Abstract WP368: Evaluation of Brain Regional Characteristics Related With Post-Stroke Delirium Using Machine Learning and Statistical Analysis

Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Seo Hyun Lee ◽  
Yun Kyong Hyon ◽  
Hee Won Yang ◽  
Ki Wan Jeon ◽  
Ki Wan Jeon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ischemic Stroke ◽  
Statistical Analysis ◽  
Acute Ischemic Stroke ◽  
Cerebral Hemisphere ◽  
Support Vector ◽  
Stroke Patients ◽  
Regional Characteristics ◽  
Post Stroke ◽  
The Brain

Background: The present study was performed to evaluate the brain regional characteristics related with development of post-stroke delirium using the machine learning and statistical analysis. Method: We used clinical and radiological data prospectively collected from 675 acute ischemic stroke patients, who were admitted in stroke unit from August 2017 to July 2018. Delirium occurrence in the patients was screened with Confusion Assessment Method and finally diagnosed using the criteria of the Diagnostic and Statistical Manual of Mental Disorders (fifth edition). Three machine learning models, Support Vector Machine (SVM), Random Forest (RF) and Tree-based Gradient Boosting (XGBoost), were applied for the prediction of post-stroke delirium with the clinical and radiologic data. And logistic regression analysis was performed to evaluate the significance of the brain regional parameters included in the importance features which were obtained from the XGBoost result. Results: Post-stroke delirium occurred in 66 (9.8%) of the total patients. On the comparison of the test accuracy to predict delirium occurrence, RF (94%), XGBoost test (93%), and SVM (89%) showed similar prediction rates. Of the brain regional parameters included in the top 30 feature importance, right side cerebral hemisphere, non-lacunar infarction, severity of periventricular white matter changes, acute temporal lobe lesion, cerebellum, brain stem, and previous lesions developed on right side cerebral hemisphere, and in temporal or frontal lobe. Conclusion: The present study shows that the brain regional characteristics related with the post-stroke delirium are shown to be significant when controlling the other features using statistical analysis with machine learning. Even though we need more studies to validate the relationships between post-stroke delirium and brain regional characteristics, the present brain regional characteristics could provide significant evidences to predict post-stroke delirium for the acute ischemic stroke patients.

Abstract P390: Prediction Enhancement of the Post-Stroke Delirium by Adding of the Brain Lesional Characteristics to the Clinical Features in Acute Ischemic Stroke Patients

Stroke ◽  
2021 ◽  
Vol 52 (Suppl_1) ◽  
Author(s):  
Hye Seon Jeong ◽  
Hee Won Yang ◽  
Seo Hyun Lee ◽  
Yun Kyong Hyon ◽  
Kiwan Jeon ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Clinical Features ◽  
Foley Catheter ◽  
Assessment Method ◽  
Periventricular White Matter ◽  
Operating Characteristics ◽  
Stroke Patients ◽  
Post Stroke ◽  
The Brain

Background: We evaluated whether the brain regional features could enhance the prediction of the occurrence of the post-stroke delirium along with consideration of clinical features in acute ischemic stroke patients. Method: We analyzed magnetic resonance imaging and clinical datasets prospectively collected from 1,024 acute ischemic stroke patients (620 men; mean age±SD, 70.2±11.8 years), who were admitted in stroke unit. Delirium occurrence in the patients was initially screened with Confusion Assessment Method and finally diagnosed using the criteria of the Diagnostic and Statistical Manual of Mental Disorders (fifth edition). The prediction performance of the clinical features was evaluated using the logistic regression analysis, and then, compared with the performance obtained after adding of the brain lesional features. Results: Post-stroke delirium occurred in 100 (9.8%) of the total patients. Independent features of the clinical features were old age (odds ratio [OR] for the delirium prediction: 1.07, 95% confidence interval [CI] 1.038-1.103), preexisting dementia (OR 0.423, CI 0.209-0.853) and atrial fibrillation OR 1.599, CI 0.938-2.726), neglect (OR 2.395, CI 1.152-4.976), visual defect (OR 2.209, CI 0.994-4.907), diplopia (OR 2.42, CI 1.021-5.738), dysuria (OR 2.404, 95% CI 1.155-5.000), Foley catheter insertion (OR 0.46, CI 0.24-0.881) and pneumonia (OR 1.954, CI 1.004-3.803). Right-sided hemispheric and mixed acute lesions (p=0.003), lesion locations in occipital lobe (OR 1.814, CI 0.923-3.564), cerebellum (OR 2.875, CI 1.32-6.258) and brainstem (OR 4.057, CI 1.714-9.601), and the presence of the periventricular white matter change (OR 1.321, CI 0.964-1.811) increased the risk for delirium. Sensitivity to predict the delirium of the regression model was enhanced from 10% obtained with the clinical features to 18% by adding the brain lesional features. Area under the curve of the receiver operating characteristics analysis was also enhanced from 0.827 with the clinical features to 0.847 after adding the brain lesions to the clinical features. Conclusion: The present study shows brain lesional characteristics that could enhance the prediction of the post-stroke delirium in acute ischemic stroke patients.

Abstract TP274: Orosomucoid-1 Protein Increases Following Ischemic Stroke in the Brain and Periphery

Stroke ◽  
2016 ◽  
Vol 47 (suppl_1) ◽  
Author(s):  
Hetal Mistry ◽  
Madeline Levy ◽  
Meaghan Roy-O'Reilly ◽  
Louise McCullough
Keyword(s):  
Sex Differences ◽  
Ischemic Stroke ◽  
Rna Sequencing ◽  
Multiple Testing ◽  
Enzyme Linked Immunosorbent Assay ◽  
Mrna Levels ◽  
Stroke Patients ◽  
Post Stroke ◽  
Protein Levels ◽  
The Brain

Background and Purpose: Orosomucoid-1 (ORM-1) is an abundant protein with important roles in inflammation and immunosuppression. We utilized RNA sequencing to measure mRNA levels in human ischemic stroke patients, with confirmation by serum ORM-1 protein measurements. A mouse model of ischemic stroke was then used to examine post-stroke changes in ORM-1 within the brain itself. Hypothesis: We tested the hypothesis that ORM-1 levels increase following ischemic stroke, with sex differences in protein dynamics over time. Methods: RNA sequencing was performed on whole blood from ischemic stroke patients (n=23) and controls (n=12), with Benjamini-Hochberg correction for multiple testing. Enzyme-linked immunosorbent assay was performed on serum from ischemic stroke patients (n=28) and controls (n=8), with analysis by T-test. For brain analysis, mice (n=14) were subjected to a 90-minute middle cerebral artery occlusion (MCAO) surgery and sacrificed 6 or 24 hours after stroke. Control mice underwent parallel “sham” surgery without occlusion. Western blotting was used to detect ORM-1 protein levels in whole brain, with analysis by two-way ANOVA. Results: RNA sequencing showed a 2.8-fold increase in human ORM-1 at 24 hours post-stroke (q=.0029), an increase also seen in serum ORM-1 protein levels (p=.011). Western blot analysis of mouse brain revealed that glycosylated (p=0.0003) and naive (p=0.0333) forms of ORM-1 were higher in female mice compared to males 6 hours post-stroke. Interestingly, ORM-1 levels were higher in the brains of stroke mice at 6 hours (p=.0483), while at 24 hours ORM-1 levels in stroke mice were lower than their sham counterparts (p=.0212). In both human and mouse data, no sex differences were seen in ORM-1 levels in the brain or periphery at 24 hours post-stroke. Conclusion: In conclusion, ORM-1 is a sexually dimorphic protein involved in the early (<24 hour) response to ischemic stroke. This research serves as an initial step in determining the mechanism of ORM-1 in the ischemic stroke response and its potential as a future therapeutic target for both sexes.

Abstract TP224: Interleukin-37 Level is Elevated in Acute Ischemic Stroke

Stroke ◽  
2017 ◽  
Vol 48 (suppl_1) ◽  
Author(s):  
Saif Bushnaq ◽  
Atif Zafar ◽  
Kempuraj Duraisamy ◽  
Nudrat Tasneem ◽  
Mohammad M Khan ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Inflammatory Responses ◽  
Enzyme Linked Immunosorbent Assay ◽  
Control Group ◽  
Delayed Presentation ◽  
Stroke Patients ◽  
Post Stroke ◽  
Urine And Serum ◽  
Serum And Urine

Background: Interleukin-37 (IL-37) is a new member of IL-1 cytokine family with a defined role as a negative feedback inhibitor of pro-inflammatory responses. IL-37 has yet to be evaluated in non-immune neurological diseases like ischemic or hemorrhagic stroke. This study aimed to measure the urine and serum IL-37 levels in patients with acute ischemic stroke. Method: Twelve patients consented for the study. Two sets of serum and urine samples were obtained and analyzed; one upon admission to the hospital, and the second the next morning after overnight fasting. The trends in serum level of IL-37 in 5 stroke patients, while trends in urine level of 6 patients were available, measured by real-time polymerase chain reaction (RT-PCR) and enzyme-linked immunosorbent assay (ELISA). Prior studies with healthy volunteers as control group have consistently showed IL-37 plasma level around or less than 65 pg/ml with maximum normal levels on ELISA approximated at 130 pg/ml. Results: IL-37 level in urine in stroke patients ranged from 297 - 4467. IL-37 levels were in the range of 300s to 1000s in patients with ischemic stroke compared with reported healthy controls in literature where the level was always less than 90. Three of these 10 patients presented within 3 hours of stroke onset with IL-37 serum levels being 2655 pg/ml, 3517 pg/ml and 5235 pg/ml. In all others, it ranged much less than that, with the trend of delayed presentation giving less IL-37 levels, both in urine and serum. There were no clear differences found in patients with or without tPA, diabetes, hyperlipidemia and high blood pressure in our small study. Conclusion: The study shows a rather stable elevation of IL-37 levels post-ischemic stroke, which if compared to available data from other studies, is 3-10 times elevated after acute ischemic stroke with an uptrend in the first few days. IL-37 plays some role in mediating post-stroke inflammation with significant rise in serum and urine IL-37 levels suggesting a key role of this novel cytokine in post-stroke pathology. This is the first ever reported study measuring and trending IL-37 levels in human plasma after an acute ischemic stroke.

Abstract TP215: Machine Learning Analysis of Gene Expression Data and Predictive Stroke Outcomes in Acute Ischemic Stroke

Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Sarah R Martha ◽  
Qiang Cheng ◽  
Liyu Gong ◽  
Lisa Collier ◽  
Stephanie Davis ◽  
...  
Keyword(s):  
Gene Expression ◽  
Machine Learning ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Mechanical Thrombectomy ◽  
Stroke Patients ◽  
Stroke Outcomes ◽  
Inflammatory Genes ◽  
Patient Demographics ◽  
Edema Volume

Background and Purpose: The ability to predict ischemic stroke outcomes in the first day of admission could be vital for patient counseling, rehabilitation, and care planning. The Blood and Clot Thrombectomy Registry and Collaboration (BACTRAC; clinicaltrials.gov NCT03153683) collects blood samples distal and proximal to the intracranial thrombus during mechanical thrombectomy. These samples are a novel resource in evaluating acute gene expression changes at the time of ischemic stroke. The purpose of this study was to identify inflammatory genes and patient demographics that are predictive of stroke outcomes (infarct and/or edema volume) in acute ischemic stroke patients. Methods: The BACTRAC study is a non-probability, convenience sampling of subjects (≥ 18 year olds) treated with mechanical thrombectomy for emergent large vessel occlusion. We evaluated relative concentrations of mRNA for gene expression in 84 inflammatory molecules in static blood distal and proximal to the intracranial thrombus from adults who underwent thrombectomy. We employed a machine learning method, Random Forest, utilizing the first set of enrolled subjects, to predict which inflammatory genes and patient demographics were important features for infarct and edema volumes. Results: We analyzed the first 28 subjects (age = 66 ± 15.48, 11 males) in the BACTRAC registry. Results from machine learning analyses demonstrate that the genes CCR4, IFNA2, IL9, CXCL3, Age, DM, IL7, CCL4, BMI, IL5, CCR3, TNF, and IL27 predict infarct volume. The genes IFNA2, IL5, CCL11, IL17C, CCR4, IL9, IL7, CCR3, IL27, DM, and CSF2 predict edema volume. There is an intersection of genes CCR4, IFNA2, IL9, IL7, IL5, CCR3 to both infarct and edema volumes. Overall, these genes depicts a microenvironment for chemoattraction and proliferation of autoimmune cells, particularly Th2 cells and neutrophils. Conclusions: Machine learning algorithms can be employed to develop predictive biomarker signatures for stroke outcomes in ischemic stroke patients, particularly in regard to identifying acute gene expression changes that occur during stroke.

Abstract NS2: Effect of Volume-Viscosity Swallow Test (V-VST) in Acute Ischemic Stroke Patients With Dysphagia: A Hospital-Based Case-Control Study

Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Ting Ye ◽  
Yi Dong ◽  
Shengyan Huang
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Case Control Study ◽  
Tube Feeding ◽  
Case Control ◽  
Stroke Patients ◽  
Post Intervention ◽  
Post Stroke ◽  
Volume Viscosity ◽  
Control Study

Background: The dysphagia screening in acute ischemic stroke plays an important role in patients with risk of dysphagia. The aim of this hospital-based case-control study is to explore if V-VST, as a new nurse-driven dysphagia screening tool for AIS patients, might help to reduce the rate of post-stroke pneumonia and early withdraw of feeding tube. Methods: 1598 acute ischemic stroke patients were enrolled in this study. The standard protocol in AIS patients were assessed by WST (before intervention and plus with V-VST after intervention). The V-VST assessment were be trained in two senior nurses and all AIS patients were assessed by V-VST during July 1and Dec 30 th , 2017. Among 299 AIS patients with suspected, all clinical data were analyzed. The comparison of their rate of pneumonia in hospital and withdraw rate of tubefeeding before discharge were performed between patients post-intervention (January 1, 2018-June 30, 2019)and those admitted before the intervention (January 1, 2016-June 30, 2017). Results: The baseline characteristics of the pre- and post- intervention AIS groups were similar in age, gender, NIHSS. The implementation of V-VST have a statistically significant reducing the risk of pneumonia with an adjusted HR (0.60, 95% CI 0.43-0.84, P=0.003). Additionally, follow-up V-VST were likely to be associated the withdraw rate of tube-feeding at discharge (29/168 vs 38/131 P=0.016).There is also a trend of length of tube-feeding decreasing (8.32±12.27 vs 6.84±8.61 P=0.241). Conclusion: In our study, the V-VST is a feasible bedside tool. The implemental might be associated with the reduction of post-stroke pneumonia. Therefore, it meets the requirements of a clinical screening test for dysphagia in acute stroke patients at bedside. Large prospective interventional study is needed to confirm our findings. V-VST: Volume-viscosity Swallow Test WST: Water Swallow Test AIS: Acute Ischemic Stroke HR: hazard ratio

Abstract WMP23: Automated ASPECTS Scoring of CT Scans for Acute Ischemic Stroke Patients Using Machine Learning

Stroke ◽  
2018 ◽  
Vol 49 (Suppl_1) ◽  
Author(s):  
Hulin Kuang ◽  
Ericka Teleg ◽  
Mohamed Najm ◽  
Alexis T Wilson ◽  
Sung I Sohn ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Ct Scans ◽  
Stroke Patients

scholarly journals Serum lipid profiles and post-stroke depression in acute ischemic stroke patients

2019 ◽  
Vol Volume 15 ◽  
pp. 1573-1583 ◽  
Author(s):  
Huiping Shen ◽  
Xinjie Tu ◽  
Xiaoqian Luan ◽  
Yaying Zeng ◽  
Jincai He ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Serum Lipid ◽  
Lipid Profiles ◽  
Stroke Patients ◽  
Post Stroke ◽  
Post Stroke Depression

scholarly journals Effect of Hypokalemia on Functional Outcome at 3 Months Post-Stroke Among First-Ever Acute Ischemic Stroke Patients

2017 ◽  
Vol 23 ◽  
pp. 2825-2832 ◽  
Author(s):  
Fan Gao ◽  
Cheng-Tai Wang ◽  
Chen Chen ◽  
Xing Guo ◽  
Li-Hong Yang ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Functional Outcome ◽  
Stroke Patients ◽  
Post Stroke

scholarly journals Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea

Diagnostics ◽  
2021 ◽  
Vol 11 (10) ◽  
pp. 1909
Author(s):  
Dougho Park ◽  
Eunhwan Jeong ◽  
Haejong Kim ◽  
Hae Wook Pyun ◽  
Haemin Kim ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Functional Outcome ◽  
Outcome Prediction ◽  
Prediction Models ◽  
Gradient Boosting ◽  
Support Vector ◽  
Extreme Gradient Boosting

Background: Functional outcomes after acute ischemic stroke are of great concern to patients and their families, as well as physicians and surgeons who make the clinical decisions. We developed machine learning (ML)-based functional outcome prediction models in acute ischemic stroke. Methods: This retrospective study used a prospective cohort database. A total of 1066 patients with acute ischemic stroke between January 2019 and March 2021 were included. Variables such as demographic factors, stroke-related factors, laboratory findings, and comorbidities were utilized at the time of admission. Five ML algorithms were applied to predict a favorable functional outcome (modified Rankin Scale 0 or 1) at 3 months after stroke onset. Results: Regularized logistic regression showed the best performance with an area under the receiver operating characteristic curve (AUC) of 0.86. Support vector machines represented the second-highest AUC of 0.85 with the highest F1-score of 0.86, and finally, all ML models applied achieved an AUC > 0.8. The National Institute of Health Stroke Scale at admission and age were consistently the top two important variables for generalized logistic regression, random forest, and extreme gradient boosting models. Conclusions: ML-based functional outcome prediction models for acute ischemic stroke were validated and proven to be readily applicable and useful.

scholarly journals Treatment Efficacy Analysis in Acute Ischemic Stroke Patients Using In Silico Modeling Based on Machine Learning: A Proof-of-Principle

Biomedicines ◽  
2021 ◽  
Vol 9 (10) ◽  
pp. 1357
Author(s):  
Anthony Winder ◽  
Matthias Wilms ◽  
Jens Fiehler ◽  
Nils D. Forkert
Keyword(s):  
Machine Learning ◽  
Ischemic Stroke ◽  
Treatment Group ◽  
Acute Ischemic Stroke ◽  
In Silico ◽  
Mechanical Thrombectomy ◽  
Intravenous Thrombolysis ◽  
Stroke Patients ◽  
New Devices

Interventional neuroradiology is characterized by engineering- and experience-driven device development with design improvements every few months. However, clinical validation of these new devices requires lengthy and expensive randomized controlled trials. This contribution proposes a machine learning-based in silico study design to evaluate new devices more quickly with a small sample size. Acute diffusion- and perfusion-weighted MRI, segmented one-week follow-up imaging, and clinical variables were available for 90 acute ischemic stroke patients. Three treatment option-specific random forest models were trained to predict the one-week follow-up lesion segmentation for (1) patients successfully recanalized using intra-arterial mechanical thrombectomy, (2) patients successfully recanalized using intravenous thrombolysis, and (3) non-recanalizing patients as an analogue for conservative treatment for each patient in the sample, independent of the true group membership. A repeated-measures analysis of the three predicted follow-up lesions for each patient revealed significantly larger lesions for the non-recanalizing group compared to the successful intravenous thrombolysis treatment group, which in turn showed significantly larger lesions compared to the successful mechanical thrombectomy treatment group (p < 0.001). A groupwise comparison of the true follow-up lesions for the three treatment options showed the same trend but did not reach statistical significance (p = 0.19). We conclude that the proposed machine learning-based in silico trial design leads to clinically feasible results and can support new efficacy studies by providing additional power and potential early intermediate results.

Sign in / Sign up

Export Citation Format

Share Document