Early prediction of delayed cerebral ischemia after subarachnoid hemorrhage: development and validation of a practical risk chart

Integrating Clinical Data and Radiomics and Deep Learning Features for End-to-End Delayed Cerebral Ischemia Prediction on Noncontrast CT

BACKGROUND AND PURPOSE

Delayed cerebral ischemia is hard to diagnose early due to gradual, symptomless development. This study aimed to develop an automated model for predicting delayed cerebral ischemia following aneurysmal SAH on NCCT.

MATERIALS AND METHODS

This retrospective study included 400 patients with aneurysmal SAH (156 with delayed cerebral ischemia) who underwent NCCT. The study used ATT-Deeplabv3+ for automatically segmenting hemorrhagic regions using semisupervised learning. Principal component analysis was used for reducing the dimensionality of deep learning features extracted from the average pooling layer of ATT-DeepLabv3+. The classification model integrated clinical data, radiomics, and deep learning features to predict delayed cerebral ischemia. Feature selection involved Pearson correlation coefficients, least absolute shrinkage, and selection operator regression. We developed models based on clinical features, clinical-radiomics, and a combination of clinical, radiomics, and deep learning. The study selected logistic regression, Naive Bayes, Adaptive Boosting (AdaBoost), and multilayer perceptron as classifiers. The performance of segmentation and classification models was evaluated on their testing sets using the Dice similarity coefficient for segmentation, and the area under the receiver operating characteristic curve (AUC) and calibration curves for classification.

RESULTS

The segmentation process achieved a Dice similarity coefficient of 0.91 and the average time of 0.037 s/image. Seventeen features were selected to calculate the radiomics score. The clinical-radiomics-deep learning model with multilayer perceptron achieved the highest AUC of 0.84 (95% CI, 0.72-0.97), which outperformed the clinical-radiomics model (P = .002) and the clinical features model (P = .001) with multilayer perceptron. The performance of clinical-radiomics-deep learning model using AdaBoost was significantly superior to its clinical-radiomics model (P = .027). The performance of the clinical-radiomics-deep learning model and the clinical-radiomics model with logistic regression notably exceeded that of the model based solely on clinical features (P = .028; P = .046). The AUC of the clinical-radiomics-deep learning model with multilayer perceptron (P < .001) and the clinical-radiomics model with logistic regression (P = .046) were significantly higher than the clinical model with logistic regression. Of all models, the clinical-radiomics-deep learning model with multilayer perceptron showed best calibration.

CONCLUSIONS

The proposed 2-stage end-to-end model not only achieves rapid and accurate segmentation but also demonstrates superior diagnostic performance with high AUC values and good calibration in the clinical-radiomics-deep learning model, suggesting its potential to enhance delayed cerebral ischemia detection and treatment strategies.

Bacterial Meningitis Following Aneurysmal Subarachnoid Hemorrhage and Its Association with Cerebral Vasospasm

Aneurysmal subarachnoid hemorrhage (aSAH) is a critical condition with high in-hospital mortality rates. Delayed cerebral ischemia (DCI), a secondary complication associated with aSAH, can also contribute to morbidity and mortality. Although draining the hematoma from the subarachnoid space has been considered effective in preventing DCI, the placement of a drainage system could increase the risk of bacterial meningitis and ventriculitis. This study aimed to examine the association between meningitis following aSAH and the occurrence of DCI, focusing on the role of cerebral vasospasm. Patients who underwent endovascular coiling or surgical clipping for aSAH from April 2001 to March 2022 were included in this study, while those who did not undergo postoperative drainage were excluded. The patient's clinical characteristics, treatment modalities, and outcomes were then analyzed, after which logistic regression was used to assess the odds ratios (OR) for DCI. A total of 810 patients with aSAH were included in this study. Meningitis following aSAH was identified as an independent factor associated with DCI (odds ratio 5.0 [95% confidence intervals (CI) 2.3-11]). Other significant factors were female sex (odds ratio 1.5 [95% CI 0.89-2.5]) and surgical clipping (odds ratio 2.1 [95% CI 1.3-3.4]). This study demonstrated a significant association between meningitis following aSAH and the development of DCI, suggesting that the inflammatory environment associated with meningitis may contribute to cerebral vasospasm. Early recognition and treatment of meningitis in patients with aSAH could reduce the risk of DCI and improve patient outcomes.

Beyond nimodipine: advanced neuroprotection strategies for aneurysmal subarachnoid hemorrhage vasospasm and delayed cerebral ischemia

The clinical management of aneurysmal subarachnoid hemorrhage (SAH)-associated vasospasm remains a challenge in neurosurgical practice, with its prevention and treatment having a major impact on neurological outcome. While considered a mainstay, nimodipine is burdened by some non-negligible limitations that make it still a suboptimal candidate of pharmacotherapy for SAH. This narrative review aims to provide an update on the pharmacodynamics, pharmacokinetics, overall evidence, and strength of recommendation of nimodipine alternative drugs for aneurysmal SAH-associated vasospasm and delayed cerebral ischemia. A PRISMA literature search was performed in the PubMed/Medline, Web of Science, ClinicalTrials.gov, and PubChem databases using a combination of the MeSH terms "medical therapy," "management," "cerebral vasospasm," "subarachnoid hemorrhage," and "delayed cerebral ischemia." Collected articles were reviewed for typology and relevance prior to final inclusion. A total of 346 articles were initially collected. The identification, screening, eligibility, and inclusion process resulted in the selection of 59 studies. Nicardipine and cilostazol, which have longer half-lives than nimodipine, had robust evidence of efficacy and safety. Eicosapentaenoic acid, dapsone and clazosentan showed a good balance between effectiveness and favorable pharmacokinetics. Combinations between different drug classes have been studied to a very limited extent. Nicardipine, cilostazol, Rho-kinase inhibitors, and clazosentan proved their better pharmacokinetic profiles compared with nimodipine without prejudice with effective and safe neuroprotective role. However, the number of trials conducted is significantly lower than for nimodipine. Aneurysmal SAH-associated vasospasm remains an area of ongoing preclinical and clinical research where the search for new drugs or associations is critical.

Early Intravenous Magnesium Sulfate and Its Impact on Cerebral Vasospasm as well as Delayed Cerebral Ischemia in Aneurysmal Subarachnoid Hemorrhage: A Retrospective Matched Case-Control Analysis

BACKGROUND

Magnesium sulfate (MgSO4) is a potential neuroprotective agent for patients with aneurysmal subarachnoid hemorrhage (SAH). We analyzed the effect of early application of intraoperative intravenous MgSO4 and compared cerebral vasospasm (CV), delayed cerebral ischemia (DCI), and neurological outcome in 2 patient cohorts.

METHODS

A retrospective matched-pair analysis from patients at a single center in Germany was performed without (group A) and with (group B) MgSO4 application <24 hours after diagnosis. Pairs were matched according to the known risk factors for DCI and CV (age, Fisher grade, smoking, severity of SAH). Incidence of CV and DCI and neurological outcome using the modified Rankin Scale score 3 and 12 months after SAH were recorded.

RESULTS

The inclusion criteria were met by 196 patients. After risk stratification, 48 patients were included in the final analysis (age 54.2 ± 8.1 years; 30 women and 18 men) and were assigned to group A (n = 24) or group B (n = 24). CV occurred less frequently in group B (33%) than in group A (46%). Likewise, DCI was present in 13% in group B compared with 42% in group A. After 12 months, 22 patients in group B had a favorable functional outcome (modified Rankin Scale score 0-3) compared with 15 patients in group A.

CONCLUSIONS

In this study, the incidence of CV and DCI was lower in patients receiving intravenous MgSO4 within 24 hours after aneurysmal SAH onset. Favorable functional outcome was more likely in the MgSO4 group after 12 months of follow-up.

Early localization of tissue at risk for delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage: blood distribution on initial imaging vs early CT perfusion

OBJECTIVE

Delayed cerebral ischemia (DCI) is a potentially reversible adverse event after aneurysmal subarachnoid hemorrhage (aSAH), when early detected and treated. Computer tomography perfusion (CTP) is used to identify the tissue at risk for DCI. In this study, the predictive power of early CTP was compared with that of blood distribution on initial CT for localization of tissue at risk for DCI.

METHODS

A consecutive patient cohort with aSAH treated between 2012 and 2020 was retrospectively analyzed. Blood distribution on CT was semi-quantitatively assessed with the Hijdra-score. The vessel territory with the most surrounding blood and the one with perfusion deficits on CTP performed on day 3 after ictus were considered to be at risk for DCI, respectively.

RESULTS

A total of 324 patients were included. Delayed infarction occurred in 17% (56/324) of patients. Early perfusion deficits were detected in 82% (46/56) of patients, 85% (39/46) of them developed infarction within the predicted vessel territory at risk. In 46% (25/56) a vessel territory at risk was reliably determined by the blood distribution. For the prediction of DCI, blood amount/distribution was inferior to CTP. Concerning the identification of "tissue at risk" for DCI, a combination of both methods resulted in an increase of sensitivity to 64%, positive predictive value to 58%, and negative predictive value to 92%.

CONCLUSIONS

Regarding the DCI-prediction, early CTP was superior to blood amount/distribution, while a consideration of subarachnoid blood distribution may help identify the vessel territories at risk for DCI in patients without early perfusion deficits.

Pharmacological Prevention of Delayed Cerebral Ischemia in Aneurysmal Subarachnoid Hemorrhage

BACKGROUND

Causes of morbidity and mortality following aneurysmal subarachnoid hemorrhage (aSAH) include early brain injury and delayed neurologic deterioration, which may result from delayed cerebral ischemia (DCI). Complex pathophysiological mechanisms underlie DCI, which often includes angiographic vasospasm (aVSP) of cerebral arteries.

METHODS

Despite the study of many pharmacological therapies for the prevention of DCI in aSAH, nimodipine-a dihydropyridine calcium channel blocker-remains the only drug recommended universally in this patient population. A common theme in the research of preventative therapies is the use of promising drugs that have been shown to reduce the occurrence of aVSP but ultimately did not improve functional outcomes in large, randomized studies. An example of this is the endothelin antagonist clazosentan, although this agent was recently approved in Japan.

RESULTS

The use of the only approved drug, nimodipine, is limited in practice by hypotension. The administration of nimodipine and its counterpart nicardipine by alternative routes, such as intrathecally or formulated as prolonged release implants, continues to be a rational area of study. Additional agents approved in other parts of the world include fasudil and tirilazad.

CONCLUSIONS

We provide a brief overview of agents currently being studied for prevention of aVSP and DCI after aSAH. Future studies may need to identify subpopulations of patients who can benefit from these drugs and perhaps redefine acceptable outcomes to demonstrate impact.

Diagnosis of Delayed Cerebral Ischemia in Patients with Aneurysmal Subarachnoid Hemorrhage and Triggers for Intervention

INTRODUCTION

Delayed cerebral ischemia (DCI) is a major determinant for poor neurological outcome after aneurysmal subarachnoid hemorrhage (aSAH). Detection and treatment of DCI is a key component in the neurocritical care of patients with aSAH after initial aneurysm repair.

METHODS

Narrative review of the literature.

RESULTS

Over the past 2 decades, there has been a paradigm shift away from macrovascular (angiographic) vasospasm as a main diagnostic and therapeutic target. Instead, the pathophysiology of DCI is hypothesized to derive from several proischemic pathomechanisms. Clinical examination remains the most reliable means for monitoring and treatment of DCI, but its value is limited in comatose patients. In such patients, monitoring of DCI is usually based on numerous neurophysiological and/or radiological diagnostic modalities. Catheter angiography remains the gold standard for the detection of macrovascular spasm. Computed tomography (CT) angiography is increasingly used instead of catheter angiography because it is less invasive and may be combined with CT perfusion imaging. CT perfusion permits semiquantitative cerebral blood flow measurements, including the evaluation of the microcirculation. It may be used for prediction, early detection, and diagnosis of DCI, with yet-to-prove benefit on clinical outcome when used as a screening modality. Transcranial Doppler may be considered as an additional noninvasive screening tool for flow velocities in the middle cerebral artery, with limited accuracy in other cerebral arteries. Continuous electroencephalography enables detection of early signs of ischemia at a reversible stage prior to clinical manifestation. However, its widespread use is still limited because of the required infrastructure and expertise in data interpretation. Near-infrared spectroscopy, a noninvasive and continuous modality for evaluation of cerebral blood flow dynamics, has shown conflicting results and needs further validation. Monitoring techniques beyond neurological examinations may help in the detection of DCI, especially in comatose patients. However, these techniques are limited because of their invasive nature and/or restriction of measurements to focal brain areas.

CONCLUSION

The current literature review underscores the need for incorporating existing modalities and developing new methods to evaluate brain perfusion, brain metabolism, and overall brain function more accurately and more globally.

The Role of Early Serum Biomarkers and Clinical Rating Scales in the Prediction of Delayed Cerebral Ischaemia and Short-Term Outcome after Aneurysmal Subarachnoid Haemorrhage: Single Centre Experience

Considering the variety of complications that arise after aneurysmal subarachnoid haemorrhage (aSAH) and the complex pathomechanism of delayed cerebral ischaemia (DCI), the task of predicting the outcome assumes a profound complexity. Therefore, there is a need to develop early predictive and decision-making models. This study explores the effect of serum biomarkers and clinical scales on patients' outcomes and their interrelationship with DCI and systemic complications in aSAH. This was a retrospective analysis including aSAH patients admitted to the Wroclaw University Hospital (Wrocław, Poland) from 2011 to 2020. A good outcome was defined as a modified Rankin Scale (mRS) score of 0-2. The prediction of the development of DCI and poor outcome was conducted using logistic regression as a standard model (SM) and random forest as a machine learning method (ML). A cohort of 174 aSAH patients were included in the analysis. DCI was diagnosed in 79 (45%) patients. Significant differences between patients with poor vs. good outcome were determined from their levels of albumin (31 ± 7 vs. 35 ± 5 (g/L); p < 0.001), D-dimer (3.0 ± 4.5 vs. 1.5 ± 2.8 (ng/mL); p < 0.001), procalcitonin (0.2 ± 0.4 vs. 0.1 ± 0.1 (ng/mL); p < 0.001), and glucose (169 ± 69 vs. 137 ± 48 (nmol/L); p < 0.001). SM for DCI prediction included the Apache II scale (odds ratio [OD] 1.05; 95% confidence interval [CI] 1.00-1.09) and albumin level (OD 0.88; CI 0.82-0.95). ML demonstrated that low albumin level, high Apache II scale, increased D-dimer and procalcitonin levels had the highest predictive values for DCI. The integration of clinical parameters and scales with a panel of biomarkers may effectively facilitate the stratification of aSAH patients, identifying those at high risk of secondary complications and poor outcome.

Predicting vasospasm risk using first presentation aneurysmal subarachnoid hemorrhage volume: A semi-automated CT image segmentation analysis using ITK-SNAP

PURPOSE

Cerebral vasospasm following aneurysmal subarachnoid hemorrhage (aSAH) is a significant complication associated with poor neurological outcomes. We present a novel, semi-automated pipeline, implemented in the open-source medical imaging analysis software ITK-SNAP, to segment subarachnoid blood volume from initial CT head (CTH) scans and use this to predict future radiological vasospasm.

METHODS

42 patients were admitted between February 2020 and December 2021 to our tertiary neurosciences center, and whose initial referral CTH scan was used for this retrospective cohort study. Blood load was segmented using a semi-automated random forest classifier and active contour evolution implemented in ITK-SNAP. Clinical data were extracted from electronic healthcare records in order to fit models aimed at predicting radiological vasospasm risk.

RESULTS

Semi-automated segmentations demonstrated excellent agreement with manual, expert-derived volumes (mean Dice coefficient = 0.92). Total normalized blood volume, extracted from CTH images at first presentation, was significantly associated with greater odds of later radiological vasospasm, increasing by approximately 7% for each additional cm3 of blood (OR = 1.069, 95% CI: 1.021-1.120; p < .005). Greater blood volume was also significantly associated with vasospasm of a higher Lindegaard ratio, of longer duration, and a greater number of discrete episodes. Total blood volume predicted radiological vasospasm with a greater accuracy as compared to the modified Fisher scale (AUC = 0.86 vs 0.70), and was of independent predictive value.

CONCLUSION

Semi-automated methods provide a plausible pipeline for the segmentation of blood from CT head images in aSAH, and total blood volume is a robust, extendable predictor of radiological vasospasm, outperforming the modified Fisher scale. Greater subarachnoid blood volume significantly increases the odds of subsequent vasospasm, its time course and its severity.

Plasma SPARC Elevation in Delayed Cerebral Ischemia After Aneurysmal Subarachnoid Hemorrhage

Matricellular proteins have been implicated in pathologies after subarachnoid hemorrhage (SAH). To find a new therapeutic molecular target, the present study aimed to clarify the relationships between serially measured plasma levels of a matricellular protein, secreted protein acidic and rich in cysteine (SPARC), and delayed cerebral ischemia (DCI) in 117 consecutive aneurysmal SAH patients with admission World Federation of Neurological Surgeons (WFNS) grades I-III. DCI developed in 25 patients with higher incidences of past history of hypertension and dyslipidemia, preoperative WFNS grade III, modified Fisher grade 4, spinal drainage, and angiographic vasospasm. Plasma SPARC levels were increased after SAH, and significantly higher in patients with than without DCI at days 7-9, and in patients with VASOGRADE-Yellow compared with VASOGRADE-Green at days 1-3 and 7-9. However, there were no relationships between plasma SPARC levels and angiographic vasospasm. Receiver-operating characteristic curves differentiating DCI from no DCI determined the cut-off value of plasma SPARC ≥ 82.1 ng/ml at days 7 - 9 (sensitivity, 0.800; specificity, 0.533; and area under the curve, 0.708), which was found to be an independent determinant of DCI development in multivariate analyses. This is the first study to show that SPARC is upregulated in peripheral blood after SAH, and that SPARC may be involved in the development of DCI without angiographic vasospasm in a clinical setting.

An update of predictors of cerebral infarction after aneurysmal subarachnoid hemorrhage: systematic review and meta-analysis

INTRODUCTION

Evidence about predictors of poor outcomes such as cerebral infarction (CI) after aneurysmal subarachnoid hemorrhage (aSAH) has not been fully elucidated.

EVIDENCE ACQUISITION

We performed a systematic review and meta-analysis on studies with adults with aSAH considering RCT and non-RCT, prospective, and retrospective cohort studies describing clinical, imaging as well as angiographic studies in patients with aSAH.

EVIDENCE SYNTHESIS

After reviewing the complete text, 11 studies were considered eligible, out of which four were ruled out. Degree of clinical severity was the most predictive factor with a higher degree at the presentation on different severity scales being associated with a statistically significant increasing the risk of suffering a CI following aSAH (OR 2.49 [95% CI 1.38-4.49] P=0.0003). Aneurysm size increased the risk of CI (OR 1.49 [95% CI 1.20-1.85] P=0.0003; I²=4%). In six studies analyzed, it was found that an important factor for the subsequent development of CI is vasospasm (OR 7.62 [2.19, 26.54], P=0.0001).

CONCLUSIONS

The development of vasospasm is a risk factor for CI development after aSAH. In our review, three factors were associated with an increased risk of CI: clinical severity at presentation, vasospasm, and aneurysm size. The major limitation of this meta-analysis is that included studies were conducted retrospectively or were post hoc analyses of a prospective trial.

The Role of VASOGRADE as a Simple Grading Scale to Predict Delayed Cerebral Ischemia and Functional Outcome After Aneurysmal Subarachnoid Hemorrhage

BACKGROUND

The VASOGRADE is a simple aneurysmal subarachnoid hemorrhage (aSAH) grading scale that combines the modified Fisher scale (mFisher) and the World Federation of Neurological Societies (WFNS) grading system, allowing the stratification of delayed cerebral ischemia (DCI) risk. However, the VASOGRADE accuracy in predicting functional outcomes is still to be determined.

METHODS

We retrospectively evaluated a multiethnic cohort of consecutive patients with aSAH admitted to a high-volume center in Brazil from January 2016 to January 2019. Patients were classified according to the severity of the clinical presentation (WFNS), the amount of blood in the initial head computerized tomography (mFisher) scan, and the VASOGRADE (green, yellow, red). The primary outcome was to detect DCI-related cerebral infarction, and the secondary outcome was the functional outcome at hospital discharge according to the modified Rankin scale (mRs). Univariate and multivariate logistic regression models were employed.

RESULTS

A total of 212 patients (71.7% female, mean age 52.7 ± 12.8) were included. Sixty-nine patients were classified as VASOGRADE-Green (32.5%), 98 patients as VASOGRADE-Yellow (46.9%), and 45 patients as VASOGRADE-Red (20.6%). DCI-related infarction was present in 39 patients (18.9%). The proportions of patients in the VASOGRADE-Green, VASOGRADE-Yellow, and VASOGRADE-Red categories with DCI-related infarction were 7.7, 61.5, and 30.8%, respectively. After a multivariable analysis including age, sex, aneurysm location, and the VASOGRADE classification as variables, both VASOGRADE-Yellow and VASOGRADE-Red were independently associated with DCI-related infarction (odds ratio [OR] 7.69, 95% confidence interval [CI] 2.13-27.8, and OR 8.07, 95% CI 2.03-32.11, respectively) and unfavorable outcome (OR 4.16, 95% CI 1.33-13.03, and OR 25.57, 95% CI 4.45-147.1, respectively). The VASOGRADE discrimination performance for DCI-related infarction (area under the receiver operating characteristic curve) was 0.67 ± 0.04 (95% CI 0.58-0.75; p = 0.001). VASOGRADE-Red had 97.5% specificity for predicting an unfavorable mRs score at discharge (95% CI 92.8-99.5%). Conversely, VASOGRADE-Green had an excellent specificity for predicting favorable outcome at discharge (mRs score 0-2, 95% CI 82.6-95.5%).

CONCLUSIONS

In conclusion, in a multiethnic cohort of patients with aSAH, VASOGRADE-Green predicted the absence of DCI and good clinical outcome at discharge with very high specificity, and patients in this category might be selected for early intensive care unit (ICU) discharge, minimizing costs and medical complications associated with prolonged hospital stay. On the other hand, patients categorized as VASOGRADE-Yellow and VASOGRADE-Red were at the highest risk for DCI. They should, therefore, be selected as a priority for care in high-volume aSAH centers, being aggressively monitored for DCI at the ICU. Such stratification methods are crucial, especially in countries with low financial resources and high health care services demand.

Cerebrospinal Fluid Lactate and Glucose Levels as Predictors of Symptomatic Delayed Cerebral Ischemia in Patients with Aneurysmal Subarachnoid Hemorrhage

BACKGROUND

Aneurysmal subarachnoid hemorrhage (aSAH) is a complex neurovascular syndrome with profound systemic effects associated with high rates of disability and mortality. Delayed cerebral ischemia (DCI), which encompasses all neurobiological events occurring in the subacute-late stage after aSAH, has a complex pathogenesis and can occur in the absence of instrumental vasospasm. Our aim was to assess the correlation between cerebrospinal fluid (CSF) lactate and glucose levels measured on the second or third day after aSAH with clinical deterioration caused by DCI and with 3-month functional outcome.

METHODS

This prospective study included all aSAH patients admitted between January 2020 and December 2021 who underwent external ventricular drain placement and CSF lactate and glucose measurement.

RESULTS

Among 133 aSAH patients, 48 had an external ventricular drain placed and early CSF lactate and glucose assessment. Independent predictors of symptomatic DCI were World Federation of Neurosurgical Societies grade IV-V (adjusted odds ratio [aOR] 25.8, 95% confidence interval [CI] 2.9-649.2, P = 0.012), elevated CSF glucose (aOR 28.8, 95% CI 3.3-775.2, P = 0.010), and elevated CSF lactate (aOR 14.7, 95% CI 1.9-205.7, P = 0.018). The only independent predictor of 3-month functional outcome was occurrence of symptomatic DCI (aOR 0.02, 95% CI 0.0-0.2, P = 0.01).

CONCLUSIONS

Elevated CSF lactate and glucose levels in the first 3 days following aSAH were independent predictors of subsequent DCI-related neurological impairment; the presence of instrumental vasospasm was not significantly correlated with DCI after multivariate adjustment. CSF lactate and glucose monitoring may represent a point-of-care test, which could potentially improve prediction of subacute neurological worsening and guide therapeutic choices. Further research with larger prospective cohorts is warranted.

Wasp venom from Vespa magnifica acts as a neuroprotective agent to alleviate neuronal damage after stroke in rats

CONTEXT

Acute ischaemic stroke (AIS) is a major cause of disability and death, which is a serious threat to human health and life. Wasp venom extracted from Vespa magnifica Smith (Vespidae) could treat major neurological disorders.

OBJECTIVE

This study investigated the effects of wasp venom on AIS in rats.

MATERIAL AND METHODS

We used a transient middle cerebral artery occlusion (MCAO) model in Sprague-Dawley rats (260-280 g, n = 8-15) with a sham operation group being treated as negative control. MCAO rats were treated with wasp venom (0.05, 0.2 and 0.6 mg/kg, i.p.) using intraperitoneal injection. After treatment 48 h, behavioural tests, cortical blood flow (CBF), TTC staining, H&E staining, Nissl staining, TUNEL assay, immunohistochemistry (IHC) and ELISA were employed to investigate neuroprotective effects of wasp venom.

RESULTS

Compared with the MCAO group, wasp venom (0.6 mg/kg) improved neurological impairment, accelerated CBF recovery (205.6 ± 52.92 versus 216.7 ± 34.56), reduced infarct volume (337.1 ± 113.2 versus 140.7 ± 98.03) as well as BBB permeability as evidenced by changes in claudin-5 and AQP4. In addition, function recovery of stroke by wasp venom treatment was associated with a decrease in TNF-α, IL-1β, IL-6 and inhibition activated microglia as well as apoptosis. Simultaneously, the wasp venom regulated the angiogenesis factors VEGF and b-FGF in the brain.

CONCLUSIONS

Wasp venom exhibited a potential neuroprotective effect for AIS. In the future, we will focus on determining whether the observed actions were due to a single compound or the interaction of multiple components of the venom.

The prognostic value of hyperglycemia in aneurysmal subarachnoid hemorrhage: a systematic review and meta-analysis

Recent studies have demonstrated that hyperglycemia may result in a poor prognosis following aneurysmal subarachnoid hemorrhage (aSAH). However, the association between hyperglycemia and the clinical outcome of aSAH has not been clearly established thus far. Therefore, we performed a systematic review and meta-analysis to investigate the association between hyperglycemia and the development of aSAH. We completed a literature search in four databases (PubMed, EMBASE, Cochrane Library, and Web of Science) up to November 1, 2021, including all eligible studies investigating the prognostic value of hyperglycemia in patients with aSAH. We performed a quality assessment of included studies using the Newcastle-Ottawa Quality Assessment Scale. The pooled odds ratios (ORs) with corresponding 95% confidence intervals (CIs) were calculated to assess the association of hyperglycemia in aneurysmal subarachnoid hemorrhage. A total of 35 studies with 11,519 patients were finally included in the meta-analysis. Nineteen studies reported the association between hyperglycemia and poor outcome, 12 studies reported the association between hyperglycemia and all-cause mortality, 7 studies reported the association between hyperglycemia and cerebral vasospasm, and 9 studies reported the association between hyperglycemia and cerebral infarction. The pooled data of these studies suggested that hyperglycemia was significantly associated with poor functional outcomes (odds ratio [OR], 1.29; 95% confidence interval [CI], 1.17-1.42; P < 0.00001; I² = 83%), all-cause mortality (OR, 1.02; 95% CI, 1.01-1.04; P = 0.0006; I² = 89%), cerebral vasospasm (OR, 1.02; 95% CI, 1.01-1.02; P = 0.0002; I² = 35%), and cerebral infarction (OR, 1.16; 95% CI, 1.09-1.23; P < 0.00001; I² = 10%) in aSAH patients. These findings suggested that assessing for hyperglycemia at admission may help clinicians to identify critically ill patients and complete patient stratification early, which may achieve better management and improve the prognosis of patients with aSAH.

Comparison of Conventional Logistic Regression and Machine Learning Methods for Predicting Delayed Cerebral Ischemia After Aneurysmal Subarachnoid Hemorrhage: A Multicentric Observational Cohort Study

Background

Timely and accurate prediction of delayed cerebral ischemia is critical for improving the prognosis of patients with aneurysmal subarachnoid hemorrhage. Machine learning (ML) algorithms are increasingly regarded as having a higher prediction power than conventional logistic regression (LR). This study aims to construct LR and ML models and compare their prediction power on delayed cerebral ischemia (DCI) after aneurysmal subarachnoid hemorrhage (aSAH).

Methods

This was a multicenter, retrospective, observational cohort study that enrolled patients with aneurysmal subarachnoid hemorrhage from five hospitals in China. A total of 404 aSAH patients were prospectively enrolled. We randomly divided the patients into training (N = 303) and validation cohorts (N = 101) according to a ratio of 75–25%. One LR and six popular ML algorithms were used to construct models. The area under the receiver operating characteristic curve (AUC), accuracy, balanced accuracy, confusion matrix, sensitivity, specificity, calibration curve, and Hosmer–Lemeshow test were used to assess and compare the model performance. Finally, we calculated each feature of importance.

Results

A total of 112 (27.7%) patients developed DCI. Our results showed that conventional LR with an AUC value of 0.824 (95%CI: 0.73–0.91) in the validation cohort outperformed k-nearest neighbor, decision tree, support vector machine, and extreme gradient boosting model with the AUCs of 0.792 (95%CI: 0.68–0.9, P = 0.46), 0.675 (95%CI: 0.56–0.79, P < 0.01), 0.677 (95%CI: 0.57–0.77, P < 0.01), and 0.78 (95%CI: 0.68–0.87, P = 0.50). However, random forest (RF) and artificial neural network model with the same AUC (0.858, 95%CI: 0.78–0.93, P = 0.26) were better than the LR. The accuracy and the balanced accuracy of the RF were 20.8% and 11% higher than the latter, and the RF also showed good calibration in the validation cohort (Hosmer-Lemeshow: P = 0.203). We found that the CT value of subarachnoid hemorrhage, WBC count, neutrophil count, CT value of cerebral edema, and monocyte count were the five most important features for DCI prediction in the RF model. We then developed an online prediction tool (https://dynamic-nomogram.shinyapps.io/DynNomapp-DCI/) based on important features to calculate DCI risk precisely.

Conclusions

In this multicenter study, we found that several ML methods, particularly RF, outperformed conventional LR. Furthermore, an online prediction tool based on the RF model was developed to identify patients at high risk for DCI after SAH and facilitate timely interventions.

Clinical Trial Registration

http://www.chictr.org.cn, Unique identifier: ChiCTR2100044448.

Scoring system to predict hospital outcome after subarachnoid hemorrhage-incorporating systemic response: The CRIG score

OBJECTIVES

Local and systemic proinflammatory and prothrombotic processes after aneurysmal subarachnoid hemorrhage (aSAH) precipitate delayed cerebral ischemia (DCI) and determine clinical outcome. Recent studies using admission and temporal trends of mean platelet volume to platelet count ratio (MPV:PLT) and neutrophil to lymphocyte ratio (NLR) have identified patients developing DCI. We examine if MPV:PLT and NLR along with admission clinical or radiological features can be used to develop a scoring system to predict DCI and in-hospital clinical outcome.

MATERIALS AND METHODS

A 7-year retrospective cohort of aSAH patients admitted to a tertiary care medical center was used to study and identify clinical, radiological and laboratory parameters to predict DCI and clinical outcome (good: discharge to home or rehabilitation facility; poor: all other discharge destinations). Using regression analyses a scoring system (Clinical, Radiological, Inflammatory, dysGlycemia, CRIG) was developed.

RESULTS

Of 271 patients, admission clinical grade (World Federation of Neurological Surgeons' scale), radiological grade (modified Fisher score), NLR and glycated hemoglobin were identified as contributors for CRIG score. CRIG_DCI score threshold of 112 and CRIG_discharge 109, respectively predicted DCI and adverse clinical outcome in score development cohort. The same threshold predicted DCI and adverse clinical outcome with 78.1 and 100% sensitivity, 44.0 and 52.2% specificity, and 63.2 and 61.4% accuracy, respectively in the score validation cohort.

CONCLUSIONS

CRIG is an easily calculable scoring system that incorporates systemic response of aSAH - thus, alluding to its multisystem nature. It can be used at the time of admission to predict DCI and clinical outcome.

Early cisternal fibrinolysis is more effective than rescue spasmolysis for the prevention of delayed infarction after subarachnoid haemorrhage

BACKGROUND

To compare the efficacy of two different concepts of cisternal therapy-PREVENTIVE fibrinolysis plus on-demand spasmolysis versus RESCUE spasmolysis-for the prevention of cerebral vasospasm (CVS) and delayed cerebral infarction (DCI) in patients with aneurysmal subarachnoid haemorrhage (aSAH).

METHODS

Retrospective analysis of 84 aSAH patients selected for cisternal therapy for DCI prevention. 66 high-risk patients received PREVENTIVE cisternal therapy to enhance blood clearance. Either stereotactic catheter ventriculocisternostomy (STX-VCS) or intraoperative placement of a cisterno-ventriculostomy catheter (CVC), followed by fibrinolytic cisternal lavage using urokinase was performed. In case of vasospasm, nimodipine was applied intrathecally. 22 low-risk patients who developed CVS against expectations were selected for STX-VCS as RESCUE intervention for cisternal spasmolysis with nimodipine. Rates of DCI and mean flow velocities of daily transcranial Doppler (TCD) ultrasonographies were evaluated.

RESULTS

Despite a higher prespecified DCI risk, patients selected for PREVENTIVE intervention primarily aiming at blood clearance had a lower DCI rate compared with patients selected for intrathecal spasmolysis as a RESCUE therapy (11.3% vs 18.2%). After intrathecal treatment onset, CVS (TCD>160 cm/s) occurred in 45% of patients with PREVENTIVE and 77% of patients with RESCUE therapy (p=0.013). A stronger response of CVS to intrathecal nimodipine was observed in patients with PREVENTIVE intervention as the mean CVS duration after start of intrathecal nimodipine was 3.2 days compared with 5.8 days in patients with RESCUE therapy (p=0.026).

CONCLUSIONS

PREVENTIVE cisternal therapy directed at blood clearance is more effective for the prevention of CVS and delayed infarction compared with cisternal RESCUE spasmolysis.

TRIAL REGISTRATION NUMBER

DRKS00016532.

A Comparison of LASSO Regression and Tree-Based Models for Delayed Cerebral Ischemia in Elderly Patients With Subarachnoid Hemorrhage

Backgrounds

As a most widely used machine learning method, tree-based algorithms have not been applied to predict delayed cerebral ischemia (DCI) in elderly patients with aneurysmal subarachnoid hemorrhage (aSAH). Hence, this study aims to develop the conventional regression and tree-based models and determine which model has better prediction performance for DCI development in hospitalized elderly patients after aSAH.

Methods

This was a multicenter, retrospective, observational cohort study analyzing elderly patients with aSAH aged 60 years and older. We randomly divided the multicentral data into model training and validation cohort in a ratio of 70–30%. One conventional regression and tree-based model, such as least absolute shrinkage and selection operator (LASSO), decision tree (DT), random forest (RF), and eXtreme Gradient Boosting (XGBoost), was developed. Accuracy, sensitivity, specificity, area under the precision-recall curve (AUC-PR), and area under the receiver operating characteristic curve (AUC-ROC) with 95% CI were employed to evaluate the model prediction performance. A DeLong test was conducted to calculate the statistical differences among models. Finally, we figured the importance weight of each feature to visualize the contribution on DCI.

Results

There were 111 and 42 patients in the model training and validation cohorts, and 53 cases developed DCI. According to AUC-ROC value in the model internal validation, DT of 0.836 (95% CI: 0.747–0.926, p = 0.15), RF of 1 (95% CI: 1–1, p < 0.05), and XGBoost of 0.931 (95% CI: 0.885–0.978, p = 0.01) outperformed LASSO of 0.793 (95% CI: 0.692–0.893). However, the LASSO scored a highest AUC-ROC value of 0.894 (95% CI: 0.8–0.989) than DT of 0.764 (95% CI: 0.6–0.928, p = 0.05), RF of 0.821 (95% CI: 0.683–0.959, p = 0.27), and XGBoost of 0.865 (95% CI: 0.751–0.979, p = 0.69) in independent external validation. Moreover, the LASSO had a highest AUC-PR value of 0.681 than DT of 0.615, RF of 0.667, and XGBoost of 0.622 in external validation. In addition, we found that CT values of subarachnoid clots, aneurysm therapy, and white blood cell counts were the most important features for DCI in elderly patients with aSAH.

Conclusions

The LASSO had a superior prediction power than tree-based models in external validation. As a result, we recommend the conventional LASSO regression model to predict DCI in elderly patients with aSAH.

Basic Surveillance Parameters Improve the Prediction of Delayed Cerebral Infarction After Aneurysmal Subarachnoid Hemorrhage

Background

To establish a practical risk chart for prediction of delayed cerebral infarction (DCI) after aneurysmal subarachnoid hemorrhage (aSAH) by using information that is available until day 5 after ictus.

Methods

We assessed all consecutive patients with aSAH admitted to our service between September 2008 and September 2015 (n = 417). The data set was randomly split into thirds. Two-thirds were used for model development and one-third was used for validation. Characteristics that were present between the bleeding event and day 5 (i.e., prior to >95% of DCI diagnoses) were assessed to predict DCI by using logistic regression models. A simple risk chart was established and validated.

Results

The amount of cisternal and ventricular blood on admission CT (Hijdra sum score), early sonographic vasospasm (i.e., mean flow velocity of either intracranial artery >160 cm/s until day 5), and a simplified binary level of consciousness score until day 5 were the strongest predictors of DCI. A model combining these predictors delivered a high predictive accuracy [the area under the receiver operating characteristic (AUC) curve of 0.82, Nagelkerke's R² 0.34 in the development cohort]. Validation of the model demonstrated a high discriminative capacity with the AUC of 0.82, Nagelkerke's R² 0.30 in the validation cohort.

Conclusion

Adding level of consciousness and sonographic vasospasm between admission and postbleed day 5 to the initial blood amount allows for simple and precise prediction of DCI. The suggested risk chart may prove useful for selection of appropriate candidates for interventions to prevent DCI.

Combining Transcranial Doppler and EEG Data to Predict Delayed Cerebral Ischemia After Subarachnoid Hemorrhage

BACKGROUND AND OBJECTIVES

Delayed cerebral ischemia (DCI) is the leading complication of subarachnoid hemorrhage (SAH). Because DCI was traditionally thought to be caused by large vessel vasospasm, transcranial Doppler ultrasounds (TCDs) have been the standard of care. Continuous EEG has emerged as a promising complementary monitoring modality and predicts increased DCI risk. Our objective was to determine whether combining EEG and TCD data improves prediction of DCI after SAH. We hypothesize that integrating these diagnostic modalities improves DCI prediction.

METHODS

We retrospectively assessed patients with moderate to severe SAH (2011-2015; Fisher 3-4 or Hunt-Hess 4-5) who had both prospective TCD and EEG acquisition during hospitalization. Middle cerebral artery (MCA) peak systolic velocities (PSVs) and the presence or absence of epileptiform abnormalities (EAs), defined as seizures, epileptiform discharges, and rhythmic/periodic activity, were recorded daily. Logistic regressions were used to identify significant covariates of EAs and TCD to predict DCI. Group-based trajectory modeling (GBTM) was used to account for changes over time by identifying distinct group trajectories of MCA PSV and EAs associated with DCI risk.

RESULTS

We assessed 107 patients; DCI developed in 56 (51.9%). Univariate predictors of DCI are presence of high-MCA velocity (PSV ≥200 cm/s, sensitivity 27%, specificity 89%) and EAs (sensitivity 66%, specificity 62%) on or before day 3. Two univariate GBTM trajectories of EAs predicted DCI (sensitivity 64%, specificity 62.75%). Logistic regression and GBTM models using both TCD and EEG monitoring performed better. The best logistic regression and GBTM models used both TCD and EEG data, Hunt-Hess score at admission, and aneurysm treatment as predictors of DCI (logistic regression: sensitivity 90%, specificity 70%; GBTM: sensitivity 89%, specificity 67%).

DISCUSSION

EEG and TCD biomarkers combined provide the best prediction of DCI. The conjunction of clinical variables with the timing of EAs and high MCA velocities improved model performance. These results suggest that TCD and cEEG are promising complementary monitoring modalities for DCI prediction. Our model has potential to serve as a decision support tool in SAH management.

CLASSIFICATION OF EVIDENCE

This study provides Class II evidence that combined TCD and EEG monitoring can identify delayed cerebral ischemia after SAH.

Mitigation of Blood Load Impact in Patients with Subarachnoid Hemorrhage by Cisternal Lavage

OBJECT

The initial amount of subarachnoid and ventricular blood is an important prognostic factor for outcome in patients with aneurysmal subarachnoid hemorrhage (aSAH). In this comparative study of an unselected aSAH-population, we assess the modifiability of these factors by implementation of blood clearance by cisternal lavage.

METHODS

All patients with aSAH treated in our department between October 2011 and October 2019 (8 years, n = 458) were included in our study. In the first 4-year period (BEFORE, n = 237), patients were treated according to international guidelines. In the second 4-year period (AFTER, n = 221), cisternal lavage methods were available and applied in 72 high-risk patients (32.5%). The cisternal and ventricular blood load was recorded by the Hijdra score. Multivariable regression models were used to assess the prognostic significance of risk factors, including blood load, in relation to common aSAH characteristics in both study groups.

RESULTS

Worse neurological outcomes (mRS > 3) occurred in the BEFORE population with 41.45% versus 30.77% in the AFTER cohort, 6 months after aSAH (HR: 1.59, 95% CI 1.08-2.34, p = 0.01). Admission WFNS grade, comorbidities (Charlson Comorbidity Index), herniation signs, concomitant intracerebral hemorrhage, and the development of delayed cerebral infarction were strongly associated with poor outcome in both study groups. Intraventricular and cisternal blood load and, particularly, a cast fourth ventricle (Cast 4) represented strong prognosticators of poor neurological outcome in the BEFORE cohort. This effect was lost after implementation of cisternal lavage (AFTER cohort).

CONCLUSION

Cisternal and ventricular blood load - in particular: a Cast 4 - represent important prognosticators in patients with aSAH. They are, however, amenable to modification by blood clearing therapies.

Screening Computed Tomography Angiography to Identify Patients at Low Risk for Delayed Cerebral Ischemia Following Aneurysmal Subarachnoid Hemorrhage

Introduction: Delayed cerebral ischemia (DCI) occurs during a risk period of 3-21 days following aneurysmal subarachnoid hemorrhage (aSAH) and is associated with worse outcomes. The identification of patients at low risk for DCI might permit triage to less intense monitoring and management. While large-vessel vasospasm (LVV) is a distinct clinical entity from DCI, the presence of moderate-to-severe LVV is associated with a higher risk of DCI. Our hypothesis was that the absence of moderate-to-severe LVV on screening computed tomographic angiography (CTA) performed within the first few days of the DCI risk period will accurately identify patients at low risk for subsequent DCI. Methods: This was a retrospective cohort study. Our institutional SAH outcomes registry was queried for all aSAH patients admitted in 2016-2019 who underwent screening CTA brain between days 4 and 8 following ictus. We excluded patients diagnosed with DCI prior to the first CTA performed during this time period. All variables are prospectively entered into the registry, and outcomes including DCI and LVV are prospectively adjudicated. We evaluated the predictive value and accuracy of moderate-to-severe LVV on CTA performed 4-8 days following ictus for the prediction of subsequent DCI. Results: A total of 243 aSAH patients were admitted during the study timeframe. Of the 54 patients meeting the eligibility criteria, 11 (20%) had moderate-to-severe LVV on the screening CTA study performed during the risk period. Seven of the 11 (64%) patients with moderate-to-severe LVV on the days 4-8 screening CTA vs. six of 43 (14%) patients without, subsequently developed DCI. On multivariate analysis, the presence of LVV on days 4-8 screening CTA was an independent predictor of DCI (odds ratio 10.26, 95% CI 1.69-62.24, p = 0.011). NPV for the subsequent development of DCI was 86% (95% CI 77-92%). Sensitivity was 54% (25-81%), specificity 90% (77-97%), and positive predictive value 64% (38-83%). Conclusions: The presence of moderate-to-severe LVV on screening CTA performed between days 4 and 8 following aSAH was an independent predictor of DCI, but achieved only moderate diagnostic accuracy, with NPV 86% and sensitivity 54%. Complementary risk-stratification strategies are likely necessary.

Impact of Implementing an Elaborated CT Perfusion Protocol for Aneurysmal SAH on Functional Outcome: CTP Protocol for SAH

BACKGROUND AND PURPOSE

The acute phase of aneurysmal SAH is characterized by a plethora of impending complications with the potential to worsen patients' outcomes. The aim of this study was to evaluate whether an elaborated CTP-based imaging protocol during the acute aneurysmal SAH phase is able to prevent delayed infarctions and contribute to a better outcome.

MATERIALS AND METHODS

In 2012, an elaborated CTP-based protocol was implemented for the management of patients with aneurysmal SAH. Retrospective analysis of patients with aneurysmal SAH treated from 2010 to 2013 was performed, comparing the patients treated before (group one, 2010-2011) with those treated after the protocol implementation (group two, 2012-2013) with regard to delayed infarctions and outcome according to the mRS at 3-months' follow-up.

RESULTS

A total of 133 patients were enrolled, of whom 57 were included in group 1, and 76, in group 2. There were no significant differences between the groups concerning baseline characteristics. In the multivariate analysis, independent predictors of a good outcome (mRS ≤ 2) were younger age (P < .001), lower World Federation of Neurosurgical Societies grade (P < .001), absence of delayed infarction (P = .01), and management according to the CTP protocol (P = .01). Larger or multiple infarctions occurred significantly more often in group 1 compared with group 2 (88% versus 33% of all delayed infarctions, P = .03). The outcome in group 2 was significantly better compared with group 1 (P = .005).

CONCLUSIONS

The findings suggest that implementation of an elaborated CTP protocol is associated with a better outcome. An earlier initiation of further diagnostics and treatment with prevention of large territorial and/or multiple infarctions might have led to this finding.

Cerebral circulation time on DSA during endovascular treatment in WFNS grade I aneurysmal SAH patients-a predictor of DCI?

PURPOSE

Delayed cerebral ischemia (DCI) remains a contributor to poor outcome following aneurysmal subarachnoid hemorrhage (aSAH). We evaluated cerebral circulation time (CCT) on digital subtraction angiography (DSA) during endovascular treatment (EVT) in WFNS grade I aSAH patients as a predictor of DCI.

METHODS

Of 135 consecutive WNFS grade I aSAH patients, 90 were included. Age, gender, time of DSA from ictus (< 72 h or > 72 h), Fisher scale, severe vasospasm, development of DCI, EVD-dependent hydrocephalus, re-bleeding, and procedural complications were recorded. CCT was calculated retrospectively from multiphase DSA. Association with DCI was established through univariate and, subsequently, multivariable logistic regression. An optimal threshold value was identified using ROC curve analysis. Patient groups defined by threshold CCT value, DCI, and, subsequently, time of DSA from ictus were analyzed using χ² and Fisher's exact test.

RESULTS

CCT was the only significant factor in the multivariable logistic regression for the outcome development of DCI (OR/second increase in CCT = 1.46 [95% CI 1.14-1.86, p = .003]). When CCT was dichotomized at 8.5 s, the odds ratio for developing DCI was 7.12 (95% CI 1.93-26.34, p = .003) for CCT > 8.5 s compared with < 8.5 s. There was a significant difference for DCI in all patient groups dichotomized by CCT < 8.5 s and > 8.5 s (all patients, p = .001; patients imaged before and after 72 h of ictus, p = .024 and p = .034, respectively).

CONCLUSION

A CCT > 8.5 s on DSA during EVT in WFNS grade I aSAH patients is associated with an increased risk of developing DCI and may aid in the management of high-risk patients.

Prediction Models in Aneurysmal Subarachnoid Hemorrhage: Forecasting Clinical Outcome With Artificial Intelligence

BACKGROUND

Predicting outcome after aneurysmal subarachnoid hemorrhage (aSAH) is known to be challenging and complex. Machine learning approaches, of which feedforward artificial neural networks (ffANNs) are the most widely used, could contribute to the patient-specific outcome prediction.

OBJECTIVE

To investigate the prediction capacity of an ffANN for the patient-specific clinical outcome and the occurrence of delayed cerebral ischemia (DCI) and compare those results with the predictions of 2 internationally used scoring systems.

METHODS

A prospective database was used to predict (1) death during hospitalization (ie, mortality) (n = 451), (2) unfavorable modified Rankin Scale (mRS) at 6 mo (n = 413), and (3) the occurrence of DCI (n = 362). Additionally, the predictive capacities of the ffANN were compared to those of Subarachnoid Haemorrhage International Trialists (SAHIT) and VASOGRADE to predict clinical outcome and occurrence of DCI.

RESULTS

The area under the curve (AUC) of the ffANN showed to be 88%, 85%, and 72% for predicting mortality, an unfavorable mRS, and the occurrence of DCI, respectively. Sensitivity/specificity rates of the ffANN for mortality, unfavorable mRS, and the occurrence of DCI were 82%/80%, 94%/80%, and 74%/68%. The ffANN and SAHIT calculator showed similar AUCs for predicting personalized outcome. The presented ffANN and VASOGRADE were found to perform equally with regard to personalized prediction of occurrence of DCI.

CONCLUSION

The presented ffANN showed equal performance when compared with VASOGRADE and SAHIT scoring systems while using less individual cases. The web interface launched simultaneously with the publication of this manuscript allows for usage of the ffANN-based prediction tool for individual data (https://nutshell-tool.com/).

Modified Glasgow coma scale for predicting outcome after subarachnoid hemorrhage surgery

There are many grading scales that attempt to predict outcome following aneurysmal subarachnoid hemorrhage (aSAH). Most scales used to assess outcome are based on the neurological status of the patient. Here, we propose a new scale for aSAH patients that combines the Glasgow Coma Scale (GCS) and the modified Fisher scale (mFS).Five hundred ninety-seven patients with aSAH who were treated at our institution between January 2008 and December 2017 were retrospectively analyzed. Initial GCS score, Hunt and Hess scale, World Federation of Neurosurgical Societies scale, mFS, and modified Rankin Scale were obtained by reviewing data. Incidence of vasospasm was investigated. Factors found to be significant on a multivariable regression analysis were used to develop a scale that was compared with other grading systems using the area under the curve (AUC) calculated from receiver operating characteristic curve.The GCS score and mFS were related to outcomes in patients with aSAH. A simple score, which we call the GCS-F score, was calculated using these initial data. The GCS-F score had an AUC of 90.5% for unfavorable outcome prediction, and 88.4% for in-hospital mortality prediction. On the receiver operating characteristic curve analysis for vasospasm, the AUC for World Federation of Neurosurgical Societies, mFS and GCS-F scores were 0.912, 0.704, and 0.936, respectively.A simple arithmetic combination of the GCS score and mFS, the GCS-F score, includes the radiographic status as well as the clinical status of the patient, so that the state of the patient can be known in more detail than other single scales. The GCS-F score may be a useful scale for predicting outcome and the occurrence of vasospasm in patients with aSAH.

Validation and Optimization of Barrow Neurological Institute Score in Prediction of Adverse Events and Functional Outcome After Subarachnoid Hemorrhage-Creation of the HATCH (Hemorrhage, Age, Treatment, Clinical State, Hydrocephalus) Score

BACKGROUND

The Barrow Neurological Institute (BNI) score, measuring maximal thickness of aneurysmal subarachnoid hemorrhage (aSAH), has previously shown to predict symptomatic cerebral vasospasms (CVSs), delayed cerebral ischemia (DCI), and functional outcome.

OBJECTIVE

To validate the BNI score for prediction of above-mentioned variables and cerebral infarct and evaluate its improvement by integrating further variables which are available within the first 24 h after hemorrhage.

METHODS

We included patients from a single center. The BNI score for prediction of CVS, DCI, infarct, and functional outcome was validated in our cohort using measurements of calibration and discrimination (area under the curve [AUC]). We improved it by adding additional variables, creating a novel risk score (measure by the dichotomized Glasgow Outcome Scale) and validated it in a small independent cohort.

RESULTS

Of 646 patients, 41.5% developed symptomatic CVS, 22.9% DCI, 23.5% cerebral infarct, and 29% had an unfavorable outcome. The BNI score was associated with all outcome measurements. We improved functional outcome prediction accuracy by including age, BNI score, World Federation of Neurologic Surgeons, rebleeding, clipping, and hydrocephalus (AUC 0.84, 95% CI 0.8-0.87). Based on this model we created a risk score (HATCH-Hemorrhage, Age, Treatment, Clinical State, Hydrocephalus), ranging 0 to 13 points. We validated it in a small independent cohort. The validated score demonstrated very good discriminative ability (AUC 0.84 [95% CI 0.72-0.96]).

CONCLUSION

We developed the HATCH score, which is a moderate predictor of DCI, but excellent predictor of functional outcome at 1 yr after aSAH.

The Involvement of Aquaporin-4 in the Interstitial Fluid Drainage Impairment Following Subarachnoid Hemorrhage

The mechanism of brain injury following subarachnoid hemorrhage (SAH) has not yet been clarified. The glymphatic system (GS), a glia-dependent waste clearance pathway, drains away soluble waste proteins and metabolic products, even some toxic factors from the brain. Aquaporin-4 (Aqp4) is highly expressed on the astrocyte foot processes and facilitates the interstitial fluid (ISF) transportation in the GS system. In this study, the role of Aqp4 in the GS injury after SAH was explored using Aqp4 gene knockout (Aqp4^−/−) Sprague Dawley rats. The results of MRI, fluorescent imaging, and transmission electron microscopy (TEM) indicated that, after SAH, the inflow of cerebrospinal fluid (CSF) into the brain and the clearance of ISF from the brain were both significantly decreased. Meanwhile, the expression level of Aqp4 around the artery was markedly higher than that around the vein following SAH. Aqp4 knockout exacerbated the GS damage after SAH. In summary, after SAH, there was an apparent GS impairment, and Aqp4 played key roles in modulating the function of GS in the brain.

The Updated Role of the Blood Brain Barrier in Subarachnoid Hemorrhage: From Basic and Clinical Studies

Subarachnoid hemorrhage (SAH) is a type of hemorrhagic stroke associated with high mortality and morbidity. The blood-brain-barrier (BBB) is a structure consisting primarily of cerebral microvascular endothelial cells, end feet of astrocytes, extracellular matrix, and pericytes. Post-SAH pathophysiology included early brain injury and delayed cerebral ischemia. BBB disruption was a critical mechanism of early brain injury and was associated with other pathophysiological events. These pathophysiological events may propel the development of secondary brain injury, known as delayed cerebral ischemia. Imaging advancements to measure BBB after SAH primarily focused on exploring innovative methods to predict clinical outcome, delayed cerebral ischemia, and delayed infarction related to delayed cerebral ischemia in acute periods. These predictions are based on detecting abnormal changes in BBB permeability. The parameters of BBB permeability are described by changes in computed tomography (CT) perfusion and magnetic resonance imaging (MRI). K_ep seems to be a stable and sensitive indicator in CT perfusion, whereas K^trans is a reliable parameter for dynamic contrast-enhanced MRI. Future prediction models that utilize both the volume of BBB disruption and stable parameters of BBB may be a promising direction to develop practical clinical tools. These tools could provide greater accuracy in predicting clinical outcome and risk of deterioration. Therapeutic interventional exploration targeting BBB disruption is also promising, considering the extended duration of post-SAH BBB disruption.

Aneurysmal Subarachnoid Hemorrhage: the Last Decade

Aneurysmal subarachnoid hemorrhage (SAH) affects six to nine people per 100,000 per year, has a 35% mortality, and leaves many with lasting disabilities, often related to cognitive dysfunction. Clinical decision rules and more sensitive computed tomography (CT) have made the diagnosis of SAH easier, but physicians must maintain a high index of suspicion. The management of these patients is based on a limited number of randomized clinical trials (RCTs). Early repair of the ruptured aneurysm by endovascular coiling or neurosurgical clipping is essential, and coiling is superior to clipping in cases amenable to both treatments. Aneurysm repair prevents rebleeding, leaving the most important prognostic factors for outcome early brain injury from the hemorrhage, which is reflected in the neurologic condition of the patient, and delayed cerebral ischemia (DCI). Observational studies suggest outcomes are better when patients are managed in specialized neurologic intensive care units with inter- or multidisciplinary clinical groups. Medical management aims to minimize early brain injury, cerebral edema, hydrocephalus, increased intracranial pressure (ICP), and medical complications. Management then focuses on preventing, detecting, and treating DCI. Nimodipine is the only pharmacologic treatment that is approved for SAH in most countries, as no other intervention has demonstrated efficacy. In fact, much of SAH management is derived from studies in other patient populations. Therefore, further study of complications, including DCI and other medical complications, is needed to optimize outcomes for this fragile patient population.

Nomogram for predicting delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage in the Chinese population

BACKGROUND

Delayed cerebral ischemia is a serious complication of aneurysmal subarachnoid hemorrhage with debilitating and fatal consequences. Lack of well-established risk factors impedes early identification of high-risk patients with delayed cerebral ischemia. A nomogram provides personalized, evidence-based, and accurate risk estimation. To offset the lack of a predictive tool, we developed a nomogram to predict delayed cerebral ischemia before performing surgical interventions for aneurysmal subarachnoid hemorrhage to aid surgical decision-making.

METHODS

We retrospectively collected data from 887 consecutive eligible Chinese patients who underwent surgical clipping or endovascular coiling for aneurysmal subarachnoid hemorrhage. Patients who previously underwent surgery formed the training cohort (n = 621) for nomogram development; those who underwent surgery later formed the validation cohort (n = 266) to confirm the performance of the model. A multivariate logistic regression analysis identified the independent risk factors associated with delayed cerebral ischemia, which were then incorporated into the nomogram.

RESULTS

Delayed cerebral ischemia was identified in 158/621 patients (25.4%) in the training cohort and in 66/266 patients (24.8%) in the validation cohort. Preoperative factors associated with delayed cerebral ischemia were age > 65 years, modified Fisher grade of 3-4, ruptured aneurysm in the anterior circulation, Hunt-Hess grade of 4-5, high blood pressure on admission, and plasma homocysteine level ≥ 10 μmol/L. Incorporating these six factors in the nomogram achieved efficient concordance indices of 0.73 (95% confidence interval, 0.68-0.77) and 0.65 (95% confidence interval, 0.57-0.72) in predicting delayed cerebral ischemia in the training and validation cohorts, respectively.

CONCLUSIONS

Our model can help determine an individual's risk of developing delayed cerebral ischemia in the Chinese population, and thereby, facilitate reasonable treatment-related decision-making.

High Early Fluid Input After Aneurysmal Subarachnoid Hemorrhage: Combined Report of Association With Delayed Cerebral Ischemia and Feasibility of Cardiac Output-Guided Fluid Restriction

BACKGROUND

Guidelines on the management of aneurysmal subarachnoid hemorrhage (aSAH) recommend euvolemia, whereas hypervolemia may cause harm. We investigated whether high early fluid input is associated with delayed cerebral ischemia (DCI), and if fluid input can be safely decreased using transpulmonary thermodilution (TPT).

METHODS

We retrospectively included aSAH patients treated at an academic intensive care unit (2007-2011; cohort 1) or managed with TPT (2011-2013; cohort 2). Local guidelines recommended fluid input of 3 L daily. More fluids were administered when daily fluid balance fell below +500 mL. In cohort 2, fluid input in high-risk patients was guided by cardiac output measured by TPT per a strict protocol. Associations of fluid input and balance with DCI were analyzed with multivariable logistic regression (cohort 1), and changes in hemodynamic indices after institution of TPT assessed with linear mixed models (cohort 2).

RESULTS

Cumulative fluid input 0 to 72 hours after admission was associated with DCI in cohort 1 (n=223; odds ratio [OR] 1.19/L; 95% confidence interval 1.07-1.32), whereas cumulative fluid balance was not. In cohort 2 (23 patients), using TPT fluid input could be decreased from 6.0 ± 1.0 L before to 3.4 ± 0.3 L; P = .012), while preload parameters and consciousness remained stable.

CONCLUSION

High early fluid input was associated with DCI. Invasive hemodynamic monitoring was feasible to reduce fluid input while maintaining preload. These results indicate that fluid loading beyond a normal preload occurs, may increase DCI risk, and can be minimized with TPT.

Magnesium and Hemorrhage Volume in Patients With Aneurysmal Subarachnoid Hemorrhage

OBJECTIVES

We tested the hypothesis that admission serum magnesium levels are associated with extent of hemorrhage in patients with aneurysmal subarachnoid hemorrhage.

DESIGN

Single-center prospective observational study.

SETTING

Tertiary hospital neurologic ICU.

PATIENTS

Patients with aneurysmal subarachnoid hemorrhage.

INTERVENTIONS

Clinically indicated CT scans and serum laboratory studies.

MEASUREMENTS AND MAIN RESULTS

Demographic, clinical, laboratory, and radiographic data were analyzed. Extent of initial hemorrhage was graded semi-quantitatively on admission CT scans using the modified Fisher scale (grades: 0, no radiographic hemorrhage; 1, thin [< 1 mm in depth] subarachnoid hemorrhage; 2, thin subarachnoid hemorrhage with intraventricular hemorrhage; 3, thick [≥ 1 mm] subarachnoid hemorrhage; 4, thick subarachnoid hemorrhage with intraventricular hemorrhage). We used both ordinal (modified Fisher scale) and dichotomized (thick vs thin subarachnoid hemorrhage) univariate and adjusted logistic regression models to assess associations between serum magnesium and radiographic subarachnoid hemorrhage severity. Data from 354 patients (mean age 55 ± 14 yr, 28.5% male, median admission Glasgow Coma Scale 14 [10-15]) were analyzed. Mean magnesium was lower in patients with thick versus thin subarachnoid hemorrhage (1.92 vs 1.99 mg/dL; p = 0.022). A monotonic trend across categories of modified Fisher scale was found using analysis of variance and Spearman rank correlation (p = 0.015 and p = 0.008, respectively). In adjusted ordinal and binary regression models, lower magnesium levels were associated with higher modified Fisher scale (odds ratio 0.33 per 1 mg/dL increase; 95% CI, 0.14-0.77; p = 0.011) and with thick subarachnoid hemorrhage (odds ratio 0.29 per 1 mg/dL increase; 95% CI, 0.10-0.78; p = 0.015).

CONCLUSIONS

These data support the hypothesis that magnesium influences hemorrhage severity in patients with aneurysmal subarachnoid hemorrhage, potentially through a hemostatic mechanism.

Impact of Stereotactic Ventriculocisternostomy on Delayed Cerebral Infarction and Outcome After Subarachnoid Hemorrhage

Background and Purpose- Delayed cerebral infarction (DCI) is an important cause of morbidity and mortality in patients with aneurysmal subarachnoid hemorrhage (aSAH). Stereotactic catheter ventriculocisternostomy (STX-VCS) and fibrinolytic/spasmolytic lavage is a new method for DCI prevention. Here, we assess the effects of implementing STX-VCS in an unselected aSAH patient population of a tertiary referral center. Methods- Retrospective cohort study of all consecutive aSAH patients admitted to a neurosurgical referral center during a 7-year period (April 2012 to April 2019). Midterm STX-VCS was introduced and offered to patients at high risk for DCI. We compared the incidence and burden of DCI, neurological outcome, and the use of induced hypertension and endovascular rescue therapy in this consecutive aSAH population 3.5 years before versus 3.5 years after STX-VCS became available. Results- Four hundred thirty-six consecutive patients were included: 222 BEFORE and 214 AFTER. Fifty-seven of 214 (27%) patients received STX-VCS. Stereotactic procedures resulted in one (2%) subdural hematoma. Favorable neurological outcome at 6 months occurred in 118 (53%) patients BEFORE and 139 (65%) patients AFTER (relative risk, 0.79 [95% CI, 0.66-0.95]). DCI occurred in 40 (18.0%) patients BEFORE and 17 (7.9%) patients AFTER (relative risk, 0.68 [95% CI, 0.57-0.86]), and total DCI volumes were 8933 (100%) and 3329 mL (36%), respectively. Induced hypertension was used in 97 (44%) and 30 (15%) patients, respectively (relative risk, 0.55 [95% CI, 0.46-0.65]). Thirty (13.5%) patients BEFORE versus 5 (2.3%) patients AFTER underwent endovascular rescue therapies (relative risk, 0.17 [95% CI, 0.07-0.42]). Conclusions- Selecting high-risk patients for STX-VCS reduced the DCI incidence, burden, and related mortality in a consecutive aSAH patient population. This was associated with an improved neurological outcome.

Association of Cerebrospinal Fluid Volume with Cerebral Vasospasm After Aneurysmal Subarachnoid Hemorrhage: A Retrospective Volumetric Analysis

BACKGROUND

In aneurysmal subarachnoid hemorrhage (SAH), clot volume has been shown to correlate with the development of radiographic vasospasm (VS), while the role of cerebrospinal fluid (CSF) volume remains largely elusive in the literature. We evaluated CSF volume as a potential surrogate for VS in addition to SAH volume in this retrospective series.

PATIENTS AND METHODS

From a consecutive cohort of aneurysmal SAH (n= 320), cases were included when angiographic evaluation for VS was performed (n= 125). SAH and CSF volumes were volumetrically quantified using an algorithm-assisted segmentation approach on initial computed tomography after ictus. Association with VS was analyzed using regression analysis. Receiver operating characteristic (ROC) curves were used to evaluate predictive accuracy of volumetric measures for VS and to identify cutoffs for risk stratification.

RESULTS

Among 125 included cases, angiography showed VS in 101 (VS+), while no VS was observed in 24 (VS-) cases. In volumetric analysis, mean SAH volume was significantly larger (26.8 ± 21.1 ml vs. 12.6 ± 12.2 ml, p= 0.001), while mean CSF volume was significantly smaller (63.0 ± 31.2 ml vs. 85.7 ± 62.8, p= 0.03) in VS+ compared to VS- cases, respectively. The absence of correlation for SAH and CSF volumes (Pearson R - 0.05, p= 0.58) indicated independence of both measures of the subarachnoid compartment, which was a prerequisite for CSF to act as a new surrogate for VS not related to SAH. Regression analysis confirmed an increased risk of VS with increasing SAH (OR 1.06, 95% CI 1.02-1.11, p= 0.006), while CSF had a protective effect toward VS (OR 0.99, 95% CI 0.98-0.99, p= 0.02). SAH/CSF ratio was also associated with VS (OR 1.03, 95% CI 1.01-1.05, p= 0.015). ROC curves suggested cutoffs at 120 ml CSF and 20 ml SAH for VS stratification. Combination of variables improved stratification accuracy compared to use of SAH alone.

CONCLUSION

This study provides a proof of concept for CSF correlating with angiographic VS after aneurysmal SAH. Quantification of CSF in conjunction with SAH might enhance risk stratification and exhibit advantages over traditional scores. The association of CSF has to be corroborated for delayed cerebral ischemia to further establish CSF as a surrogate parameter.

Stereotactic Catheter Ventriculocisternostomy for Clearance of Subarachnoid Hemorrhage in Patients with Coiled Aneurysms

BACKGROUND

Cerebral vasospasm leading to delayed cerebral infarction (DCI) is a central source of poor outcome in patients with aneurysmal subarachnoid hemorrhage (aSAH). Current treatments of cerebral vasospasm are insufficient. Cisternal blood clearance is a promising treatment option. However, a generally applicable, safe, and effective method to access the cisterns of the brain is lacking.

OBJECTIVE

To report on stereotactic catheter ventriculocisternostomy (STX-VCS) as a method to access the cisterns of the brain for clearance of subarachnoid hemorrhage in patients with aSAH and coiled aneurysms.

METHODS

In 9 aSAH patients at high risk for DCI (Hunt and Hess grade ≥3, modified Fisher grade ≥3), access to the basal cisterns of the brain was created by STX-VCS. Fibrinolytic and/or spasmolytic lavage therapy was administered.

RESULTS

STX-VCS was feasible and safe in all patients. Subarachnoid blood was rapidly cleared by irrigation with urokinase. Vasospasm occurred in 2 patients and was interrupted by irrigation with nimodipine. There was 1 fatality due to pneumogenic sepsis. Minor DCI occurred in 1 patient. Eight survived without DCI and are independent (modified Rankin score [mRS] ≤ 3) at 6 mo after aSAH.

CONCLUSION

STX-VCS allows for rapid clearance of subarachnoid hemorrhage in patients with coiled aneurysms.

Clinical and experimental aspects of aneurysmal subarachnoid hemorrhage

Aneurysmal subarachnoid hemorrhage (aSAH) continues to be associated with significant morbidity and mortality despite advances in care and aneurysm treatment strategies. Cerebral vasospasm continues to be a major source of clinical worsening in patients. We intended to review the clinical and experimental aspects of aSAH and identify strategies that are being evaluated for the treatment of vasospasm. A literature review on aSAH and cerebral vasospasm was performed. Available treatments for aSAH continue to expand as research continues to identify new therapeutic targets. Oral nimodipine is the primary medication used in practice given its neuroprotective properties. Transluminal balloon angioplasty is widely utilized in patients with symptomatic vasospasm and ischemia. Prophylactic "triple-H" therapy, clazosentan, and intraarterial papaverine have fallen out of practice. Trials have not shown strong evidence supporting magnesium or statins. Other calcium channel blockers, milrinone, tirilazad, fasudil, cilostazol, albumin, eicosapentaenoic acid, erythropoietin, corticosteroids, minocycline, deferoxamine, intrathecal thrombolytics, need to be further investigated. Many of the current experimental drugs may have significant roles in the treatment algorithm, and further clinical trials are needed. There is growing evidence supporting that early brain injury in aSAH may lead to significant morbidity and mortality, and this needs to be explored further.

The SAFARI Score to Assess the Risk of Convulsive Seizure During Admission for Aneurysmal Subarachnoid Hemorrhage

BACKGROUND

Seizure is a significant complication in patients under acute admission for aneurysmal SAH and could result in poor outcomes. Treatment strategies to optimize management will benefit from methods to better identify at-risk patients.

OBJECTIVE

To develop and validate a risk score for convulsive seizure during acute admission for SAH.

METHODS

A risk score was developed in 1500 patients from a single tertiary hospital and externally validated in 852 patients. Candidate predictors were identified by systematic review of the literature and were included in a backward stepwise logistic regression model with in-hospital seizure as a dependent variable. The risk score was assessed for discrimination using the area under the receiver operator characteristics curve (AUC) and for calibration using a goodness-of-fit test.

RESULTS

The SAFARI score, based on 4 items (age ≥ 60 yr, seizure occurrence before hospitalization, ruptured aneurysm in the anterior circulation, and hydrocephalus requiring cerebrospinal fluid diversion), had AUC = 0.77, 95% confidence interval (CI): 0.73-0.82 in the development cohort. The validation cohort had AUC = 0.65, 95% CI 0.56-0.73. A calibrated increase in the risk of seizure was noted with increasing SAFARI score points.

CONCLUSION

The SAFARI score is a simple tool that adequately stratified SAH patients according to their risk for seizure using a few readily derived predictor items. It may contribute to a more individualized management of seizure following SAH.

New risk score of the early period after spontaneous subarachnoid hemorrhage: For the prediction of delayed cerebral ischemia

Background and Purpose

The aim of this study is to identify the early predictors for delayed cerebral ischemia (DCI) and develop a risk stratification score by focusing on the early change after aneurysmal subarachnoid hemorrhage (aSAH).

Methods

The study retrospectively reviewed aSAH patients between 2014 and 2015. Risk factors within 72 hours after aSAH were included into univariable and multivariable logistic regression analysis to screen the independent predictors for DCI and to design a risk stratification score.

Results

We analyzed 702 aSAH patients; four predictors were retained from the final multivariable analysis: World Federation of Neurosurgical Societies scale (WFNS; OR = 4.057, P < .001), modified Fisher Scale (mFS; OR = 2.623, P < .001), Subarachnoid Hemorrhage Early Brain Edema Score (SEBES; OR = 1.539, P = .036), and intraventricular hemorrhage (IVH; OR = 1.932, P = .002). According to the regression coefficient, we created a risk stratification score ranging from 0 to 7 (WFNS = 3, mFS = 2, SEBES = 1, and IVH = 1). The new score showed a significantly higher area under curve (0.785) compared with other scores (P < .001).

Conclusion

The early DCI score provides a practical method at the early 72 hours after aSAH to predict DCI.

Clinical prediction of delayed cerebral ischemia in aneurysmal subarachnoid hemorrhage

OBJECTIVE

The aim of this study was to derive a clinically applicable decision rule using clinical, radiological, and laboratory data to predict the development of delayed cerebral ischemia (DCI) in aneurysmal subarachnoid hemorrhage (aSAH) patients.

METHODS

Patients presenting over a consecutive 9-year period with subarachnoid hemorrhage (SAH) and at least 1 angiographically evident aneurysm were included. Variables significantly associated with DCI in univariate analysis underwent multivariable logistic regression. Using the beta coefficients, points were assigned to each predictor to establish a scoring system with estimated risks. DCI was defined as neurological deterioration attributable to arterial narrowing detected by transcranial Doppler ultrasonography, CT angiography, MR angiography, or catheter angiography, after exclusion of competing diagnoses.

RESULTS

Of 463 patients, 58% experienced angiographic vasospasm with an overall DCI incidence of 21%. Age, modified Fisher grade, and ruptured aneurysm location were significantly associated with DCI. This combination of predictors had a greater area under the receiver operating characteristic curve than the modified Fisher grade alone (0.73 [95% CI 0.67-0.78] vs 0.66 [95% CI 0.60-0.71]). Patients 70 years or older with modified Fisher grade 0 or 1 SAH and a posterior circulation aneurysm had the lowest risk of DCI at 1.2% (0 points). The highest estimated risk was 38% (17 points) in patients 40-59 years old with modified Fisher grade 4 SAH following rupture of an anterior circulation aneurysm.

CONCLUSIONS

Among patients presenting with aSAH, this score-based clinical prediction tool exhibits increased accuracy over the modified Fisher grade alone and may serve as a useful tool to individualize DCI risk.

Computed tomography angiography-based analysis of high-risk intracerebral haemorrhage patients by employing a mathematical model

Background

Haemorrhagic stroke accounts for approximately 31.52% of all stroke cases, and the most common origin is hypertension. However, little is known about the method to identify high-risk populations of hypertensive intracerebral haemorrhage.

Results

The results showed that the angle between the middle cerebral artery and the internal carotid artery (AMIC), the distance between the beginning of the median artery and superior trunk (DMS), and the density (CT value) of the lenticulostriate artery (CTL) were statistically significant enough to cause intracerebral haemorrhage. In addition, we chose these three potential features for the ensemble learning classification model. Our developed ensemble-learning method outperforms not only previous work but also three other classic classification methods based on accuracy measurements.

Conclusions

The developed mathematical model in the present study is efficient in predicting the probability of intracerebral haemorrhage.

Electronic supplementary material

The online version of this article (10.1186/s12859-019-2741-5) contains supplementary material, which is available to authorized users.

Early blood-brain barrier dysfunction predicts neurological outcome following aneurysmal subarachnoid hemorrhage

BACKGROUND

Disease progression and delayed neurological complications are common after aneurysmal subarachnoid hemorrhage (aSAH). We explored the potential of quantitative blood-brain barrier (BBB) imaging to predict disease progression and neurological outcome.

METHODS

Data were collected as part of the Co-Operative Studies of Brain Injury Depolarizations (COSBID). We analyzed retrospectively, blinded and semi-automatically magnetic resonance images from 124 aSAH patients scanned at 4 time points (24-48 h, 6-8 days, 12-15 days and 6-12 months) after the initial hemorrhage. Volume of brain with apparent pathology and/or BBB dysfunction (BBBD), subarachnoid space and lateral ventricles were measured. Neurological status on admission was assessed using the World Federation of Neurosurgical Societies and Rosen-Macdonald scores. Outcome at ≥6 months was assessed using the extended Glasgow outcome scale and disease course (progressive or non-progressive based on imaging-detected loss of normal brain tissue in consecutive scans). Logistic regression was used to define biomarkers that best predict outcomes. Receiver operating characteristic analysis was performed to assess accuracy of outcome prediction models.

FINDINGS

In the present cohort, 63% of patients had progressive and 37% non-progressive disease course. Progressive course was associated with worse outcome at ≥6 months (sensitivity of 98% and specificity of 97%). Brain volume with BBBD was significantly larger in patients with progressive course already 24-48 h after admission (2.23 (1.23-3.17) folds, median with 95%CI), and persisted at all time points. The highest probability of a BBB-disrupted voxel to become pathological was found at a distance of ≤1 cm from the brain with apparent pathology (0·284 (0·122-0·594), p < 0·001, median with 95%CI). A multivariate logistic regression model revealed power for BBBD in combination with RMS at 24-48 h in predicting outcome (ROC area under the curve = 0·829, p < 0·001).

INTERPRETATION

We suggest that early identification of BBBD may serve as a key predictive biomarker for neurological outcome in aSAH. FUND: Dr. Dreier was supported by grants from the Deutsche Forschungsgemeinschaft (DFG) (DFG DR 323/5-1 and DFG DR 323/10-1), the Bundesministerium für Bildung und Forschung (BMBF) Center for Stroke Research Berlin 01 EO 0801 and FP7 no 602150 CENTER-TBI. Dr. Friedman was supported by grants from Israel Science Foundation and Canada Institute for Health Research (CIHR). Dr. Friedman was supported by grants from European Union's Seventh Framework Program (FP7/2007-2013; grant #602102).

Machine Learning Analysis of Matricellular Proteins and Clinical Variables for Early Prediction of Delayed Cerebral Ischemia After Aneurysmal Subarachnoid Hemorrhage

Although delayed cerebral ischemia (DCI) is a well-known complication after subarachnoid hemorrhage (SAH), there are no reliable biomarkers to predict DCI development. Matricellular proteins (MCPs) have been reported relevant to DCI and expected to become biomarkers. As machine learning (ML) enables the classification of various input data and the result prediction, the aim of this study was to construct early prediction models of DCI development with clinical variables and MCPs using ML analyses. Early-stage clinical data of 95 SAH patients in a prospective cohort were analyzed and applied to a ML algorithm, random forest, to construct three prediction models: (1) a model with only clinical variables on admission, (2) a model with only plasma levels of MCP (periostin, osteopontin, and galectin-3) at post-onset days 1-3, and (3) a model with both clinical variables on admission and MCP values at days 1-3. The prediction accuracy of the development of DCI, angiographic vasospasm, or cerebral infarction and the importance of each feature were computed. The prediction accuracy of DCI development was 93.9% in model 1, 87.2% in model 2, and 95.1% in model 3, but that of angiographic vasospasm or cerebral infarction was lower. The three most important features in model 3 for DCI were periostin, osteopontin, and galectin-3, followed by aneurysm location. All of the early-stage prediction models of DCI development constructed by ML worked with high accuracy and sensitivity. One-time early-stage measurement of plasma MCPs served for reliable prediction of DCI development, suggesting their potential utility as biomarkers.

Predictive Accuracy of Alpha-Delta Ratio on Quantitative Electroencephalography for Delayed Cerebral Ischemia in Patients with Aneurysmal Subarachnoid Hemorrhage: Meta-Analysis

OBJECTIVE

Delayed cerebral ischemia (DCI) is significantly related to death and unfavorable functional outcome in patients with aneurysmal subarachnoid hemorrhage (SAH). The association between alpha-delta ratio (ADR) on quantitative electroencephalography (EEG) and DCI has been reported in several previous studies, but their results are conflicting. This meta-analysis was conducted to assess the accuracy of ADR for DCI prediction in patients with aneurysmal SAH.

METHODS

PubMed and Embase were systematically searched for related records. Study selection and data collection were completed by 2 investigators. Sensitivity, specificity, and their 95% confidence intervals (CIs) were pooled. A summary receiver operating characteristic curve was plotted to show the pooled accuracy. Deeks funnel plot was used to evaluate publication bias.

RESULTS

Five studies were included in this meta-analysis. The pooled sensitivity and specificity of worsening ADR for DCI prediction in patients with aneurysmal SAH were 0.83 (95% CI 0.44-0.97) and 0.74 (95% CI 0.50-0.89), respectively. In addition, the area under the summary receiver operating characteristic curve was 0.84 (95% CI 0.81-0.87). No obvious publication bias was found using Deeks funnel plot (P = 0.29).

CONCLUSIONS

Worsening ADR on quantitative EEG is a reliable predictor of DCI in patients with aneurysmal SAH. Further studies are still needed to confirm the role of quantitative EEG in DCI prediction.

Decision tree analysis in subarachnoid hemorrhage: prediction of outcome parameters during the course of aneurysmal subarachnoid hemorrhage using decision tree analysis

OBJECTIVEThe aim of this study was to create prediction models for outcome parameters by decision tree analysis based on clinical and laboratory data in patients with aneurysmal subarachnoid hemorrhage (aSAH).METHODSThe database consisted of clinical and laboratory parameters of 548 patients with aSAH who were admitted to the Neurocritical Care Unit, University Hospital Zurich. To examine the model performance, the cohort was randomly divided into a derivation cohort (60% [n = 329]; training data set) and a validation cohort (40% [n = 219]; test data set). The classification and regression tree prediction algorithm was applied to predict death, functional outcome, and ventriculoperitoneal (VP) shunt dependency. Chi-square automatic interaction detection was applied to predict delayed cerebral infarction on days 1, 3, and 7.RESULTSThe overall mortality was 18.4%. The accuracy of the decision tree models was good for survival on day 1 and favorable functional outcome at all time points, with a difference between the training and test data sets of < 5%. Prediction accuracy for survival on day 1 was 75.2%. The most important differentiating factor was the interleukin-6 (IL-6) level on day 1. Favorable functional outcome, defined as Glasgow Outcome Scale scores of 4 and 5, was observed in 68.6% of patients. Favorable functional outcome at all time points had a prediction accuracy of 71.1% in the training data set, with procalcitonin on day 1 being the most important differentiating factor at all time points. A total of 148 patients (27%) developed VP shunt dependency. The most important differentiating factor was hyperglycemia on admission.CONCLUSIONSThe multiple variable analysis capability of decision trees enables exploration of dependent variables in the context of multiple changing influences over the course of an illness. The decision tree currently generated increases awareness of the early systemic stress response, which is seemingly pertinent for prognostication.

Machine learning improves prediction of delayed cerebral ischemia in patients with subarachnoid hemorrhage

Background and purpose

Delayed cerebral ischemia (DCI) is a severe complication in patients with aneurysmal subarachnoid hemorrhage. Several associated predictors have been previously identified. However, their predictive value is generally low. We hypothesize that Machine Learning (ML) algorithms for the prediction of DCI using a combination of clinical and image data lead to higher predictive accuracy than previously applied logistic regressions.

Materials and methods

Clinical and baseline CT image data from 317 patients with aneurysmal subarachnoid hemorrhage were included. Three types of analysis were performed to predict DCI. First, the prognostic value of known predictors was assessed with logistic regression models. Second, ML models were created using all clinical variables. Third, image features were extracted from the CT images using an auto-encoder and combined with clinical data to create ML models. Accuracy was evaluated based on the area under the curve (AUC), sensitivity and specificity with 95% CI.

Results

The best AUC of the logistic regression models for known predictors was 0.63 (95% CI 0.62 to 0.63). For the ML algorithms with clinical data there was a small but statistically significant improvement in the AUC to 0.68 (95% CI 0.65 to 0.69). Notably, aneurysm width and height were included in many of the ML models. The AUC was highest for ML models that also included image features: 0.74 (95% CI 0.72 to 0.75).

Conclusion

ML algorithms significantly improve the prediction of DCI in patients with aneurysmal subarachnoid hemorrhage, particularly when image features are also included. Our experiments suggest that aneurysm characteristics are also associated with the development of DCI.