Predicting who has delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage using machine learning approach: a multicenter, retrospective cohort study.

BACKGROUND: Early prediction of delayed cerebral ischemia (DCI) is critical to improving the prognosis of aneurysmal subarachnoid hemorrhage (aSAH). Machine learning (ML) algorithms can learn from intricate information unbiasedly and facilitate the early identification of clinical outcomes. This study aimed to construct and compare the ability of different ML models to predict DCI after aSAH. Then, we identified and analyzed the essential risk of DCI occurrence by preoperative clinical scores and postoperative laboratory test results. METHODS: This was a multicenter, retrospective cohort study. A total of 1039 post-operation patients with aSAH were finally included from three hospitals in China. The training group contained 919 patients, and the test group comprised 120 patients. We used five popular machine-learning algorithms to construct the models. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, precision, and f1 score were used to evaluate and compare the five models. Finally, we performed a Shapley Additive exPlanations analysis for the model with the best performance and significance analysis for each feature. RESULTS: A total of 239 patients with aSAH (23.003%) developed DCI after the operation. Our results showed that in the test cohort, Random Forest (RF) had an AUC of 0.79, which was better than other models. The five most important features for predicting DCI in the RF model were the admitted modified Rankin Scale, D-Dimer, intracranial parenchymal hematoma, neutrophil/lymphocyte ratio, and Fisher score. Interestingly, clamping or embolization for the aneurysm treatment was the fourth button-down risk factor in the ML model. CONCLUSIONS: In this multicenter study, we compared five ML methods, among which RF performed the best in DCI prediction. In addition, the essential risks were identified to help clinicians monitor the patients at high risk for DCI more precisely and facilitate timely intervention.

Ischemic Stroke in Young Tunisian Adults.

INTRODUCTION: Ischemic Stroke in young adults is a real public health problem; it's a major cause of disability, alters quality of life and has a great socio-economic impact. AIM: determine risk factors and specify the etiology of arterial ischemic stroke in young Tunisian adults. METHODS: In this 5 years retrospective study (2015-2020), we included all young adults (18-50 years) admitted for arterial ischemic stroke (AIS). Risk factors were registered and analyzed. All patients were investigated using a standard protocol: biological tests, brain imaging, carotid ultrasound and cardiac assessment. Additional investigations were carried out at the discretion of the treating physician. The cause of ischemic stroke was classified according to the TOAST criteria. RESULTS: We collected 200 patients with AIS. The mean age was 41.37 years ± 6.99. Traditional vascular risk factors were observed in more than 1/4 patients. A definite cause of stroke was identified in 120 patients. Cardio-embolic causes were the most common among our patients (19%) followed by atherosclerosis of the large arteries (11.5%). Other determined etiologies were found in 27.5% of patients. The etiology remained unclear in 40% of cases: undetermined despite complete investigation in 17.5%, undetermined and incompletely investigated 14.5 % and more than one potential pathomechanisms in 8%. CONCLUSION: Through this study, we demonstrated the diversity of etiology of stroke in young Tunisian adults. Changes of lifestyle are responsible for the occurrence of the traditional risk factors at an early age. Rheumatic heart diseases remain a frequent cause of AIS in our area.

Evaluation of CSF 8-iso-prostaglandin F2α and erythrocyte anisocytosis as prognostic biomarkers for delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage.

Delayed cerebral ischemia (DCI) is a serious, life-threatening, complication affecting patients who have survived the initial bleeding from a ruptured intracranial aneurysm. Due to the challenging diagnosis, potential DCI prognostic markers should be of value in clinical practice. According to recent reports isoprostanes and red blood cell distribution (RDW) showed to be promising in this respect. We conducted a prospective study of 27 aSAH patients and control group (n = 8). All patients from the study group were treated within the first day of the initial bleeding. We collected data regarding clinical status and results of biochemical, and radiological examinations. We measured cerebrospinal fluid (CSF) concentration of 8-iso-prostaglandin F2α (F2-IsoP) and RDW on days 1, 3, and 5. Both CSF F2-IsoP level and RDW-SD measured on day 1 were significant predictors of DCI. The receiver operating characteristics curve for DCI prediction based on the multivariate model yielded an area under the curve of 0.924 (95% CI 0.824-1.000, p < 0.001). In our study, the model based on the combination of RDW and the level of isoprostanes in CSF on the first day after the initial bleeding showed a prognostic value for DCI prediction. Further studies are required to validate this observation.

Favorable prognosis in posterior circulation ischemic stroke: Insights from a nationwide stroke databank.

INTRODUCTION: Clinical trials have historically underrepresented patients with posterior circulation ischemic stroke (PCIS). This study aimed to comprehensively assess the clinical characteristics and outcomes of PCIS patients compared to those with anterior circulation ischemic stroke (ACIS). METHODS: A retrospective analysis was conducted using data from the Japan Stroke Data Bank, encompassing 20 years across 130 stroke centers. The study focused on patients diagnosed with PCIS or ACIS. RESULTS: Among 37,069 patients reviewed, 7425 had PCIS, whereas 29,644 had ACIS. PCIS patients were younger and had a lower female representation than ACIS patients. Notably, PCIS patients had more favorable outcomes: 71% achieved a modified Rankin Scale of 0-2 or showed no deterioration at discharge (17 days at the median after admission), compared to 60% for ACIS patients (p < 0.001). Factors associated with an unfavorable outcome in the PCIS subgroup were older age, female sex (assigned at birth), history of hypertension, and higher National Institute of Health Stroke Scale (NIHSS) scores at admission. In both sexes, older age and higher NIHSS scores were negatively associated with favorable outcomes. CONCLUSIONS: PCIS patients demonstrated a more favorable prognosis than ACIS patients. Factors like older age, female sex, and higher NIHSS scores at admission were identified as independent predictors of unfavorable outcomes in PCIS patients. Older age and higher NIHSS scores at admission were common independent negative factors for a favorable outcome regardless of sex.

Baseline Uric Acid Levels and Intravenous Thrombolysis Outcomes in Patients With Acute Ischemic Stroke: A Prospective Cohort Study.

BACKGROUND: The study aimed to investigate the relationship between uric acid (UA) levels and functional outcomes at 3 months in patients with acute ischemic stroke (AIS) who underwent intravenous thrombolysis (IVT). METHODS AND RESULTS: This prospective cohort study included 1001 consecutive patients with AIS who underwent IVT. The correlation between UA levels and post-IVT AIS outcomes was examined. Any nonlinear relationship was assessed using a restricted cubic spline function. The nonlinear P value for the association of UA levels with favorable (modified Rankin Scale [mRS] score ≤2) and excellent (mRS score ≤1) outcomes at 3 months post-IVT were <0.001 and 0.001, respectively. However, for patients with and without hyperuricemia, no evident nonlinear relationship was observed between UA levels and favorable 3-month post-IVT outcomes, with nonlinear P values of 0.299 and 0.207, respectively. The corresponding interaction analysis yielded a P value of 0.001, indicating significant heterogeneity. Similar results were obtained for excellent outcomes at 3 months post-IVT. In the hyperuricemia group, increased UA levels by 50 µmol/L reduced the odds of a favorable 3-month post-AIS outcome (odds ratio [OR], 0.75 [95% CI, 0.57-0.97]). Conversely, in the nonhyperuricemia group, a similar UA increase was linked to higher favorable outcome odds (OR, 1.31 [95% CI, 1.15-1.50]). CONCLUSIONS: An inverted U-shaped nonlinear relationship was observed between UA levels and favorable and excellent outcomes at 3 months in patients with AIS who underwent IVT. Higher UA levels predict favorable outcomes in patients without hyperuricemia but unfavorable outcomes in those with hyperuricemia.

Peripheral blood syndecan-1 levels after mechanical thrombectomy can predict the clinical prognosis of patients with acute ischemic stroke.

BACKGROUND: Previously, we revealed noticeable dynamic fluctuations in syndecan-1 levels in the peripheral blood of post-stroke patients. We further investigated the clinical prognostic value of syndecan-1 as a biomarker of glycoprotein damage in patients with acute ischaemic stroke (AIS). METHODS: We examined 105 patients with acute large vessel occlusion in the anterior circulation, all of whom underwent mechanical thrombectomy (MT). Peripheral blood syndecan-1 levels were measured 1 day after MT, and patients were categorised into favourable and unfavourable prognostic groups based on the 90-day modified Rankin Scale (mRS) score. Additionally, we compared the clinical outcomes between groups with high and low syndecan-1 concentrations. RESULTS: The findings revealed a significantly lower syndecan-1 level in the group with an unfavourable prognosis compared to those with a favourable prognosis (p < 0.01). In the multivariable logistic regression analysis, lower syndecan-1 levels were identified as a predictor of unfavourable prognosis (odds ratio (OR) = 0.965, p = 0.001). Patients displaying low syndecan-1 expression in the peripheral blood (< 29.51 ng/mL) experienced a > twofold increase in the rates of unfavourable prognosis and mortality. CONCLUSIONS: Our study demonstrates that syndecan-1, as an emerging, easily detectable stroke biomarker, can predict the clinical outcomes of patients with AIS. After MT, low levels of syndecan-1 in the peripheral blood on the first day emerged as an independent risk factor for an unfavourable prognosis, suggesting that lower syndecan-1 levels might signify worse clinical presentation and outcomes in stroke patients undergoing this procedure.

Intraoperative neuromonitoring as real-time diagnostic for cerebral ischemia in endovascular treatment of ruptured brain aneurysms.

OBJECTIVE: To evaluate the diagnostic accuracy of intraoperative neurophysiological monitoring (IONM) during endovascular treatment (EVT) of ruptured intracranial aneurysms (rIA). METHODS: IONM and clinical data from 323 patients who underwent EVT for rIA from 2014-2019 were retrospectively reviewed. Significant IONM changes and outcomes were evaluated based on visual review of data and clinical documentation. RESULTS: Of the 323 patients undergoing EVT, significant IONM changes were noted in 30 patients (9.29%) and 46 (14.24%) experienced postprocedural neurological deficits (PPND). 22 out of 30 (73.33%) patients who had significant IONM changes experienced PPND. Univariable analysis showed changes in somatosensory evoked potential (SSEP) and electroencephalogram (EEG) were associated with PPND (p-values: <0.001 and <0.001, retrospectively). Multivariable analysis showed that IONM changes were significantly associated with PPND (Odd ratio (OR) 20.18 (95%CI:7.40-55.03, p-value: <0.001)). Simultaneous changes in both IONM modalities had specificity of 98.9% (95% CI: 97.1%-99.7%). While sensitivity when either modality had a change was 47.8% (95% CI: 33.9%-62.0%) to predict PPND. CONCLUSIONS: Significant IONM changes during EVT for rIA are associated with an increased risk of PPND. SIGNIFICANCE: IONM can be used confidently as a real time neurophysiological diagnostic guide for impending neurological deficits during EVT treatment of rIA.

Duration of Remote Ischemic Conditioning and Outcome in Acute Ischemic Stroke.

BACKGROUND: Remote ischemic conditioning has been found to be effective in improving functional outcomes in acute ischemic stroke. We conducted a post hoc analysis of the RICAMIS (Remote Ischemic Conditioning for Acute Moderate Ischemic Stroke) trial to determine whether long-term remote ischemic conditioning duration after stroke onset is associated with better clinical outcomes in ischemic stroke. METHODS AND RESULTS: Patients from the full analysis set were included in this secondary analysis. The primary outcome was the proportion of patients with an excellent functional outcome at 90 days, defined as a modified Rankin Scale score of 0 to 1. Among the 1776 patients, there were 55 patients in the 1 to 7 days remote ischemic conditioning group, 345 in the 8 to 10 days group, 412 in the 11 to 13 days group, 51 in the 14 to 16 days group, and 913 in the control group. Compared with the control group, a significantly higher proportion of excellent functional outcomes at 90 days was found in the 11 to 13 days remote ischemic conditioning group (adjusted absolute difference, 9.1% [95% CI, 3.7%-14.5%]; P =0.001), which was attenuated in the other groups (adjusted absolute difference in the 8-10 days group, 2.0% [95% CI, -4.0% to 8.0%]; P=0.51; adjusted absolute difference in the 14-16 days group, 7.4% [95% CI, -5.8% to 20.5%]; P=0.27), but compared to the control group, there was lower proportion of excellent functional outcomes in the 1 to 7 days group (adjusted absolute difference, -14.4% [95% CI, -27.8% to 0.0%]; P=0.05). CONCLUSIONS: Among patients with acute moderate ischemic stroke, a higher likelihood of excellent clinical outcome was found in patients with longer duration of remote ischemic conditioning.

Predictive model for the risk of hemorrhagic transformation after rt-PA intravenous thrombolysis in patients with acute ischemic stroke: A systematic review and meta-analysis.

OBJECTIVE: To systematically review the risk prediction model of Hemorrhages Transformation (HT) after intravenous thrombolysis in patients with Acute Ischemic Stroke (AIS). METHODS: Web of Science, The Cochrane Library, PubMed, Embase, CINAHL, CNKI, CBM, WanFang, and VIP were searched from inception to February 25, 2023 for literature related to the risk prediction model for HT after thrombolysis in AIS. RESULTS: A total of 17 included studies contained 26 prediction models, and the AUC of all models at the time of modeling ranged from 0.662 to 0.9854, 16 models had AUC>0.8, indicating that the models had good predictive performance. However, most of the included studies were at risk of bias. the results of the Meta-analysis showed that atrial fibrillation (OR=2.72, 95% CI:1.98-3.73), NIHSS score (OR=1.09, 95% CI:1.07-1.11), glucose (OR=1.12, 95% CI:1.06-1.18), moderate to severe leukoaraiosis (OR=3.47, 95% CI:1.61-7.52), hyperdense middle cerebral artery sign (OR=2.35, 95% CI:1.10-4.98), large cerebral infarction (OR=7.57, 95% CI:2.09-27.43), and early signs of infarction (OR=4.80, 95% CI:1.74-13.25) were effective predictors of HT after intravenous thrombolysis in patients with AIS. CONCLUSIONS: The performance of the models for HT after thrombolysis in patients with AIS in the Chinese population is good, but there is some risk of bias. Future post-intravenous HT conversion prediction models for AIS patients in the Chinese population should focus on predictors such as atrial fibrillation, NIHSS score, glucose, moderate to severe leukoaraiosis, hyperdense middle cerebral artery sign, massive cerebral infarction, and early signs of infarction.

Utilizing RNA sequencing to identify gene expression markers of stroke-causing thrombi origin: A pilot study.

INTRODUCTION: Stroke embolic source have an unknown origin in 30-40% of cases. Mechanical thrombectomy for acute large vessel occlusion stroke has provided us with a method to directly retrieve the thrombi from patients for analysis. By collecting stroke-causing thrombi from known sources, we can then use high-throughput RNA sequencing (RNAseq) technology to directly measure the gene expression signatures of these clots. This may allow us to identify genetic markers to predict the cause of cryptogenic embolism. METHODS: This is a prospective study in which RNAseq was used to analyze cerebral thrombi retrieved by mechanical thrombectomy devices in acute ischemic stroke patients. Samples were separated into two groups based on known stroke thrombus etiology, including Carotid group (patients with ipsilateral >70% carotid stenosis) and Atrial fibrillation (AF) group (patients with atrial fibrillation). Gene expression was compared by RNAseq analysis between the groups. RESULTS: From October 2016 to September 2017, 8 thrombi (4 in Carotid group, 4 in Afib group) were included in this study. There were 131 genes that were significantly up- or down-regulated between the two groups defined as a false discovery rate ≤ 0.05 and a fold change ≥ 2. Twenty-six genes were selected as candidate gene biomarkers based on the criteria in the methods section. Candidate genes HSPA1B, which encodes a heatshock protein, and GPRC5B, which encodes a G-protein, showed the greatest fold differences in expression between the two groups. CONCLUSION: This study has shown that RNA sequencing of acute ischemic stroke thrombi is feasible and indentified potential novel biomarkers for identifying stroke-causing thrombi origin, especially in cryptogenic stroke.

Factors associated with clopidogrel resistance and clinical outcomes in ischemic cerebrovascular disease: A retrospective study.

OBJECTIVE: Clopidogrel resistance may lead to the recurrence of cerebrovascular diseases. We aimed to identify potential factors associated with clopidogrel resistance and evaluate the clinical outcomes of the patients. MATERIALS AND METHODS: In this retrospective study, patients with ischemic cerebrovascular disease treated with clopidogrel were included and classified into 2 groups according to the adenosine diphosphate (ADP)-induced platelet aggregation. Patients with the ADP inhibition rate of <30 % were included in clopidogrel resistance group, otherwise were included in clopidogrel sensitive group. CYP2C19 genotype and other clinical data were analyzed to identify factors and clinical features in the multivariate analysis. The outcomes were vascular events in 6 months. RESULTS: In total, 139 patients were enrolled with 81 (58.27 %) in clopidogrel sensitive group and 58 (41.73 %) in clopidogrel resistance group. Female and CYP2C19 *2*3 carrying were risk factors for clopidogrel resistance, and female was an independent risk factor (OR 2.481, 95 % CI 1.066-5.771, P=0.035). The clopidogrel resistance group showed a higher use rate of argatroban (P=0.030) and a lower arachidonic acid-induced inhibition of platelet aggregation (P=0.036). Clopidogrel resistance was related to the progressing stroke (HR 3.521, 95 % CI 1.352-9.170, P=0.010), but had no influence on the bleeding events (P>0.05). CONCLUSIONS: The risk of clopidogrel resistance increased significantly in female patients. Patients with clopidogrel resistance may have an increased incidence of stroke progression in the acute phase.

Intravenous thrombolysis for ischemic stroke in the posterior circulation: A systematic review and meta-analysis.

OBJECTIVES: Intravenous thrombolysis (IVT) is recommended in patients with ischemic stroke in the anterior and posterior circulation. Neurological outcomes due to posterior circulation strokes (PCS) without treatment remain poor. Our aim was to overview the literature on outcomes of IVT and conservative treatment in PCS, based on a systematic review and meta-analysis. METHODS: A systematic literature search was performed on February 27th 2023. Outcome measures included favorable functional outcome at 90 days (modified Rankin Scale [mRS] 0-2), mortality at 90 days, and symptomatic intracranial hemorrhages (sICH). Weighted averages with DerSimonian-Laird approach was used to analyze the data. Subgroup analyses by time window were performed: standard time window (<4.5 hours after symptom onset) and extended time window (>4.5 hours). Analyses were performed using R. RESULTS: Eight prospective and four retrospective cohort studies were included (n = 1589 patients); no studies with conservative treatment were eligible. The pooled weighted probability regarding favorable functional outcome after IVT was 63 % (95 %CI:0.45-0.78), for mortality 19 % (95 %CI:0.11-0.30), and for sICH 4 % (95 %CI:0.02-0.07). Subgroup analyses showed higher probabilities on achieving favorable functional outcomes for patients treated in the standard (77 %; 95 %CI:0.62-0.88) compared to the extended time window (38 %; 95 %CI:0.29-0.48) with RR = 1.93 (95 %CI:1.66-2.24). Lower probabilities regarding mortality at 90 days and sICH were seen in patients treated in standard compared to extended time window (RR = 0.42, 95 %CI:0.34-0.51 and RR = 0.27, 95 %CI:0.16-0.45, respectively). CONCLUSIONS: IVT in patients with PCS seems to be safe and effective in standard and extended time window. The effect of IVT is higher in the standard time window.

ECG predictors of AF: A systematic review (predicting AF in ischaemic stroke-PrAFIS).

In 25% of patients presenting with embolic stroke, a cause is not determined. Atrial fibrillation (AF) is a commonly identified mechanism of stroke in this population, particularly in older patients. Conventional investigations are used to detect AF, but can we predict AF in this population and generally? We performed a systematic review to identify potential predictors of AF on 12-lead electrocardiogram (ECG). METHOD: We conducted a search of EMBASE and Medline databases for prospective and retrospective cohorts, meta-analyses or case-control studies of ECG abnormalities in sinus rhythm predicting subsequent atrial fibrillation. We assessed quality of studies based on the Newcastle-Ottawa scale and data were extracted according to PRISMA guidelines. RESULTS: We identified 44 studies based on our criteria. ECG patterns that predicted the risk of developing AF included interatrial block, P-wave terminal force lead V1, P-wave dispersion, abnormal P-wave-axis, abnormal P-wave amplitude, prolonged PR interval, left ventricular hypertrophy, QT prolongation, ST-T segment abnormalities and atrial premature beats. Furthermore, we identified that factors such as increased age, high CHADS-VASC, chronic renal disease further increase the positive-predictive value of some of these parameters. Several of these have been successfully incorporated into clinical scoring systems to predict AF. CONCLUSION: There are several ECG abnormalities that can predict AF both independently, and with improved predictive value when combined with clinical risk factors, and if incorporated into clinical risk scores. Improved and validated predictive models could streamline selection of patients for cardiac monitoring and initiation of oral anticoagulants.

Cumulative Exposure to Oxidized Low-density Lipoprotein is a Potential Predictor for Prognosis in Acute Ischemic Stroke: A Cohort Study.

BACKGROUND: Oxidized Low-Density Lipoprotein (ox-LDL) is crucial in the recrudescence and prognosis of acute ischemic stroke (AIS). We aimed to probe into the influence of cumulative ox-LDL exposure on the 90-day prognosis of AIS. METHODS: Patients with AIS were recruited in this research. AIS severity at admission was estimated with infarct volumes and National Institute of Health Stroke Scale (NIHSS) scores. AIS prognosis was assessed using Modified Rankin Scale (mRS) scores at 90 days and the change in NIHSS scores from admission to discharge. Cumulative ox-LDL exposure was defined as ox-LDL level (pg/mL) multiplied by age(y). Multivariate logistic regression analysis was employed to reveal the correlation between exposure factors and the prognosis of AIS. The prognostic prediction ability of cumulative ox-LDL exposure was compared with cumulative LDL exposure by the receiver operating characteristic curve (ROC). RESULTS: Higher cumulative ox-LDL exposure was related to worse prognosis, including neurological worsening at discharge (NIHSS increasing more than 2 points) (OR = 3.02, 95% CI, 1.30-6.98, P = 0.01) and poor functional prognosis at 90 days (mRS ≥ 3) (OR = 21.21, 95% CI, 4.72-95.36, P < 0.001). As multivariate regression analysis showed, significantly increased cumulative ox-LDL exposure was relevant to poor functional prognosis at 90 days (OR = 9.92, 95% CI, 1.23-79.76, P = 0.031), but not with neurological worsening at discharge (P = 0.414). ROC curve revealed that cumulative ox-LDL exposure had a higher predictive value (AUC = 0.843, P < 0.001) for functional prognosis of AIS than cumulative LDL exposure (AUC = 0.629, P = 0.023). CONCLUSION: Cumulative ox-LDL exposure has a positive correlation with poor prognosis at 90 days of AIS, and has a more accurate predictive ability than cumulative LDL exposure.

Asymptomatic Intracerebral Hemorrhage Following Endovascular Stroke Therapy Is Not Benign: A Systematic Review and Meta-Analysis.

BACKGROUND: Asymptomatic intracerebral hemorrhage (aICH) occurs in approximately 35% of patients with acute ischemic stroke after endovascular thrombectomy. Unlike symptomatic ICH, studies evaluating the effect of aICH on outcomes have been inconclusive. We performed a systematic review and meta-analysis to evaluate the long-term effects of postendovascular thrombectomy aICH. METHODS AND RESULTS: The meta-analysis protocol was submitted to the International Prospective Register of Systematic Reviews a priori. PubMed, Scopus, and Web of Science were searched from inception through September 2023, yielding 312 studies. Two authors independently reviewed all abstracts. Included studies contained adult patients with ischemic stroke undergoing endovascular thrombectomy with follow-up imaging assessment of ICH reporting comparative outcomes according to aICH versus no ICH. After screening, 60 papers were fully reviewed, and 10 studies fulfilled inclusion criteria (n=5723 patients total, 1932 with aICH). Meta-analysis was performed using Cochrane RevMan v5.4. Effects were estimated by a random-effects model to estimate summary odds ratio (OR) of the effect of aICH versus no ICH on primary outcomes of 90-day modified Rankin Scale 3 to 6 and mortality. The presence of aICH was associated with a higher odds of 90-day mRS 3 to 6 (OR, 2.17 [95% CI, 1.81-2.60], P<0.0001, I2 46% Q 19.15) and mortality (OR, 1.72 [95% CI, 1.17-2.53], P:0.005, I2 79% Q 27.59) compared with no ICH. This difference was maintained following subgroup analysis according to hemorrhage classification and recanalization status. CONCLUSIONS: The presence of aICH is associated with worse 90-day functional outcomes and higher mortality. Further studies to evaluate the factors predicting aICH and treatments aimed at reducing its occurrence are warranted.

SCANED: Siamese collateral assessment network for evaluation of collaterals from ischemic damage.

This study conducts collateral evaluation from ischemic damage using a deep learning-based Siamese network, addressing the challenges associated with a small and imbalanced dataset. The collateral network provides an alternative oxygen and nutrient supply pathway in ischemic stroke cases, influencing treatment decisions. Research in this area focuses on automated collateral assessment using deep learning (DL) methods to expedite decision-making processes and enhance accuracy. Our study employed a 3D ResNet-based Siamese network, referred to as SCANED, to classify collaterals as good/intermediate or poor. Utilizing non-contrast computed tomography (NCCT) images, the network automates collateral identification and assessment by analyzing tissue degeneration around the ischemic site. Relevant features from the left/right hemispheres were extracted, and Euclidean Distance (ED) was employed for similarity measurement. Finally, dichotomized classification of good/intermediate or poor collateral is performed by SCANED using an optimal threshold derived from ROC analysis. SCANED provides a sensitivity of 0.88, a specificity of 0.63, and a weighted F1 score of 0.86 in the dichotomized classification.

Investigating the Impact on Long-Term Outcomes and the Necessity of Hereditary Thrombophilia Screening in Presumed or Perinatal Arterial Ischemic Stroke.

This study aimed to investigate the influence of prothrombotic risk factors on long-term outcomes of patients with perinatal arterial ischemic stroke. The study was conducted through an analysis of monitoring results that were regularly maintained for approximately 20 years at a tertiary stroke-monitoring center. The study assessed prothrombotic risk factors, radiological area of involvement, clinical presentation, treatments, clinical outcomes, and long-term outcomes of the 48 patients included in the study, with a mean monitoring time of 77.6 ± 45.7 months (range: 6-204). Our results showed that the presence of prothrombotic risk factors did not affect long-term outcomes. However, patients with middle cerebral artery infarction had the highest risk of developing cerebral palsy, whereas those with presumed stroke had the highest risk of developing epilepsy. This study suggests that prothrombotic risk factors should not be evaluated during the acute stage unless there is a strong suspicion of the patient's history, and prevention or early diagnosis of presumed stroke patients will positively impact their long-term prognosis.

Sex Differences in Prehospital Identification of Large Vessel Occlusion in Patients With Suspected Stroke.

BACKGROUND: Differences in clinical presentation of acute ischemic stroke between men and women may affect prehospital identification of anterior circulation large vessel occlusion (aLVO). We assessed sex differences in diagnostic performance of 8 prehospital scales to detect aLVO. METHODS: We analyzed pooled individual patient data from 2 prospective cohort studies (LPSS [Leiden Prehospital Stroke Study] and PRESTO [Prehospital Triage of Patients With Suspected Stroke Study]) conducted in the Netherlands between 2018 and 2019, including consecutive patients ≥18 years suspected of acute stroke who presented within 6 hours after symptom onset. Ambulance paramedics assessed clinical items from 8 prehospital aLVO detection scales: Los Angeles Motor Scale, Rapid Arterial Occlusion Evaluation, Cincinnati Stroke Triage Assessment Tool, Cincinnati Prehospital Stroke Scale, Prehospital Acute Stroke Severity, gaze-face-arm-speech-time, Conveniently Grasped Field Assessment Stroke Triage, and Face-Arm-Speech-Time Plus Severe Arm or Leg Motor Deficit. We assessed the diagnostic performance of these scales for identifying aLVO at prespecified cut points for men and women. RESULTS: Of 2358 patients with suspected stroke (median age, 73 years; 47% women), 231 (10%) had aLVO (100/1114 [9%] women and 131/1244 [11%] men). The area under the curve of the scales ranged from 0.70 (95% CI, 0.65-0.75) to 0.77 (95% CI, 0.73-0.82) in women versus 0.69 (95% CI, 0.64-0.73) to 0.75 (95% CI, 0.71-0.79) in men. Positive predictive values ranged from 0.23 (95% CI, 0.20-0.27) to 0.29 (95% CI, 0.26-0.31) in women versus 0.29 (95% CI, 0.24-0.33) to 0.37 (95% CI, 0.32-0.43) in men. Negative predictive values were similar (0.95 [95% CI, 0.94-0.96] to 0.98 [95% CI, 0.97-0.98] in women versus 0.94 [95% CI, 0.93-0.95] to 0.96 [95% CI, 0.94-0.97] in men). Sensitivity of the scales was slightly higher in women than in men (0.53 [95% CI, 0.43-0.63] to 0.76 [95% CI, 0.68-0.84] versus 0.49 [95% CI, 0.40-0.57] to 0.63 [95% CI, 0.55-0.73]), whereas specificity was lower (0.79 [95% CI, 0.76-0.81] to 0.87 [95% CI, 0.84-0.89] versus 0.82 [95% CI, 0.79-0.84] to 0.90 [95% CI, 0.88-0.91]). Rapid arterial occlusion evaluation showed the highest positive predictive values in both sexes (0.29 in women and 0.37 in men), reflecting the different event rates. CONCLUSIONS: aLVO scales show similar diagnostic performance in both sexes. The rapid arterial occlusion evaluation scale may help optimize prehospital transport decision-making in men as well as in women with suspected stroke.