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.

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.

Abstract P506: Machine Learning Models Improve Prediction of Large Vessel Occlusion and Mechanical Thrombectomy Candidacy in Acute Ischemic Stroke

Stroke ◽  
2021 ◽  
Vol 52 (Suppl_1) ◽  
Author(s):  
Shon Thomas ◽  
Paula De La Pena ◽  
Liam Butler ◽  
Oguz Akbilgic ◽  
Daniel Heiferman ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ischemic Stroke ◽  
Random Forest ◽  
Acute Ischemic Stroke ◽  
Predictive Value ◽  
Mechanical Thrombectomy ◽  
Demographic Variables ◽  
Large Vessel ◽  
Stroke Patients ◽  
Forest Model

Background and Purpose: Early identification of large vessel occlusions (LVO) and timely recanalization are paramount in improved clinical outcomes in acute ischemic stroke. Multiple simple stroke scales have good sensitivity, but compromise specificity for predicting LVO. No scale has been shown to predict mechanical thrombectomy (MT) candidacy. Machine learning techniques are being used for predictive modeling in many aspects of stroke care and may have potential in predicting LVO presence and MT candidacy. Methods: 287 acute ischemic stroke patients from July 2018 to July 2019 at Loyola University Medical Center were included. 36 clinical and demographic variables were analyzed using machine learning and statistical algorithms, including logistic regression, extreme gradient boosting, random forest, and decision trees to build models predictive of LVO and MT. The best performing model was compared with prior stroke scales. Results: Random forest based model resulted in the highest classification performance to predict both LVO and MT outcomes with an area under the curve (AUC) of 0.90±0.07 and 0.94±0.04, respectively. When the predictors were reduced to 7, random forest maintained a high AUC for predicting LVO (0.89). When reduced to 10 predictors, the random forest model predicted MT with an AUC = 0.93. Random forest models had excellent sensitivity and specificity of 0.86 and 0.89 for LVO and 0.89 and 0.95 for MT, respectively. The negative predictive value was 0.94 for LVO and 0.98 for MT while the positive predictive value was 0.77 for LVO and 0.79 for MT. With equal sensitivity, the random forest model was favorable to all previous stroke scales. Conclusion: Machine learning utilizing clinical and demographic variables predicts LVO and patient candidacy for MT with a high degree of accuracy. Further validation of this strategy for triage of stroke patients requires prospective and external validation.

scholarly journals Dysphagia in Patients with Acute Ischemic Stroke: Early Dysphagia Screening May Reduce Stroke-Related Pneumonia and Improve Stroke Outcomes

2016 ◽  
Vol 42 (1-2) ◽  
pp. 81-89 ◽  
Author(s):  
Mohamed Al-Khaled ◽  
Christine Matthis ◽  
Andreas Binder ◽  
Jonas Mudter ◽  
Joern Schattschneider ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Case Fatality ◽  
National Institutes Of Health ◽  
Modified Rankin Scale ◽  
Stroke Patients ◽  
Stroke Outcomes ◽  
Increased Risk ◽  
Reduced Risk

Background: Dysphagia is associated with poor outcome in stroke patients. Studies investigating the association of dysphagia and early dysphagia screening (EDS) with outcomes in patients with acute ischemic stroke (AIS) are rare. The aims of our study are to investigate the association of dysphagia and EDS within 24 h with stroke-related pneumonia and outcomes. Methods: Over a 4.5-year period (starting November 2007), all consecutive AIS patients from 15 hospitals in Schleswig-Holstein, Germany, were prospectively evaluated. The primary outcomes were stroke-related pneumonia during hospitalization, mortality, and disability measured on the modified Rankin Scale ≥2-5, in which 2 indicates an independence/slight disability to 5 severe disability. Results: Of 12,276 patients (mean age 73 ± 13; 49% women), 9,164 patients (74%) underwent dysphagia screening; of these patients, 55, 39, 4.7, and 1.5% of patients had been screened for dysphagia within 3, 3 to <24, 24 to ≤72, and >72 h following admission. Patients who underwent dysphagia screening were likely to be older, more affected on the National Institutes of Health Stroke Scale score, and to have higher rates of neurological symptoms and risk factors than patients who were not screened. A total of 3,083 patients (25.1%; 95% CI 24.4-25.8) had dysphagia. The frequency of dysphagia was higher in patients who had undergone dysphagia screening than in those who had not (30 vs. 11.1%; p < 0.001). During hospitalization (mean 9 days), 1,271 patients (10.2%; 95% CI 9.7-10.8) suffered from stroke-related pneumonia. Patients with dysphagia had a higher rate of pneumonia than those without dysphagia (29.7 vs. 3.7%; p < 0.001). Logistic regression revealed that dysphagia was associated with increased risk of stroke-related pneumonia (OR 3.4; 95% CI 2.8-4.2; p < 0.001), case fatality during hospitalization (OR 2.8; 95% CI 2.1-3.7; p < 0.001) and disability at discharge (OR 2.0; 95% CI 1.6-2.3; p < 0.001). EDS within 24 h of admission appeared to be associated with decreased risk of stroke-related pneumonia (OR 0.68; 95% CI 0.52-0.89; p = 0.006) and disability at discharge (OR 0.60; 95% CI 0.46-0.77; p < 0.001). Furthermore, dysphagia was independently correlated with an increase in mortality (OR 3.2; 95% CI 2.4-4.2; p < 0.001) and disability (OR 2.3; 95% CI 1.8-3.0; p < 0.001) at 3 months after stroke. The rate of 3-month disability was lower in patients who had received EDS (52 vs. 40.7%; p = 0.003), albeit an association in the logistic regression was not found (OR 0.78; 95% CI 0.51-1.2; p = 0.2). Conclusions: Dysphagia exposes stroke patients to a higher risk of pneumonia, disability, and death, whereas an EDS seems to be associated with reduced risk of stroke-related pneumonia and disability.

Acute intracranial stenting with mechanical thrombectomy is safe and efficacious in patients diagnosed with underlying intracranial atherosclerotic disease

2021 ◽  
pp. 159101992110394
Author(s):  
Ameer E Hassan ◽  
Victor M Ringheanu ◽  
Laurie Preston ◽  
Wondwossen G Tekle ◽  
Adnan I Qureshi
Keyword(s):  
Ischemic Stroke ◽  
Length Of Stay ◽  
Intracerebral Hemorrhage ◽  
Cerebral Infarction ◽  
Acute Ischemic Stroke ◽  
Mechanical Thrombectomy ◽  
Modified Rankin Scale ◽  
Stroke Patients ◽  
Intracranial Stenting ◽  
Intracranial Atherosclerotic Disease

Objective To investigate whether significant differences exist in recanalization rates and primary outcomes between patients who undergo mechanical thrombectomy alone versus those who undergo mechanical thrombectomy with acute intracranial stenting. Methods Through the utilization of a prospectively collected endovascular database at a comprehensive stroke center between 2012 and 2020, variables such as demographics, co-morbid conditions, symptomatic intracerebral hemorrhage, mortality rate at discharge, and good/poor outcomes in regard to modified thrombolysis in cerebral infarction score and modified Rankin Scale were examined. The outcomes between patients receiving acute intracranial stenting + mechanical thrombectomy and patients that underwent mechanical thrombectomy alone were compared. Results There were a total of 420 acute ischemic stroke patients who met criteria for the study (average age 70.6 ± 13.01 years; 46.9% were women). Analysis of 46 patients from the acute stenting + mechanical thrombectomy group (average age 70.34 ± 13.75 years; 37.0% were women), and 374 patients from the mechanical thrombectomy alone group (average age 70.64 ± 12.92 years; 48.1% were women). Four patients (8.7%) in the acute stenting + mechanical thrombectomy group experienced intracerebral hemorrhage versus 45 patients (12.0%) in the mechanical thrombectomy alone group ( p = 0.506); no significant increases were noted in the median length of stay (7 vs 8 days; p = 0.208), rates of modified thrombolysis in cerebral infarction 2B-3 recanalization ( p = 0.758), or good modified Rankin Scale scores ( p = 0.806). Conclusion Acute intracranial stenting in addition to mechanical thrombectomy was not associated with an increase in overall length of stay, intracerebral hemorrhage rates, or any change in discharge modified Rankin Scale. Further research is required to determine whether mechanical thrombectomy and acute intracranial stenting in acute ischemic stroke patients is unsafe.

116 Effect of Annual Hospital Procedure Volume on Outcomes After Mechanical Thrombectomy in Acute Ischemic Stroke Patients

Neurosurgery ◽  
2016 ◽  
Vol 63 ◽  
pp. 149 ◽  
Author(s):  
Vishal B. Jani ◽  
Chiu Yuen To ◽  
Achint Patel ◽  
Prashant S. Kelkar ◽  
Boyd Richards ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Mechanical Thrombectomy ◽  
Stroke Patients ◽  
Procedure Volume

scholarly journals Anestezijos metodo reikšmė pacientų, sergančių ūminiu išeminiu insultu ir gydytų mechanine trombektomija, ankstyvai neurologinei būklei Relevance of anaesthesia type on early neurological outcome in acute ischemic stroke patients undergoing mechanical thrombectomy

2019 ◽  
Vol 22 (78) ◽  
pp. 325-329
Author(s):  
L. Šalaševičius ◽  
A. Vilionskis
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Neurological Outcome ◽  
Mechanical Thrombectomy ◽  
Stroke Patients

Įvadas. Sąmonės sedacija (SS) ir bendroji endotrachėjinė anestezija (BETA) – anestezijos metodai, taikomi mechaninės trombektomijos (MTE) metu. Tikslių rekomendacijų dėl anestezijos metodo pasirinkimo MTE metu nėra. Retrospektyviniai tyrimai teigia, kad BETA yra susijusi su blogesnėmis pacientų išeitimis, tačiau naujuose klinikiniuose tyrimuose tokio skirtumo nestebima. Darbo tikslas buvo nustatyti anestezijos metodo įtaką mechaninės trombektomijos efektyvumui ir saugumui ligoniams, patyrusiems ūminį išeminį insultą. Tiriamieji ir tyrimo metodai. Į tyrimą įtraukti dviejuose Vilniaus centruose gydyti ūminį išeminį insultą patyrę ligoniai, kuriems buvo atlikta MTE. Ligoniai suskirstyti į 2 grupes pagal taikytą anestezijos metodą: bendroji endotrachėjinė anestezija (BETA) ir sąmonės sedacija (SS). Abiejose grupėse vertinti demografiniai, klinikiniai ir logistiniai rodikliai. Pirminiu vertinimo kriterijumi pasirinkta gera baigtis po 24 valandų. MTE saugumas vertintas pagal 7 parų mirštamumą ir simptominių intrasmegeninių kraujosruvų (sISK) dažnį. Rezultatai. Į tyrimą įtraukta 248 pacientai. 105 pacientams (42,3 %) taikyta BETA ir 143 (57,7 %) – SS. Pagal pradines charakteristikas abi grupės statistiškai nesiskyrė, išskyrus prieširdžių virpėjimo dažnį (55,9 % – SS vs 37,1 % – BETA grupėje, p = 0,003) ir intraveninės trombolizės taikymą iki MTE (66,4 % – SS grupėje ir 46,7 % – BETA grupėje, p = 0,003). Gera baigtis po 24 val. nustatyta 51,4 % (n = 54) ligonių – BETA grupėje ir 58,7 % (n = 84) ligonių – SS grupėje (p = 0,252). 7 parų mirštamumo sISK dažnis abiejose grupėse statistiškai reikšmingai nesiskyrė. Regresinė analizė parodė, kad geros baigties nepriklausomi prognoziniai veiksniai yra laikas nuo atvykimo į stacionarą iki rekanalizacijos ir sėkminga rekanalizacija. Išvados. Anestezijos tipas nėra reikšmingas mechaninės trombektomijos efektyvumo ir saugumo veiksnys ankstyvai pacientų baigčiai. Siekiant tiksliau įvertinti anestezijos reikšmę mechaninės trombektomijos baigčiai ir nustatyti procedūros baigties prognozinius veiksnius, reikalingi papildomi atsitiktinės atrankos tyrimai.

Abstract TP52: Endovascular Therapy in Patients Over 80 Years of Age With Acute Ischemic Stroke

Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Janhavi M Modak ◽  
Syed Daniyal Asad ◽  
Jussie Lima ◽  
Amre Nouh ◽  
Ilene Staff ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Symptom Onset ◽  
Time Window ◽  
Extended Time ◽  
Stroke Patients ◽  
Stroke Outcomes ◽  
Stroke Treatment ◽  
Group A ◽  
Group B

Introduction: Acute ischemic stroke treatment has undergone a paradigm shift, with patients being treated in the extended time window (6-24 hours post symptom onset). The purpose of this study is to assess outcomes in stroke patients above 80 years of age undergoing endovascular treatment (EVT) in the extended time window. Methods: Acute ischemic stroke patients presenting to Hartford Hospital between January 2017 to June 2019 were considered for the study. Stroke outcomes in patients above 80 years of age with anterior circulation ischemic strokes presenting in the extended time window (Group A, n=30) were compared to a younger cohort of patients below 80 years (Group B, n=31). Patients over 80 years treated in the traditional time window (within 6 hours of symptom onset) served as a second set of controls (Group C, n=40). Statistical analysis was performed with a significance level of 0.05 Results: For angiographic results, there were no statistically significant differences in terms of good outcomes (TICI 2b-3) among patients of Group A, when compared to Groups B or C (p>0.05). For the endovascular procedures, no significant differences were noted in the total fluoroscopy time (Median Group A 44.05, Group B 38.1, Group C 35.25 min), total intra-procedure time (Median Group A 144, Group B 143, Group C 126 min) or total radiation exposure (Median Group A 8308, Group B 8960, Group C 8318 uGy-m 2 ). For stroke outcomes, a good clinical outcome was defined as modified Rankin score of 0-2 at discharge. Significantly better outcomes were noted in the younger patients in Group B - 35.4%, when compared to 13.3% in Group A (p=0.03). Comparative outcomes differed in the elderly patients above 80 years, Group A -13.3% vs Group C - 25%, although not statistically significant (p=0.23). There was a significant difference in mortality in patients of Group A - 40% as compared to 12% in the younger cohort, Group B (p= 0.01). Conclusions: In the extended time window, patients above 80 years of age were noted to have a higher mortality, morbidity compared to the younger cohort of patients. No significant differences were noted in the stroke outcomes in patients above 80 years of age when comparing the traditional and the extended time window for stroke treatment.

Sign in / Sign up

Export Citation Format

Share Document