Stroke Mimics in the Acute Setting: Role of Multimodal CT Protocol

SMART: Development and Application of a Multimodal Multi-organ Trauma Screening Model for Abdominal Injuries in Emergency Settings

RATIONALE AND OBJECTIVES

Effective trauma care in emergency departments necessitates rapid diagnosis by interdisciplinary teams using various medical data. This study constructed a multimodal diagnostic model for abdominal trauma using deep learning on non-contrast computed tomography (CT) and unstructured text data, enhancing the speed and accuracy of solid organ assessments.

MATERIALS AND METHODS

Data were collected from patients undergoing abdominal CT scans. The SMART model (Screening for Multi-organ Assessment in Rapid Trauma) classifies trauma using text data (SMART_GPT), non-contrast CT scans (SMART_Image), or both. SMART_GPT uses the GPT-4 embedding API for text feature extraction, whereas SMART_Image incorporates nnU-Net and DenseNet121 for segmentation and classification. A composite model was developed by integrating multimodal data via logistic regression of SMART_GPT, SMART_Image, and patient demographics (age and gender).

RESULTS

This study included 2638 patients (459 positive, 2179 negative abdominal trauma cases). A trauma-based dataset included 1006 patients with 1632 real continuous data points for testing. SMART_GPT achieved a sensitivity of 81.3% and an area under the receiver operating characteristic curve (AUC) of 0.88 based on unstructured text data. SMART_Image exhibited a sensitivity of 87.5% and an AUC of 0.81 on non-contrast CT data, with the average sensitivity exceeding 90% at the organ level. The integrated SMART model achieved a sensitivity of 93.8% and an AUC of 0.88. In emergency department simulations, SMART reduced waiting times by over 64.24%.

CONCLUSION

SMART provides rapid, objective trauma diagnostics, improving emergency care efficiency, reducing patient wait times, and enabling multimodal screening in diverse emergency contexts.

Assessment of collateral circulation in patients with anterior circulation stroke treated with mechanical thrombectomy as a predictor of long-term clinical outcomes

BackgroundMechanical thrombectomy (MT) is the most effective treatment for large vessel occlusion (LVO) stroke. Despite this treatment, clinical outcomes are highly variable.PurposeTo evaluate the role of collateral circulation in patients undergoing MT as a determinant of clinical outcome, especially in the long term.Material and MethodsThe study included 80 patients who underwent MT for LVO of the anterior cerebral circulation. Patient data were collected on demographics, baseline neurological status, imaging studies (including ASPECTS and collateral circulation score), and clinical status of the patients as determined by NIHSS at discharge and by modified Rankin Scale (mRS) score at 3 and 12 months postoperatively.ResultsPatients with good collateral circulation were compared to the group with poor collateral circulation: they had significantly lower NIHSS at 24 h (median NIHSS 8 vs. 16; P < 0.001) and at the time of discharge (median NIHSS 3.5 vs. 13; P < 0.001). At 3 months, patients with good collateral circulation had a significantly higher chance of achieving a good functional outcome (mRS = 0-2) (62.75% vs. 10.34%; P < 0.001) and had a lower mortality (13.73% vs. 41.38%; P = 0.005). The benefits of good collateral circulation extended into the long term. At 12 months, patients with good collateral circulation were significantly more likely to have good functional outcome (mRS = 0-2) (60.78% vs. 10.34%; P < 0.001) and lower mortality (19.61% vs. 44.83%; P = 0.017).ConclusionGood collateral circulation increases the likelihood of favorable outcome in MT-treated stroke patients at discharge, 3 months, and 12 months.

Acute Moderate Hemodynamic Stroke Secondary to Large Vessel Stenosis: A Case Series Exploring Imaging Characteristics and Endovascular Treatment Outcomes

BACKGROUND

This study aimed to characterize the imaging features and the outcomes of endovascular treatment (EVT) in patients with moderate hemodynamic stroke due to large vessel stenosis.

METHODS

Data from patients with moderate hemodynamic stroke due to large vessel stenosis who underwent EVT at a single center between January 2021 and June 2024 were retrospectively analyzed. Hemodynamic stroke was defined as infarction in the watershed area on diffusion-weighted imaging and hypoperfusion on perfusion-weighted imaging. Demographics, National Institutes of Health Stroke Scale (NIHSS), imaging findings, cerebral circulation time (CCT; the interval from arterial origin visualization to completion of the intracranial arterial phase), and EVT details were collected. The primary outcome was functional independence, defined as a modified Rankin Scale score of 0-2 at 90-day post-stroke.

RESULTS

Among 313 patients treated with EVT, 14 (4.4%) were diagnosed with moderate hemodynamic stroke secondary to large vessel stenosis. The mean age was 64.6±11.8 years, and the median NIHSS score was 9 (range, 6-12). Stenosis was predominantly located at the origin of the vertebral artery in 12 cases and at the origin of the internal carotid artery in 2 cases. All patients underwent stent angioplasty, leading to a significant reduction in median CCT from 3.0 s preoperatively to 1.43 s postoperatively (P=0.00001). At 90-day post-stroke, 78.6% of patients (11/14) achieved a functional independence.

CONCLUSION

Moderate hemodynamic stroke caused by large vessel stenosis was relatively rare but could be safely and effectively treated with EVT.

Time is brain: detection of nonconvulsive seizures and status epilepticus during acute stroke evaluation using point-of-care electroencephalography

OBJECTIVES

Seizures are both a common mimic and a potential complication of acute stroke. Although EEG can be helpful to evaluate this differential diagnosis, conventional EEG infrastructure is resource-intensive and unable to provide timely monitoring to match the emergent context of a stroke code. We aimed to evaluate the real-world use and utility of a point-of-care EEG device as an adjunct to acute stroke evaluation.

MATERIALS AND METHODS

We performed a retrospective observational cohort study at a tertiary care community teaching hospital by identifying patients who underwent point-of-care EEG monitoring using Rapid Response EEG system (Ceribell Inc., Sunnyvale, CA) during stroke code evaluation of acute neurological deficits during the study period from January 1, 2020 to December 31, 2020. We assessed the frequency of seizures and highly epileptiform patterns among patients with either confirmed strokes or stroke mimics.

RESULTS

Point-of-care EEG monitoring was used in the wake of a stroke code in 70 patients. Of these, neuroimaging and clinical information resulted in a diagnosis of stroke in 38 patients (28 ischemic, 6 hemorrhagic, 4 transient ischemic attack; median NIHSS score of 6.5 [IQR 2.0-12.0]) and absence of any stroke in 32 patients. Point-of-care EEG detected seizures and highly epileptiform patterns in 6 (15.8 %) stroke patients and 11 (34.4 %) stroke-mimic patients, including 2 patients with persistent expressive aphasia due to repeated focal seizures.

CONCLUSIONS

Point-of-care EEG has utility for detecting nonconvulsive seizures in patients undergoing acute stroke evaluations.

Development, assessment and validation of a novel nomogram model for predicting stroke mimics in stroke center：A single-center observational study

BACKGROUND

Early recognition and prediction of stroke mimics (SM) can avoid inappropriate recanalization therapy and delay in the management of SM etiology. The purpose of this study is to screen the predictors for SM and develop a novel predictive nomogram model for predicting SM. Meanwhile, the diagnostic performance of the nomogram model was evaluated and validated. The diagnostic efficacy of the nomogram model was also compared with four other SM structured scales.

METHODS

The clinical data of eligible patients were retrospectively enrolled as training datasets from January 2020 to December 2021; and the clinical data of eligible patients were prospectively enrolled as validation datasets from February to December 2022 in stroke center, Shengjing hospital, respectively. Univariate analysis and Lasso regression were used to select the optimal predictors for the training set, and a nomogram model was constructed by multivariate logistics regression, predictive scoring based on nomogram model is performed for each subject suffering from suspected acute ischemic stroke. Area under the curve (AUC), Hosmer-Lemeshow goodness-of-fit test, Calibration curve, decision curve analysis (DCA), clinical impact curve (CIC) analysis and bootstrap sampling were performed to assess and validate the predictive performance and clinical utility of the nomogram model, and the DeLong test was used to compare the overall diagnostic performance of the nomogram model with the other four structured SM scales. The Delong test was also conducted to assess the external reliability of the SM nomogram model by comparing the predictive diagnostic performance of the validation set with the training set. Additionally, the Calibration curve was utilized to evaluate the diagnostic calibration capability of the SM nomogram model in the validation set.

RESULTS

703 eligible patients (68 with SM, accounting for 9.7 %) were assigned to the training set, while 301 patients (26 with SM, accounting for 8.6 %) were assigned to the validation set. A nomogram model was then developed using these six parameters (SBP, history of epilepsy, isolated dizziness, isolated sensory impairment, headache, and absence of speech impairment symptoms), a dynamic web-based version of the nomogram was subsequently created. Comparing with four other scales, the nomogram model showed the highest overall diagnostic performance (AUC = 0.929, 95%CI = 0.908-0.947). The Hosmer-Lemeshow goodness-of-fit test was conducted to assess the agreement between the predicted SM values from the model and the observed SM values. The results of the test indicated a favorable consistency (χ2 = 9.299, P = 0.3177) between the predicted and observed SM. The results obtained from the analysis of the Calibration curve, DCA curve, and CIC analysis suggested that the nomogram possesses a favorable predictive capacity and superior clinical usefulness. Furthermore, the external validation demonstrated that there is no significant difference in the overall predictive diagnostic performance between the validation set and training set (0.929 vs 0.910, P > 0.05), thereby confirming the favorable stability of the nomogram model.

CONCLUSION

Our study firstly proposed a nomogram prediction approach based on the clinical features of SM, which could effectively predict the occurrence of SM. The utilization of the nomogram in stroke center proves advantageous for the identification and evaluation of SM, thereby enhancing diagnostic decision-making and strategies employed for suspected acute stroke patients.

Thrombolysis in Stroke Mimics: Comprehensive Stroke Centers vs Telestroke Sites

BACKGROUND

Hyperacute treatment of acute stroke may lead to thrombolysis in stroke mimics (SM). Our aim was to determine the frequency of thrombolysis in SM in primary stroke centers (PSC) dependent on telestroke versus comprehensive stroke centers (CSC).

METHOD

Retrospective review of prospectively collected data from the Quality improvement and Clinical Research (QuICR) registry, the Discharge Abstract Database (DAD), and The National Ambulatory Care Reporting System (NACRS) of consecutive patients treated with intravenous thrombolysis for acute ischemic stroke in Alberta (Canada) from April 2016 to March 2021.

RESULT

A total of 2471 patients who received thrombolysis were included. Linking the QuICR registry to DAD 169 (6.83%) patients were identified as SM; however, on our review of the records, only 112 (4.53%) were actual SM. SMs were younger with a mean age of 61.66 (±16.15) vs 71.08 (±14.55) in stroke. National Institute of Health Stroke Scale was higher in stroke with a median (IQR) of 10 (5-17) vs 7 (5-10) in SM. Only one patient (0.89 %) in SM groups had a small parenchymal hemorrhage versus 155 (6.57%) stroke patients had a parenchymal hemorrhage. There was no death among patients of thrombolysed SM during hospitalization versus 276 (11.69%) in stroke. There was no significant difference in the rate of SM among thrombolysed patients between PSC 27 (5.36%) versus CSC 85 (4.3%) (P = 0.312). The most responsible diagnosis of SM was migraine/migraine equivalent, functional disorder, seizure, and delirium.

CONCLUSION

The diagnosis of SM may not always be correct when the information is extracted from databases. The rate of thrombolysis in SM via telestroke is similar to treatment in person at CSC.

Predicting Hypoperfusion Lesion and Target Mismatch in Stroke from Diffusion-weighted MRI Using Deep Learning

Background Perfusion imaging is important to identify a target mismatch in stroke but requires contrast agents and postprocessing software. Purpose To use a deep learning model to predict the hypoperfusion lesion in stroke and identify patients with a target mismatch profile from diffusion-weighted imaging (DWI) and clinical information alone, using perfusion MRI as the reference standard. Materials and Methods Imaging data sets of patients with acute ischemic stroke with baseline perfusion MRI and DWI were retrospectively reviewed from multicenter data available from 2008 to 2019 (Imaging Collaterals in Acute Stroke, Diffusion and Perfusion Imaging Evaluation for Understanding Stroke Evolution 2, and University of California, Los Angeles stroke registry). For perfusion MRI, rapid processing of perfusion and diffusion software automatically segmented the hypoperfusion lesion (time to maximum, ≥6 seconds) and ischemic core (apparent diffusion coefficient [ADC], ≤620 × 10-6 mm2/sec). A three-dimensional U-Net deep learning model was trained using baseline DWI, ADC, National Institutes of Health Stroke Scale score, and stroke symptom sidedness as inputs, with the union of hypoperfusion and ischemic core segmentation serving as the ground truth. Model performance was evaluated using the Dice score coefficient (DSC). Target mismatch classification based on the model was compared with that of the clinical-DWI mismatch approach defined by the DAWN trial by using the McNemar test. Results Overall, 413 patients (mean age, 67 years ± 15 [SD]; 207 men) were included for model development and primary analysis using fivefold cross-validation (247, 83, and 83 patients in the training, validation, and test sets, respectively, for each fold). The model predicted the hypoperfusion lesion with a median DSC of 0.61 (IQR, 0.45-0.71). The model identified patients with target mismatch with a sensitivity of 90% (254 of 283; 95% CI: 86, 93) and specificity of 77% (100 of 130; 95% CI: 69, 83) compared with the clinical-DWI mismatch sensitivity of 50% (140 of 281; 95% CI: 44, 56) and specificity of 89% (116 of 130; 95% CI: 83, 94) (P < .001 for all). Conclusion A three-dimensional U-Net deep learning model predicted the hypoperfusion lesion from diffusion-weighted imaging (DWI) and clinical information and identified patients with a target mismatch profile with higher sensitivity than the clinical-DWI mismatch approach. ClinicalTrials.gov registration nos. NCT02225730, NCT01349946, NCT02586415 © RSNA, 2022 Supplemental material is available for this article. See also the editorial by Kallmes and Rabinstein in this issue.

Clinical application of brain perfusion imaging in detecting stroke mimics: A review

Stroke mimics constitute a significant proportion of patients with suspected acute ischemic stroke. These conditions may resemble acute ischemic stroke and demonstrate abnormalities on perfusion imaging sequences. The most common stroke mimics include seizure/epilepsy, migraine with aura, brain tumors, functional disorders, infectious encephalopathies, Wernicke's encephalopathy, and metabolic abnormalities. Brain perfusion imaging techniques, particularly computed tomography perfusion and magnetic resonance perfusion, are being widely used in routine clinical practice for treatment selection in patients presenting with large vessel occlusion. At the same time, the utilization of these imaging modalities enables the opportunity to better diagnose patients with stroke mimics in a time-sensitive setting, leading to appropriate management, decision-making, and resource allocation. In this review, we describe patterns of perfusion abnormalities that could discriminate patients with stroke mimics from those with acute ischemic stroke and provide specific case examples to illustrate these perfusion abnormalities. In addition, we discuss the challenges associated with interpretation of perfusion images in stroke-related pathologies. In general, perfusion imaging can provide additional information in some cases-when used in combination with conventional magnetic resonance imaging and computed tomography-and might help in detecting stroke mimics among patients who present with acute onset focal neurological symptoms.