scholarly journals Electroencephalography Might Improve Diagnosis of Acute Stroke and Large Vessel Occlusion

Stroke ◽  
2020 ◽  
Vol 51 (11) ◽  
pp. 3361-3365 ◽  
Author(s):  
Fareshte Erani ◽  
Nadezhda Zolotova ◽  
Benjamin Vanderschelden ◽  
Nima Khoshab ◽  
Hagop Sarian ◽  
...  
Keyword(s):  
Neural Network ◽  
Emergency Department ◽  
Deep Learning ◽  
Acute Stroke ◽  
Clinical Data ◽  
Area Under The Curve ◽  
Large Vessel ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
Deep Learning Neural Network

Background and Purpose: Clinical methods have incomplete diagnostic value for early diagnosis of acute stroke and large vessel occlusion (LVO). Electroencephalography is rapidly sensitive to brain ischemia. This study examined the diagnostic utility of electroencephalography for acute stroke/transient ischemic attack (TIA) and for LVO. Methods: Patients (n=100) with suspected acute stroke in an emergency department underwent clinical exam then electroencephalography using a dry-electrode system. Four models classified patients, first as acute stroke/TIA or not, then as acute stroke with LVO or not: (1) clinical data, (2) electroencephalography data, (3) clinical+electroencephalography data using logistic regression, and (4) clinical+electroencephalography data using a deep learning neural network. Each model used a training set of 60 randomly selected patients, then was validated in an independent cohort of 40 new patients. Results: Of 100 patients, 63 had a stroke (43 ischemic/7 hemorrhagic) or TIA (13). For classifying patients as stroke/TIA or not, the clinical data model had area under the curve=62.3, whereas clinical+electroencephalography using deep learning neural network model had area under the curve=87.8. Results were comparable for classifying patients as stroke with LVO or not. Conclusions: Adding electroencephalography data to clinical measures improves diagnosis of acute stroke/TIA and of acute stroke with LVO. Rapid acquisition of dry-lead electroencephalography is feasible in the emergency department and merits prehospital evaluation.

scholarly journals Deep Learning–Derived High-Level Neuroimaging Features Predict Clinical Outcomes for Large Vessel Occlusion

Stroke ◽  
2020 ◽  
Vol 51 (5) ◽  
pp. 1484-1492 ◽  
Author(s):  
Hidehisa Nishi ◽  
Naoya Oishi ◽  
Akira Ishii ◽  
Isao Ono ◽  
Takenori Ogura ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Large Vessel ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
Neuroimaging Biomarkers ◽  
High Level

Background and Purpose— For patients with large vessel occlusion, neuroimaging biomarkers that evaluate the changes in brain tissue are important for determining the indications for mechanical thrombectomy. In this study, we applied deep learning to derive imaging features from pretreatment diffusion-weighted image data and evaluated the ability of these features in predicting clinical outcomes for patients with large vessel occlusion. Methods— This multicenter retrospective study included patients with anterior circulation large vessel occlusion treated with mechanical thrombectomy between 2013 and 2018. We designed a 2-output deep learning model based on convolutional neural networks (the convolutional neural network model). This model employed encoder-decoder architecture for the ischemic lesion segmentation, which automatically extracted high-level feature maps in its middle layers, and used its information to predict the clinical outcome. Its performance was internally validated with 5-fold cross-validation, externally validated, and the results compared with those from the standard neuroimaging biomarkers Alberta Stroke Program Early CT Score and ischemic core volume. The prediction target was a good clinical outcome, defined as a modified Rankin Scale score at 90-day follow-up of 0 to 2. Results— The derivation cohort included 250 patients, and the validation cohort included 74 patients. The convolutional neural network model showed the highest area under the receiver operating characteristic curve: 0.81±0.06 compared with 0.63±0.05 and 0.64±0.05 for the Alberta Stroke Program Early CT Score and ischemic core volume models, respectively. In the external validation, the area under the curve for the convolutional neural network model was significantly superior to those for the other 2 models. Conclusions— Compared with the standard neuroimaging biomarkers, our deep learning model derived a greater amount of prognostic information from pretreatment neuroimaging data. Although a confirmatory prospective evaluation is needed, the high-level imaging features derived by deep learning may offer an effective prognostic imaging biomarker.

scholarly journals Diagnostic value of transcranial ultrasonography for selecting subjects with large vessel occlusion: a systematic review

2019 ◽  
Vol 11 (1) ◽  
Author(s):  
Daria Antipova ◽  
Leila Eadie ◽  
Ashish Stephen Macaden ◽  
Philip Wilson
Keyword(s):  
Systematic Review ◽  
Diagnostic Accuracy ◽  
Acute Stroke ◽  
Clinical Assessment ◽  
Assessment Tools ◽  
Large Vessel ◽  
Cochrane Library ◽  
Direct Transfer ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion

Abstract Introduction A number of pre-hospital clinical assessment tools have been developed to triage subjects with acute stroke due to large vessel occlusion (LVO) to a specialised endovascular centre, but their false negative rates remain high leading to inappropriate and costly emergency transfers. Transcranial ultrasonography may represent a valuable pre-hospital tool for selecting patients with LVO who could benefit from rapid transfer to a dedicated centre. Methods Diagnostic accuracy of transcranial ultrasonography in acute stroke was subjected to systematic review. Medline, Embase, PubMed, Scopus, and The Cochrane Library were searched. Published articles reporting diagnostic accuracy of transcranial ultrasonography in comparison to a reference imaging method were selected. Studies reporting estimates of diagnostic accuracy were included in the meta-analysis. Results Twenty-seven published articles were selected for the systematic review. Transcranial Doppler findings, such as absent or diminished blood flow signal in a major cerebral artery and asymmetry index ≥ 21% were shown to be suggestive of LVO. It demonstrated sensitivity ranging from 68 to 100% and specificity of 78–99% for detecting acute steno-occlusive lesions. Area under the receiver operating characteristics curve was 0.91. Transcranial ultrasonography can also detect haemorrhagic foci, however, its application is largely restricted by lesion location. Conclusions Transcranial ultrasonography might potentially be used for the selection of subjects with acute LVO, to help streamline patient care and allow direct transfer to specialised endovascular centres. It can also assist in detecting haemorrhagic lesions in some cases, however, its applicability here is largely restricted. Additional research should optimize the scanning technique. Further work is required to demonstrate whether this diagnostic approach, possibly combined with clinical assessment, could be used at the pre-hospital stage to justify direct transfer to a regional thrombectomy centre in suitable cases.

scholarly journals Emergency medical dispatchers’ ability to identify large vessel occlusion stroke during emergency calls

2021 ◽  
Vol 29 (1) ◽  
Author(s):  
Pauli E. T. Vuorinen ◽  
Jyrki P. J. Ollikainen ◽  
Pasi A. Ketola ◽  
Riikka-Liisa K. Vuorinen ◽  
Piritta A. Setälä ◽  
...  
Keyword(s):  
Emergency Department ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Large Vessel ◽  
Emergency Call ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
Emergency Response System ◽  
Emergency Medical ◽  
Cortical Ischemia

Abstract Background In acute ischemic stroke, conjugated eye deviation (CED) is an evident sign of cortical ischemia and large vessel occlusion (LVO). We aimed to determine if an emergency dispatcher can recognise LVO stroke during an emergency call by asking the caller a binary question regarding whether the patient’s head or gaze is away from the side of the hemiparesis or not. Further, we investigated if the paramedics can confirm this sign at the scene. In the group of positive CED answers to the emergency dispatcher, we investigated what diagnoses these patients received at the emergency department (ED). Among all patients brought to ED and subsequently treated with mechanical thrombectomy (MT) we tracked the proportion of patients with a positive CED answer during the emergency call. Methods We collected data on all stroke dispatches in the city of Tampere, Finland, from 13 February 2019 to 31 October 2020. We then reviewed all patient records from cases where the dispatcher had marked ‘yes’ to the question regarding patient CED in the computer-aided emergency response system. We also viewed all emergency department admissions to see how many patients in total were treated with MT during the period studied. Results Out of 1913 dispatches, we found 81 cases (4%) in which the caller had verified CED during the emergency call. Twenty-four of these patients were diagnosed with acute ischemic stroke. Paramedics confirmed CED in only 9 (11%) of these 81 patients. Two patients with positive CED answers during the emergency call and 19 other patients brought to the emergency department were treated with MT. Conclusion A small minority of stroke dispatches include a positive answer to the CED question but paramedics rarely confirm the emergency medical dispatcher’s suspicion of CED as a sign of LVO. Few patients in need of MT can be found this way. Stroke dispatch protocol with a CED question needs intensive implementation.

Abstract 1122‐000022: Delays in Care for Patients with Acute Stroke During Hospitalization for Other Reasons

2021 ◽  
Vol 1 (S1) ◽  
Author(s):  
Nicholas Vigilante ◽  
Parth Patel ◽  
Prasanth Romiyo ◽  
Lauren Thau ◽  
Mark Heslin ◽  
...  
Keyword(s):  
Acute Stroke ◽  
Acute Care ◽  
Large Vessel ◽  
Large Vessel Occlusion ◽  
Single Center ◽  
Anterior Circulation ◽  
Vessel Occlusion ◽  
Symptom Recognition ◽  
Risk Patients ◽  
Recognition Imaging

Introduction : In‐hospital stroke (IHS) is defined as stroke that occurs during hospitalization for non‐stroke conditions. We aimed to understand the timing of symptom recognition for patients who experienced IHS and its impact on the care they receive. Methods : A prospective, single center registry of adult patients (9/20/19‐2/28/21) was queried for acute anterior circulation IHS. Indications for hospitalization, delays from last known well (LKW) to symptom recognition, imaging, and treatment were explored. Results : Of 928 consecutively evaluated adults with acute stroke, 85 (9%) developed an anterior circulation IHS, 39 (46%) of whom were female, with a median age of 67 years (IQR 60–76) and median NIHSS of 15 (IQR 4–22). Sixty‐eight (80%) had a >1 hour delay from last known well to symptom recognition. Two patients (2%) received IV thrombolysis, although another 38 (45%) would have been eligible if not for a delay in symptom recognition. An ICA, M1, or M2 occlusion was observed in 18 patients (21%), 7 of whom were treated at a median of 174 minutes after LKW (IQR 65–219). Compared to the 11 patients who did not undergo thrombectomy with large vessel occlusion, those who underwent thrombectomy had non‐significantly shorter delays from LKW until neuroimaging (median 85 [IQR 65‐162] vs. 216 [IQR 133‐507], p = 0.12). Conclusions : While uncommon, patients with IHS experience delays in symptom recognition and treatment, which lead to exclusion from acute care treatment such as thrombolysis and thrombectomy. Earlier detection with more frequent nursing assessments or advanced neuromonitoring devices in at‐risk patients may reduce delays in care.

scholarly journals Epidemiological Surveillance of the Impact of the COVID-19 Pandemic on Stroke Care Using Artificial Intelligence

Stroke ◽  
2021 ◽  
Author(s):  
Raul G. Nogueira ◽  
Jason M. Davies ◽  
Rishi Gupta ◽  
Ameer E. Hassan ◽  
Thomas Devlin ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Acute Stroke ◽  
Systems Of Care ◽  
Ct Perfusion ◽  
Stroke Care ◽  
Large Vessel ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
Number Of Patients ◽  
The Impact

Background and Purpose: The degree to which the coronavirus disease 2019 (COVID-19) pandemic has affected systems of care, in particular, those for time-sensitive conditions such as stroke, remains poorly quantified. We sought to evaluate the impact of COVID-19 in the overall screening for acute stroke utilizing a commercial clinical artificial intelligence platform. Methods: Data were derived from the Viz Platform, an artificial intelligence application designed to optimize the workflow of patients with acute stroke. Neuroimaging data on suspected patients with stroke across 97 hospitals in 20 US states were collected in real time and retrospectively analyzed with the number of patients undergoing imaging screening serving as a surrogate for the amount of stroke care. The main outcome measures were the number of computed tomography (CT) angiography, CT perfusion, large vessel occlusions (defined according to the automated software detection), and severe strokes on CT perfusion (defined as those with hypoperfusion volumes >70 mL) normalized as number of patients per day per hospital. Data from the prepandemic (November 4, 2019 to February 29, 2020) and pandemic (March 1 to May 10, 2020) periods were compared at national and state levels. Correlations were made between the inter-period changes in imaging screening, stroke hospitalizations, and thrombectomy procedures using state-specific sampling. Results: A total of 23 223 patients were included. The incidence of large vessel occlusion on CT angiography and severe strokes on CT perfusion were 11.2% (n=2602) and 14.7% (n=1229/8328), respectively. There were significant declines in the overall number of CT angiographies (−22.8%; 1.39–1.07 patients/day per hospital, P <0.001) and CT perfusion (−26.1%; 0.50–0.37 patients/day per hospital, P <0.001) as well as in the incidence of large vessel occlusion (−17.1%; 0.15–0.13 patients/day per hospital, P <0.001) and severe strokes on CT perfusion (−16.7%; 0.12–0.10 patients/day per hospital, P <0.005). The sampled cohort showed similar declines in the rates of large vessel occlusions versus thrombectomy (18.8% versus 19.5%, P =0.9) and comprehensive stroke center hospitalizations (18.8% versus 11.0%, P =0.4). Conclusions: A significant decline in stroke imaging screening has occurred during the COVID-19 pandemic. This analysis underscores the broader application of artificial intelligence neuroimaging platforms for the real-time monitoring of stroke systems of care.

scholarly journals Pomona Large Vessel Occlusion Screening Tool for Prehospital and Emergency Room Settings

2018 ◽  
Vol 7 (3-4) ◽  
pp. 196-203 ◽  
Author(s):  
Kessarin Panichpisal ◽  
Kenneth Nugent ◽  
Maharaj Singh ◽  
Richard Rovin ◽  
Reji Babygirija ◽  
...  
Keyword(s):  
Los Angeles ◽  
Acute Stroke ◽  
Predictive Value ◽  
Area Under The Curve ◽  
Predictive Performance ◽  
Large Vessel ◽  
Stroke Severity ◽  
Vessel Occlusion ◽  
Comparable Accuracy ◽  
Score Model

Background: Early identification of patients with acute ischemic strokes due to large vessel occlusions (LVO) is critical. We propose a simple risk score model to predict LVO. Method: The proposed scale (Pomona Scale) ranges from 0 to 3 and includes 3 items: gaze deviation, expressive aphasia, and neglect. We reviewed a cohort of all acute stroke activation patients between February 2014 and January 2016. The predictive performance of the Pomona Scale was determined and compared with several National Institutes of Health Stroke Scale (NIHSS) cutoffs (≥4, ≥6, ≥8, and ≥10), the Los Angeles Motor Scale (LAMS), the Cincinnati Prehospital Stroke Severity (CPSS) scale, the Vision Aphasia and Neglect Scale (VAN), and the Prehospital Acute Stroke Severity Scale (PASS). Results: LVO was detected in 94 of 776 acute stroke activations (12%). A Pomona Scale ≥2 had comparable accuracy to predict LVO as the VAN and CPSS scales and higher accuracy than Pomona Scale ≥1, LAMS, PASS, and NIHSS. A Pomona Scale ≥2 had an accuracy (area under the curve) of 0.79, a sensitivity of 0.86, a specificity of 0.70, a positive predictive value of 0.71, and a negative predictive value of 0.97 for the detection of LVO. We also found that the presence of either neglect or gaze deviation alone had comparable accuracy of 0.79 as Pomona Scale ≥2 to detect LVO. Conclusion: The Pomona Scale is a simple and accurate scale to predict LVO. In addition, the presence of either gaze deviation or neglect also suggests the possibility of LVO.

Abstract TP237: Can We Improve Clinical Detection of Right Hemisphere Large Vessel Occlusion?

Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Sana Somani ◽  
Melissa Gazi ◽  
Michael Minor ◽  
Joe Acker ◽  
Abimbola Fadairo ◽  
...  
Keyword(s):  
Left Hemisphere ◽  
Right Hemisphere ◽  
Trauma System ◽  
Area Under The Curve ◽  
Large Vessel ◽  
Stroke Severity ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
Emergency Medical ◽  
The Right

Introduction: The Emergency Medical Stroke Assessment (EMSA) is a six point stroke severity scale with one point each for gaze preference, facial droop, arm drift, leg drift, abnormal naming, and abnormal repetition that was developed to help emergency medical services (EMS) providers identify acute ischemic stroke (AIS) patients with large vessel occlusion (LVO). We hypothesized that the EMSA would detect left hemisphere LVO with a higher sensitivity than right hemisphere LVO. Methods: We trained 24 trauma system-based emergency communication center (ECC) paramedics in the EMSA. ECC-guided EMS in performance of the EMSA on patients with suspected stroke. We compared the sensitivity, specificity, area under the curve (AUC), and 95% confidence interval (CI) of ECC-guided prehospital EMSA for right versus left hemisphere ICA or M1 occlusion. Results: We enrolled 569 patients from September 2016 through February 2018, out of which 236 had a discharge diagnosis of stroke and 173 had a diagnosis of AIS. We excluded patients with bilateral (n=21) and brainstem (n=21) AIS. There were 64 patients with left hemisphere AIS including 19 with LVO. There were 67 patients with right hemisphere AIS including 22 with LVO. A score of ≥ 4 points yielded a sensitivity of 84.2 (95% CI = 60.4-96.6) and specificity of 66.7 (51.1-80.0) for left hemisphere LVO compared to a sensitivity of 68.2 (45.1-86.1) and specificity of 73.9 (58.9-85.7) for right hemisphere LVO. For predicting a left hemisphere LVO, the AUC was 0.77 (0.65-0.90) compared to 0.66 (0.50-0.82) for right-sided LVO. Assigning 2 points for abnormal gaze yielded an AUC of 0.78 (0.66-0.91) versus 0.67 (0.52-0.83) for left and right hemisphere LVO, respectively. Conclusions: The EMSA, like the National Institutes of Health Stroke Scale (NIHSS) upon which it is based, is more sensitive to left compared to right hemisphere LVO. More heavily weighting abnormal gaze did not improve the sensitivity of the EMSA for right hemisphere LVO. There is no comparable data on the right versus left hemisphere performance of other prehospital scales. There is a need to develop sensitive tests of right hemisphere dysfunction that are suitable for use in the field.

Sign in / Sign up

Export Citation Format

Share Document