽

Vol 28 (7) ◽

pp. 2045-2051 ◽

Cited By ~ 20

Author(s):

Ravi Garg ◽

Elissa Oh ◽

Andrew Naidech ◽

Konrad Kording ◽

Shyam Prabhakaran

Keyword(s):

Machine Learning ◽

Ischemic Stroke ◽

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Stroke Subtype ◽

Subtype Classification ◽

Ischemic Stroke Subtype

Download Full-text

Abstract T P101: Low Serum Eicosapentaenoic Acid- Arachidonic Acid Ratio is Associated With Intracranial Stenosis in Patients With Acute Ischemic Stroke

Stroke ◽

10.1161/str.45.suppl_1.tp101 ◽

2014 ◽

Vol 45 (suppl_1) ◽

Author(s):

Yuko Abe ◽

Ryoichi Otsubo ◽

Sho Murase ◽

Kenichiro Nakazawa ◽

Kazuo Kitagawa

Keyword(s):

Risk Factors ◽

Arachidonic Acid ◽

Ischemic Stroke ◽

Eicosapentaenoic Acid ◽

Acute Ischemic Stroke ◽

Artery Stenosis ◽

Intracranial Artery ◽

Stroke Subtype ◽

Fa Composition ◽

Intracranial Artery Stenosis

Purpose: A low ratio of serum eicosapentaenoic acid to arachidonic acid (EPA/AA) has been associated with atherosclerotic disease. Few studies investigate the association of serum fatty acid (FA) composition with the acute ischemic stroke so far. Our aim of this study is to evaluate the relationships between FA composition and stroke subtypes, extra-/intracranial atherosclerotic stenoses, and other cerebrovascular indicators Methods: This study included 154 consecutive patients who were admitted to our hospital because of acute ischemic stroke between April 2011 and March 2012. We examined the FA composition and classical vascular risk factors. We conducted brain MRI/MRA, carotid ultrasonogram, transthoracic echocardiogram, 24hr Holter electrocardiogram, ankle brachial index (ABI) and pulse wave velocity (PWV) in order to evaluate the severity of atherosclerotic change, stroke subtype, and cardiovascular status. Results: The mean value of EPA/AA was 0.33±0.22 in all patients with acute cerebral infarction. The 154 patients in this study (mean age 71 years) were categorized as follows; large artery atherosclerosis (LA; n=57), small artery occlusion (SA; n=48), cardiogenic embolism (CE; n=18), and others (n=31). We found intracranial artery stenosis greater than 50% in 70 patients (45%). The intracranial artery stenosis was associated with low EPA/AA ratio (P=0.013) and low EPA concentration (P=0.013). This association remained significant (P<0.05) after controlling for classical atherosclerotic risk factors. We could not find a significant correlation between FA composition and stroke subtype. However, there was a tendency for the EPA/AA ratio of LA patients to be the lowest among all subtype groups. The EPA/AA ratio was not associated with ABI, PWV, prevalence of arrhythmia, or cardiac function. Conclusions: A low EPA/AA ratio was significantly associated with intracranial stenosis in patients with acute ischemic stroke. This study shows the EPA/AA ratio might be an important marker to reflect the cerebral artery stenosis.

Download Full-text

Medication Adherence of Statin Users after Acute Ischemic Stroke

European Neurology ◽

10.1159/000493530 ◽

2018 ◽

Vol 80 (1-2) ◽

pp. 106-114 ◽

Cited By ~ 6

Author(s):

Pil-Wook Chung ◽

Byung-Woo Yoon ◽

Yeong-Bae Lee ◽

Byoung-Soo Shin ◽

Hahn Young Kim ◽

...

Keyword(s):

Ischemic Stroke ◽

Medication Adherence ◽

Acute Ischemic Stroke ◽

Multiple Logistic Regression Analysis ◽

Statin Treatment ◽

Stroke Severity ◽

Large Artery ◽

Stroke Subtype ◽

Modifiable Factors ◽

Statin Adherence

Although statins are established therapy for the secondary prevention of ischemic stroke, factors associated with adherence to statin treatment following ischemic stroke are not well known. To address this, we assessed the 6-month statin adherence using 8-item Morisky Medication Adherence Scale-8 in patients with acute ischemic stroke. Of 991 patients, 65.6% were adherent to statin at 6-month after discharge. Multiple logistic regression analysis showed that patients’ awareness of hyperlipidemia (OR 1.62; 95% CI 1.07–2.43), large artery stroke subtype (versus non-large artery stroke, OR 1.79; 95% CI 1.19–2.68), and alcohol drinking habits (OR 1.64; 95% CI 1.06–2.53) were positively associated, while high statin dose (versus low dose, OR 0.6; 95% CI 0.40–0.90) and higher daily number of medication pills (OR 0.93; 95% CI 0.88–0.97) were found to have a negative association with self-reported good adherence to statin medication after acute ischemic stroke. However, stroke severity and diagnosis of hyperlipidemia were not associated with adherence. These results suggest that educational and motivational interventions may enhance statin adherence because modifiable factors were associated with statin adherence.

Download Full-text

Neurologic deterioration in patients with acute ischemic stroke or transient ischemic attack

Neurology ◽

10.1212/wnl.0000000000010603 ◽

2020 ◽

Vol 95 (16) ◽

pp. e2178-e2191

Author(s):

Tai Hwan Park ◽

Jeong-Kon Lee ◽

Moo-Seok Park ◽

Sang-Soon Park ◽

Keun-Sik Hong ◽

...

Keyword(s):

Ischemic Stroke ◽

Acute Ischemic Stroke ◽

Prospective Observational Study ◽

Stroke Onset ◽

Large Artery ◽

Stroke Subtype ◽

Relative Risks ◽

Neurologic Deterioration ◽

Early Arrival ◽

Ischemic Attack

ObjectiveTo improve epidemiologic knowledge of neurologic deterioration (ND) in patients with acute ischemic stroke (AIS).MethodsIn this prospective observational study, we captured ND prospectively in 29,446 patients with AIS admitted to 15 hospitals in Korea within 7 days of stroke onset. ND was defined as an increase in NIH Stroke Scale (NIHSS) score ≥2 (total), or ≥1 (motor or consciousness), or any new neurologic symptoms. Change in incidence rate after stroke onset, causes, factors associated with ND, modified Rankin Scale (mRS) score at 3 months and 1 year, and a composite of stroke, myocardial infarction, and all-cause death at 1 year were assessed.ResultsND occurred in 4,299 (14.6%) patients. The highest rate, 6.95 per 1,000 person-hours incidence, was within the first 6 hours, which decreased to 2.09 within 24–48 hours, and 0.66 within 72–96 hours after stroke onset. Old age, female sex, diabetes, early arrival, large artery atherosclerosis as a stroke subtype, high NIHSS scores, glucose level, systolic blood pressure, leukocytosis at admission, recanalization therapy, TIA without a relevant lesion, and steno-occlusion of relevant arteries were associated with ND. The causes were stroke progression (71.8%) followed by recurrence (8.5%). Adjusted relative risks (95% CI) for poor outcome (mRS 3–6) at 3 months and 1 year were 1.75 (1.70–1.80) and 1.70 (1.65–1.75), respectively. The adjusted hazard ratio (95% CI) for the composite event was 1.59 (1.45–1.74).ConclusionsND should be taken into consideration as a factor that may influence the outcome in acute ischemic stroke.

Download Full-text

Five-year readmission and mortality differ by ischemic stroke subtype

Journal of the Neurological Sciences ◽

10.1016/j.jns.2019.06.007 ◽

2019 ◽

Vol 403 ◽

pp. 31-37 ◽

Cited By ~ 1

Author(s):

Anna Therese Bjerkreim ◽

Andrej Netland Khanevski ◽

Lars Thomassen ◽

Henriette Aurora Selvik ◽

Ulrike Waje-Andreassen ◽

...

Keyword(s):

Ischemic Stroke ◽

Stroke Subtype ◽

Ischemic Stroke Subtype

Download Full-text

Interpretable CNN for ischemic stroke subtype classification with active model adaptation

BMC Medical Informatics and Decision Making ◽

10.1186/s12911-021-01721-5 ◽

2022 ◽

Vol 22 (1) ◽

Author(s):

Shuo Zhang ◽

Jing Wang ◽

Lulu Pei ◽

Kai Liu ◽

Yuan Gao ◽

...

Keyword(s):

Ischemic Stroke ◽

Selection Criterion ◽

Fine Tuning ◽

Data Types ◽

Stroke Subtype ◽

Subtype Classification ◽

Active Selection ◽

Sequential Experiments ◽

Evaluation Metric ◽

Toast Classification

Abstract Background TOAST subtype classification is important for diagnosis and research of ischemic stroke. Limited by experience of neurologist and time-consuming manual adjudication, it is a big challenge to finish TOAST classification effectively. We propose a novel active deep learning architecture to classify TOAST. Methods To simulate the diagnosis process of neurologists, we drop the valueless features by XGB algorithm and rank the remaining ones. Utilizing active learning framework, we propose a novel causal CNN, in which it combines with a mixed active selection criterion to optimize the uncertainty of samples adaptively. Meanwhile, KL-focal loss derived from the enhancement of Focal loss by KL regularization is introduced to accelerate the iterative fine-tuning of the model. Results To evaluate the proposed method, we construct a dataset which consists of totally 2310 patients. In a series of sequential experiments, we verify the effectiveness of each contribution by different evaluation metrics. Experimental results show that the proposed method achieves competitive results on each evaluation metric. In this task, the improvement of AUC is the most obvious, reaching 77.4. Conclusions We construct a backbone causal CNN to simulate the neurologist process of that could enhance the internal interpretability. The research on clinical data also indicates the potential application value of this model in stroke medicine. Future work we would consider various data types and more comprehensive patient types to achieve fully automated subtype classification.

Download Full-text