Alberta Stroke Program Early CT Research Articles

Automated ASPECTS Segmentation and Scoring Tool: a Method Tailored for a Colombian TelestrokeNetwork.

To evaluate our two non-machine learning (non-ML)-based algorithmic approaches for detecting early ischemic infarcts on brain CT images of patients with acute ischemic stroke symptoms, tailored to our local population, to be incorporated in our telestroke software. One-hundred and thirteen acute stroke patients, excluding hemorrhagic, subacute, and chronic patients, with accessible brain CT images were divided into calibration and test sets. The gold standard was determined through consensus among three neuroradiologist. Four neuroradiologist independently reported Alberta Stroke Program Early CT Scores (ASPECTSs). ASPECTSs were also obtained using a commercial ML solution (CMLS), and our two methods, namely the Mean Hounsfield Unit (HU) relative difference (RELDIF) and the density distribution equivalence test (DDET), which used statistical analyze the of the HUs of each region and its contralateral side. Automated segmentation was perfect for cortical regions, while minimal adjustment was required for basal ganglia regions. For dichotomized-ASPECTSs (ASPECTS < 6) in the test set, the area under the receiver operating characteristic curve (AUC) was 0.85 for the DDET method, 0.84 for the RELDIF approach, 0.64 for the CMLS, and ranged from 0.71-0.89 for the neuroradiologist. The accuracy was 0.85 for the DDET method, 0.88 for the RELDIF approach, and was ranged from 0.83 - 0.96 for the neuroradiologist. Equivalence at a margin of 5% was documented among the DDET, RELDIF, and gold standard on mean ASPECTSs. Noninferiority tests of the AUC and accuracy of infarct detection revealed similarities between both DDET and RELDIF, and the CMLS, and with at least one neuroradiologist. The alignment of our methods with the evaluations of neuroradiologist and the CMLS indicates the potential of our methods to serve as supportive tools in clinical settings, facilitating prompt and accurate stroke diagnosis, especially in health care settings, such as Colombia, where neuroradiologist are limited.

Association between ASPECTS region of infarction and clinical outcome in non-acute large vessel occlusion ischaemic stroke after endovascular recanalisation

PurposeThis study retrospectively investigated whether infarction in specific Alberta Stroke Program Early CT Score (ASPECTS) regions is associated with clinical outcome in patients with symptomatic non-acute internal carotid or middle...

The treatment effect across ASPECTS in acute ischemic stroke: Analysis from the AcT trial.

Early ischemic changes on baseline imaging are commonly evaluated for acute stroke decision-making and prognostication. We assess the association of early ischemic changes on clinical outcomes and whether it differs between intravenous tenecteplase and Alteplase. Data are from the phase 3, Alteplase compared to Tenecteplase (AcT) trial. Subjects with anterior circulation stroke were included. Early ischemic changes were assessed using the Alberta Stroke Program Early CT score (ASPECTS). Efficacy outcomes included modified Rankin scale (mRS) 0-1, mRS 0-2, and ordinal mRS at 90 days. Safety outcomes included 24-h symptomatic intracerebral hemorrhage (sICH), any hemorrhage on follow-up scan, and 90-day mortality rate. Mixed-effects logistic regression was used to assess the association of ASPECTS (continuous and categorical (0-4 vs 5-7 vs 8-10)) with outcomes and if these associations were modified by thrombolytic type after adjusting for age, sex, and baseline stroke severity. Of the 1577 patients in the trial, 901 patients (56.3%; median age 75 years (IQR 65-84), 50.8% females, median National Institute of Health Stroke Scale (NIHSS) 14 (IQR 17-19)) with anterior circulation stroke were included. mRS 0-1 at 90 days was achieved in 1/14 (0.3%), 43/160 (14.7%), and 252/726 (85.1%) in the ASPECTS 0-4, 5-7, and 8-10 groups respectively. Every one-point decrease in ASPECTS was associated with 2.7% and 1.9% decrease in chances of mRS 0-1 and mRS 0-2 at 90 days, respectively, and 1.9% chances of increase in mortality at 90 days. Subgroup analysis in endovascular thrombectomy (EVT)-treated population showed similar results. Thrombolytic type did not modify this association between ASPECTS and 90-day mRS 0-1 (P-interaction 0.75). There was no significant interaction by thrombolytic type with any other outcomes. Similar to prior studies, we found that every one-point decrease in ASPECTS was associated with poorer clinical and safety outcomes. This effect did not differ between alteplase and tenecteplase. Data shall made available on reasonable request from the PI (BMM).

Whether mTICI 3 or mTICI 2b is better in patients with vertebrobasilar artery occlusion undergoing endovascular treatment depends on pc-ASPECTS

BackgroundThe clinical relevance of differentiating between mTICI (modified Thrombolysis In Cerebral Infarction) 2b and mTICI 3 in patients with vertebrobasilar artery occlusion (VBAO) remains unclear. This study aimed to investigate...

Constructing machine learning models based on non-contrast CT radiomics to predict hemorrhagic transformation after stoke: a two-center study.

Machine learning (ML) models were constructed according to non-contrast computed tomography (NCCT) images as well as clinical and laboratory information to assess risk stratification for the occurrence of hemorrhagic transformation (HT) in acute ischemic stroke (AIS) patients. A retrospective cohort was constructed with 180 AIS patients who were diagnosed at two centers between January 2019 and October 2023 and were followed for HT outcomes. Patients were analyzed for clinical risk factors for developing HT, infarct texture features were extracted from NCCT images, and the radiomics score (Rad-score) was calculated. Then, five ML models were established and evaluated, and the optimal ML algorithm was used to construct the clinical, radiomics, and clinical-radiomics models. Receiver operating characteristic (ROC) curves were used to compare the performance of the three models in predicting HT. Based on the outcomes of the AIS patients, 104 developed HT, and the remaining 76 had no HT. The HT group consisted of 27 hemorrhagic infarction (HI) and 77 parenchymal-hemorrhage (PH). Patients with HT had a greater neutrophil-to-lymphocyte ratio (NLR), baseline National Institutes of Health Stroke Scale (NIHSS) score, infarct volume, and Rad-score and lower Alberta stroke program early CT score (ASPECTS) (all p < 0.01) than patients without HT. The best ML algorithm for building the model was logistic regression. In the training and validation cohorts, the AUC values for the clinical, radiomics, and clinical-radiomics models for predicting HT were 0.829 and 0.876, 0.813 and 0.898, and 0.876 and 0.957, respectively. In subgroup analyses with different treatment modalities, different infarct sizes, and different stroke time windows, the assessment accuracy of the clinical-radiomics model was not statistically meaningful (all p > 0.05), with an overall accuracy of 79.5%. Moreover, this model performed reliably in predicting the PH and HI subcategories, with accuracies of 82.9 and 92.9%, respectively. ML models based on clinical and NCCT radiomics characteristics can be used for early risk evaluation of HT development in AIS patients and show great potential for clinical precision in treatment and prognostic assessment.

Sex Disparities in Mortality After Endovascular Therapy in Large Core Infarcts

Background In recent large core endovascular therapy (EVT) trials of large vessel occlusion acute ischemic stroke (AIS), treatment was associated with reduced rates of mortality. Because post‐AIS mortality can be influenced by societal and biological factors that differ between women and men, we investigate sex‐based differences in mortality outcomes following EVT in large core AIS. Methods From our prospectively collected multicenter registry across 4 comprehensive stroke centers in the Greater Houston area, we identified patients from 2017 to 2022 with large vessel occlusion AIS and large infarct core. Large infarct core was defined by computed tomography perfusion exceeding 70 mL (by regional cerebral blood flow measurements using automated postprocessing) or computed tomography Alberta Stroke Program Early CT [Computed Tomography] Score&lt;6. The primary outcome of this study was the likelihood of mortality at 90 days, determined through multivariable logistic regression adjusted for EVT, sex, and EVT/sex interaction term. Secondary outcomes included 90‐day disability outcomes and intracerebral hemorrhage. Results Among 190 patients who met inclusion criteria, 50% were female and 45.3% received EVT. Demographic differences between the sexes were largely balanced apart from the older age of presentation for women compared with men (75 versus 67, women versus men; P &lt;0.01). In univariable analysis, women who did not receive EVT had greater mortality (27.4% difference; P &lt;0.001) compared with men, with comparable rates in EVT‐treated cohorts. In multivariable analysis, non‐EVT management was strongly associated with mortality in women compared with men at discharge (odds ratio [OR] 5.81, 95% CI [1.96–17.23]) and 90‐days (OR 6.77, 95% CI [2.09–21.94]). In the secondary analysis, which additionally adjusted the model for age and National Institutes of Health Stroke Scale score, these findings were unchanged. The sex/EVT interaction term showed significant interaction for mortality both at discharge and 90 days ( P &lt;0.01). Conclusion EVT in large core AIS populations may disparately reduce mortality in women compared to men.

Predicting Recanalization Failure With Conventional Devices During Endovascular Treatment Related to Vessel Occlusion

Background Among patients with stroke eligible for endovascular treatment, preprocedure identification of those with low chances of successful recanalization with conventional devices (stent‐retrievers and/or direct aspiration) may allow anticipating procedural rescue strategies. We aimed to develop a preprocedural algorithm able to predict recanalization failure with conventional devices (RFCD). Methods Observational study. Data from consecutive patients with stroke who received endovascular treatment between 2019 and 2022 in 10 centers were collected from the Catalan Stroke Registry (Codi Ictus Catalunya Registry, CICAT). RFCD was defined as final thrombolysis in cerebral infarction ≤2a or the use of rescue therapy defined as balloon angioplasty±stent deployment. Univariate and multivariate analysis to identify variables associated with RFCD were performed. A gradient boosted decision tree machine learning model to predict RFCD was developed utilizing preprocedure variables previously selected. Clinical improvement at 24 hours was defined as a drop of ≥4 points from baseline National Institutes of Health Stroke Scale score or 0–1 at 24 hours. Results In total, 984 patients were included; RFCD was observed in 14.3% (n:141) of the cases. Of these, 47.5% (n = 67) received balloon angioplasty±stent deployment as rescue therapy. Among patients receiving balloon angioplasty±stent deployment, clinical improvement was associated with lower number of attempts with conventional devices (median number of passes 2 versus 3; P = 0.045). In logistic regression, the absence of atrial fibrillation (odds ratio [OR]: 2.730, 95%CI: 1.541–4.836; P = 0.007) and no‐thrombolytic treatment (OR: 1.826, 95%CI: 1.230–2.711; P = 0.003) emerged as independent predictors of RFCD. A predictive model for RFCD, based on age, sex, hypertension, wake‐up stroke, baseline National Institutes of Health Stroke Scale score, Alberta Stroke Program Early CT [Computed Tomography] Score, occlusion site, thrombolysis, and atrial fibrillation showed an acceptable discrimination (area under the curve: 0.72±0.024 SD) and accuracy (0.75±0.015 SD). Overall performance was moderate (weighted F1‐score: 0.77±0.041 SD). Conclusion In RFCD patients, early balloon angioplasty±stent deployment rescue was associated with improved outcomes. A predictive model using affordable preprocedure clinical variables could be useful to identify these patients before intervention.

Discrepancies in ASPECTS obtained by artificial intelligence and experts: Associated factors and prognostic implications

PurposeThe differences between the Alberta Stroke Program Early CT Score (ASPECTS) obtained by experts and artificial intelligence (AI) software require elucidation. We aimed to characterize the discrepancies between the ASPECTS obtained by AI and experts and determine the associated factors and prognostic implications. MethodsThis multicenter, retrospective, observational cohort study included patients showing acute ischemic stroke caused by large-vessel occlusion in the anterior circulation. ASPECTS was determined by AI software (RAPID ASPECTS) and experts from the core laboratory. Interclass correlation coefficients (ICCs) and Bland–Altman plots were used to illustrate the consistency and discrepancies; logistic regression analyses were used to assess the correlates of inconsistency; and receiver operating characteristic analyses were performed to assess the diagnostic performance for predicting unfavorable clinical outcomes. ResultsThe study population included 491 patients. The ICC for the expert and AI ASPECTS was 0.63 (95 % confidence interval [CI]: 0.25–0.79).The mean difference between expert and AI ASPECTS was 2.24. Chronic infarcts (odds ratio [OR], 1.9; 95 % CI, 1.1–3.4; P=0.021) and expert scores in the internal capsule (OR, 2.9; 95 % CI, 1.1–7.7; P=0.034) and lentiform (OR, 2.4; 95 % CI, 1.3–4.7; P=0.008) were significant correlates of inconsistency. The ASPECTS obtained by AI showed a significantly higher area under the curve for unfavorable outcomes (0.68 vs. 0.63, P=0.04). ConclusionsIn comparison with expert ASPECTS, AI ASPECTS overestimated the infarct extent. Future studies should aim to determine whether AI ASPECTS assessments should use a lower threshold to screen patients for endovascular therapy.

Predictors of favorable functional outcomes for elderly patients undergoing endovascular thrombectomy for acute ischemic stroke

PurposeThe aim of this study was to identify factors that predict favorable functional outcomes in elderly patients with large-vessel occlusion acute ischemic stroke (LVO-AIS) who underwent mechanical thrombectomy (MT).MethodsWe conducted a retrospective observational study using the prospectively maintained Bigdata Observatory for Stroke of China (BOSC) to identify eligible patients who underwent MT for LVO-AIS at four comprehensive stroke centers between August 2019 and February 2022. Inclusion criteria included patients aged 80 years or older with a baseline modified Rankin Scale (mRS) 0–2, baseline National Institutes of Health Stroke Scale (NIHSS) > 6, baseline Alberta Stroke Program Early CT Score (ASPECTS) > 6 who received treatment within 24 h from symptom onset. Pertinent demographic, clinical, and procedural variables were collected. Multivariable regression analyses were performed to identify predictors of favorable long-term functional outcomes, defined as mRS 0–2 at 90 days.ResultsA total of 63 patients were included in the study with a mean age of 83 years. Patients with previous diagnosis of atrial fibrillation were more likely to have a favorable functional outcome (OR 2.09, 95% CI 2.09–407.33, p = 0.012), while a higher baseline NIHSS was associated with a less favorable functional outcome (OR 0.64, 95% CI 0.46–0.89, p = 0.007). In addition, there was an observed trend suggesting an association between higher baseline ASPECTS and favorable functional outcomes. This association did not reach statistical significance (OR 2.49, 95% CI 0.94–6.54, p = 0.065).ConclusionIn this study, we identified factors that predicted a favorable functional outcome in elderly LVO-AIS patients undergoing MT. A higher baseline NIHSS decreased the odds of mRS 0–2 at 90 days, whereas a history of atrial fibrillation increased the odds of a favorable functional outcome. These results emphasize the complex relationship between clinical factors and functional recovery in this vulnerable population.

Magnitude of systolic blood pressure reduction following endovascular treatment and clinical outcomes in acute large artery occlusion stroke

BackgroundThe impact of lowering systolic blood pressure (SBP) following endovascular treatment (EVT) in acute large vessel occlusion stroke (LVOS) patients remains unclear. We aimed to explore the effect of the...

A risk prediction model for unexplained early neurological deterioration following intravenous thrombolysis

Background and objectivesEarly neurological deterioration (END) post-intravenous thrombolysis significantly impacts the long-term prognosis of stroke patients. This study aimed to establish a rapid risk prediction model for unexplained END following intravenous thrombolysis.MethodsThis prospective study consecutively enrolled patients with acute ischemic stroke treated with recombinant tissue plasminogen activator intravenous thrombolysis at the Department of Neurology, Third People’s Hospital of Hubei Province, and Yangluo Hospital District between June 2019 and December 2022. Unexplained END was defined as an increase of ≥ 4 points in the National Institutes of Health Stroke Scale (NIHSS) score between admission and 24 h. A nomogram was developed and assessed by calculating the area under the receiver operating characteristic curve (AUC-ROC). The calibration was assessed using the Hosmer–Lemeshow test.ResultsA total of 211 patients (130 males and 110 patients aged < 65 years) were included, with 66 experiencing unexplained END. Multivariate logistic regression analysis identified large arterial disease, transient ischemic attack, high blood glucose, high neutrophil/lymphocyte ratio, important perforator disease, and low the Alberta Stroke Program Early CT scores (APSECTS) as independent risk factors for END and established the nomogram used above indicators. The nomogram showed an AUC-ROC of 0.809 (95% CI 0.7429–0.8751), with a specificity of 0.862 and sensitivity of 0.712. The positive predictive value was 0.702, and the negative predictive value was 0.868. The Hosmer–Lemeshow goodness-of-fit test (χ2 = 1.069, P = 0.169) indicated acceptable model calibration.ConclusionThis study successfully established a risk prediction model for END following intravenous thrombolysis and the model demonstrates good stability and predictive capacity. Further validation through a prospective, multicenter study is necessary.

Endovascular therapy for acute intracranial large vessel occlusion due to atherothrombosis: Multicenter historical registry

BackgroundAtherothrombotic stroke-related large vessel occlusion (AT-LVO) is caused by two etiologies, the intracranial artery occlusion due to in situ occlusion (intracranial group) or due to embolism from cervical carotid occlusion...

Delayed Cerebral Infarction After Aneurysmal Subarachnoid Hemorrhage: Location, Distribution Patterns, Infarct Load, and Effect on Outcome.

Delayed cerebral ischemia (DCI) is one of the main contributing factors to poor clinical outcome after aneurysmal subarachnoid hemorrhage (SAH). Unsuccessful treatment can cause irreversible brain injury in the form of DCI-related infarction. We aimed to assess the association between the location, distribution, and size of DCI-related infarction in relation to clinical outcome. Consecutive patients with SAH treated at 2 university hospitals between 2014 and 2019 (Helsinki, Finland) and between 2006 and 2020 (Aachen, Germany) were included. Size of DCI-related infarction was quantitatively measured as absolute volume (in milliliters). In a semiquantitative fashion, infarction in 14 regions of interest (ROIs) according to a modified Alberta Stroke Program Early CT Score (ASPECTS) was noted. The association of infarction in these ROIs along predefined regions of eloquent brain, with clinical outcome, was assessed. For this purpose, 1-year outcome was measured by the Glasgow Outcome Scale (GOS) and dichotomized into favorable (GOS 4-5) and unfavorable (GOS 1-3). Of 1,190 consecutive patients with SAH, 155 (13%) developed DCI-related infarction. One-year outcome data were available for 148 (96%) patients. A median overall infarct volume of 103 mL (interquartile range 31-237) was measured. DCI-related infarction was significantly associated with 1-year unfavorable outcome (odds ratio [OR] 4.89, 95% CI 3.36-7.34, p < 0.001). In patients with 1-year unfavorable outcome, vascular territories more frequently affected were left middle cerebral artery (affected in 49% of patients with unfavorable outcome vs in 30% of patients with favorable outcome; p = 0.029), as well as left (44% vs 18%; p = 0.003) and right (52% vs 14%; p < 0.001) anterior cerebral artery supply areas. According to the ASPECTS model, the right M3 (OR 8.52, 95% CI 1.41-51.34, p = 0.013) and right A2 (OR 7.84, 95% CI 1.97-31.15, p = 0.003) regions were independently associated with unfavorable outcome. DCI-related infarction was associated with a 5-fold increase in the odds of unfavorable outcome, after 1 year. Ischemic lesions in specific anatomical regions are more likely to contribute to unfavorable outcome. Data collection in Aachen was registered in the German Clinical Trial Register (DRKS00030505); on January 3, 2023.

Effectiveness of computed tomography perfusion imaging in stroke management.

Current guidelines do not support the use of computed tomography perfusion (CTP) in stroke, except when identifying the penumbra during an extended treatment window. Therefore, this study aimed to define the yield of CTP in diagnosing a stroke diagnosis beyond the imaging of the penumbra in the hyperacute phase (0-6 h) and an extended time window (6-24 h). All consecutive patients with acute onset of symptoms within a 24-h window underwent CTP imaging. The diagnostic value of CTP was calculated against the clinical and radiological diagnoses of stroke. A positive CTP result was determined by the presence of either a core or penumbra on the RAPID summary. Clinical diagnoses corresponded to discharge diagnoses of stroke. A radiological diagnosis was established if early ischemic changes [Alberta Stroke Program Early CT Score (ASPECTS) <10] were observed on the baseline CT scan, acute infarction was confirmed on follow-up imaging, or symptomatic occlusion was evident on baseline CTA. Between November 2018 and November 2019, 585 consecutive patients with an acute neurological deficit underwent multimodal CT imaging. A total of 500 patients (85%) were included, where 274 (55%) were within the hyperacute phase, 153 (31%) had a radiological diagnosis of stroke, and 122 (24%) had a clinical diagnosis of stroke. CTP yielded positive results only in patients with a confirmed stroke (positive predictive value and specificity of 100%). When CTP results were negative, 43% of the cases turned out to stroke mimics. Patients with stroke mimics were younger (66 ± 17 vs. 73 ± 13) and had lower scores on the National Institutes of Health Stroke Scale [median 0; interquartile range (IQR) 0-2 vs. median 4; IQR 2-6] compared to patients with CTP-negative strokes. In our study, CTP consistently indicated brain ischemia; therefore, in stroke management, CTP is most beneficial when it yields a positive result. A positive CTP result should prompt adequate stroke management actions without any delay. Conversely, a negative CTP result necessitates the consideration of both stroke and non-stroke diagnoses.

Bridging thrombolysis before endovascular therapy is associated with better outcomes in patients with large infarction core

BackgroundThis study investigates the efficacy and safety of bridging intravenous thrombolysis (IVT) before endovascular therapy (EVT) compared with EVT alone in patients with large infarction core.MethodsWe conducted a comprehensive search...

Acute ischemic stroke with or without asymptomatic intracranial hemorrhage after endovascular treatment: a propensity-score matching study

BackgroundThe long-term follow-up of asymptomatic intracranial hemorrhage (aICH) in patients with acute ischemic stroke after endovascular treatment (EVT) remains controversial.ObjectiveTo evaluate the potential effect of aICH in a real-world practice...

The impact of general anesthesia versus non-general anesthesia on thrombectomy outcomes by occlusion location: insights from the ETIS registry.

Identifying the optimal anesthetic technique for mechanical thrombectomy (MT) remains an unresolved issue. Prior research has not considered the influence of occlusion site when comparing general anesthesia (GA) with non-GA. This study evaluates the differential impacts of the anesthetic technique (GA vs non-GA) on outcomes according to the location of occlusion. This is a retrospective analysis of the ETIS (Endovascular Treatment in Ischemic Stroke) registry. Patients with anterior circulation large-vessel occlusion treated with MT were included. Patients were divided into groups according to the location of occlusion. Inverse propensity score weighting analysis was used. Among 2783 patients included in the propensity score analysis, 669 (24%) received GA. In the total cohort, GA was not associated with favorable outcome, excellent outcome, successful reperfusion, or complete reperfusion. GA was associated with higher odds of parenchymal hemorrhage (OR 1.42, 95% 1.05-1.92) but not symptomatic intracranial hemorrhage. GA was associated with Alberta Stroke Program Early CT Score progression (OR 1.36, 95% CI 1.11-1.68). In the internal carotid artery occlusion group, GA was associated with higher odds of mortality (OR 1.94, 95% CI 1.15-3.27). In the M1 group, GA was associated with lower odds of complications (OR 0.41, 95% CI 0.19-0.92). In the M2 group, GA was associated with successful reperfusion (OR 2.79, 95% CI 1.02-7.64). In addition, the complication rate was lower with GA (2.7% vs 7%), although the association was not significant in adjusted analysis. While GA and non-GA techniques did not differ significantly in functional outcomes, the influence of GA on angiographic and procedural safety outcomes was location dependent, underscoring the importance of a tailored anesthesia technique in MT procedures.

Haemorrhage after thrombectomy with adjuvant thrombolysis in unknown onset stroke depends on high early lesion water uptake

Background and purposeIn wake-up stroke, CT-based quantitative net water uptake (NWU) might serve as an alternative tool to MRI to guide intravenous thrombolysis with alteplase (IVT). An important complication after...

Role of mechanical thrombectomy among large vessel stroke patients during the coronavirus disease (COVID-19) pandemic

PurposeThe aim of our study is to provide insights derived from experience at multiple centers regarding the outcomes of mechanical thrombectomy (MT) for large vessel occlusion (LVO) in COVID-19 patients and compare them with those in non-COVID-19 patients during the coronavirus disease (COVID-19) pandemic.ResultsCOVID‐19 positive patients were younger than COVID‐19 negative patients (62.1 ± 2.69 versus 69.5 ± 2.2, P < 0.001). There was a significant difference between COVID-19 and non-COVID-19 groups in the median D-dimer levels (6 vs. 4.5; P < 0.001), median ESR levels (63 vs. 38; P < 0.001) and median CRP levels (110 vs. 48.5; P < 0.001), respectively. Median time from stroke symptoms onset to hospital admission was significantly higher among COVID-19 positive patients (366 vs. 155 min; P < 0.001). COVID‐19 positive patients with LVO presented with a higher median NIH Stroke Scale score at presentation (16 versus 8, P < 0.001) and lower median Alberta Stroke Program Early CT Score (ASPECTS) on admission (6 versus 8, P < 0.001). Patients with COVID-19 had significantly higher percentages of poor functional outcomes as scored using the mRS grades 3–5 in comparison to non-COVID-19 patients (69.2% vs. 13.6%; P = 0.002), but there was no significant difference between both groups in complications such as early cerebral re-occlusion, intracerebral hemorrhage, or in-hospital mortality (P > 0.05).ConclusionMechanical thrombectomy has effectively managed patients with LVO stroke. LVO stroke in COVID-19 patients occur at a young age, and have multi-territory vascular involvement. Poor functional outcomes post thrombectomy in COVID-19 patients, irrespective of timely, successful angiographic recanalization.

Deep learning-based automatic ASPECTS calculation can improve diagnosis efficiency in patients with acute ischemic stroke: a multicenter study.

The Alberta Stroke Program Early CT Score (ASPECTS), a systematic method for assessing ischemic changes in acute ischemic stroke using non-contrast computed tomography (NCCT), is often interpreted relying on expert experience and can vary between readers. This study aimed to develop a clinically applicable automatic ASPECTS system employing deep learning (DL). This study enrolled 1987 NCCT scans that were retrospectively collected from four centers between January 2017 and October 2021. A DL-based system for automated ASPECTS assessment was trained on a development cohort (N = 1767) and validated on an independent test cohort (N = 220). The consensus of experienced physicians was regarded as a reference standard. The validity and reliability of the proposed system were assessed against physicians' readings. A real-world prospective application study with 13,399 patients was used for system validation in clinical contexts. The DL-based system achieved an area under the receiver operating characteristic curve (AUC) of 84.97% and an intraclass correlation coefficient (ICC) of 0.84 for overall-level analysis on the test cohort. The system's diagnostic sensitivity was 94.61% for patients with dichotomized ASPECTS at a threshold of ≥ 6, with substantial agreement (ICC = 0.65) with expert ratings. Combining the system with physicians improved AUC from 67.43 to 89.76%, reducing diagnosis time from 130.6 ± 66.3 s to 33.3 ± 8.3 s (p < 0.001). During the application in clinical contexts, 94.0% (12,591) of scans successfully processed by the system were utilized by clinicians, and 96% of physicians acknowledged significant improvement in work efficiency. The proposed DL-based system could accurately and rapidly determine ASPECTS, which might facilitate clinical workflow for early intervention. The deep learning-based automated ASPECTS evaluation system can accurately and rapidly determine ASPECTS for early intervention in clinical workflows, reducing processing time for physicians by 74.8%, but still requires validation by physicians when in clinical applications. The deep learning-based system for ASPECTS quantification has been shown to be non-inferior to expert-rated ASPECTS. This system improved the consistency of ASPECTS evaluation and reduced processing time to 33.3 seconds per scan. 94.0% of scans successfully processed by the system were utilized by clinicians during the prospective clinical application.