A nomogram for predicting malignant cerebral artery infarction in the modern thrombectomy era

An integrated nomogram combining clinical and radiomic features of hyperattenuated imaging markers to predict malignant cerebral edema following endovascular thrombectomy

Background

Malignant cerebral edema (MCE), a potential complication following endovascular thrombectomy (EVT) in the treatment of acute ischemic stroke (AIS), can result in significant disability and mortality. This study aimed to develop a nomogram model based on the hyperattenuated imaging marker (HIM), characterized by hyperattenuation on head noncontrast computed tomography (CT) immediately after thrombectomy, to predict MCE in patients receiving EVT.

Methods

In this retrospective cohort study, we selected 151 patients with anterior circulation large-vessel occlusion who received endovascular treatment. The patients were randomly allocated into training (n=121) and test (n=30) cohorts. HIM was used to extract radiomics characteristics. Conventional clinical and radiological features associated with MCE were also extracted. A model based on extreme gradient boosting (XGBoost) machine learning using fivefold cross-validation was employed to acquire radiomics and clinical features. Based on HIM, clinical and radiological signatures were used to construct a prediction nomogram for MCE. Subsequently, the signatures were merged through logistic regression (LR) analysis in order to create a comprehensive clinical radiomics nomogram.

Results

A total of 28 patients out of 151 (18.54%) developed MCE. The analysis of the receiver operating characteristic curve indicated an area under the curve (AUC) of 0.999 for the prediction of MCE in the training group and an AUC of 0.938 in the test group. The clinical and radiomics nomogram together showed the highest accuracy in predicting outcomes in both the training and test groups.

Conclusions

The novel nomogram, which combines clinical manifestations and imaging findings based on postinterventional HIM, may serve as a predictor for MCE in patients experiencing AIS after EVT.

A dynamic nomogram for predict individual risk of malignant brain edema after endovascular thrombectomy in acute ischemic stroke

The aim of this study was to develop a dynamic nomogram combining clinical and imaging data to predict malignant brain edema (MBE) after endovascular thrombectomy (EVT) in patients with large vessel occlusion stroke (LVOS). We analyzed the data of LVOS patients receiving EVT at our center from October 2018 to February 2023, and divided a 7:3 ratio into the training cohort and internal validation cohort, and we also prospectively collected patients from another stroke center for external validation. MBE was defined as a midline shift or pineal gland shift > 5 mm, as determined by computed tomography (CT) scans obtained within 7 days after EVT. A nomogram was constructed using logistic regression analysis, and its receiver operating characteristic curve (ROC) and calibration were assessed in three cohorts. A total of 432 patients were enrolled in this study, with 247 in the training cohort, 100 in the internal validation cohort, and 85 in the external validation cohort. MBE occurred in 24% (59) in the training cohort, 16% (16) in the internal validation cohort and 14% (12) in the external validation cohort. After adjusting for various confounding factors, we constructed a nomogram including the clot burden score (CBS), baseline neutrophil count, core infarct volume on CTP before EVT, collateral index, and the number of retrieval attempts. The AUCs of the training cohorts were 0.891 (95% CI 0.840-0.942), the Hosmer-Lemeshow test showed good calibration of the nomogram (P = 0.879). And our nomogram performed well in both internal and external validation data. Our nomogram demonstrates promising potential in identifying patients at elevated risk of MBE following EVT for LVOS.

An Explainable Artificial Intelligence Model to Predict Malignant Cerebral Edema after Acute Anterior Circulating Large-Hemisphere Infarction

INTRODUCTION

Malignant cerebral edema (MCE) is a serious complication and the main cause of poor prognosis in patients with large-hemisphere infarction (LHI). Therefore, the rapid and accurate identification of potential patients with MCE is essential for timely therapy. This study utilized an artificial intelligence-based machine learning approach to establish an interpretable model for predicting MCE in patients with LHI.

METHODS

This study included 314 patients with LHI not undergoing recanalization therapy. The patients were divided into MCE and non-MCE groups, and the eXtreme Gradient Boosting (XGBoost) model was developed. A confusion matrix was used to measure the prediction performance of the XGBoost model. We also utilized the SHapley Additive exPlanations (SHAP) method to explain the XGBoost model. Decision curve and receiver operating characteristic curve analyses were performed to evaluate the net benefits of the model.

RESULTS

MCE was observed in 121 (38.5%) of the 314 patients with LHI. The model showed excellent predictive performance, with an area under the curve of 0.916. The SHAP method revealed the top 10 predictive variables of the MCE such as ASPECTS score, NIHSS score, CS score, APACHE II score, HbA1c, AF, NLR, PLT, GCS, and age based on their importance ranking.

CONCLUSION

An interpretable predictive model can increase transparency and help doctors accurately predict the occurrence of MCE in LHI patients not undergoing recanalization therapy within 48 h of onset, providing patients with better treatment strategies and enabling optimal resource allocation.

Association Between Hypoperfusion Intensity Ratio and Postthrombectomy Malignant Brain Edema for Acute Ischemic Stroke

BACKGROUND

Malignant brain edema (MBE) is a life-threatening complication that can occur after mechanical thrombectomy (MT) for acute ischemic stroke. The hypoperfusion intensity ratio (HIR) reflects the tissue-level perfusion status within the ischemic territory. This study investigated the association between HIR and MBE occurrence after MT in patients with anterior circulation large artery occlusion.

METHODS

We conducted a retrospective cohort study of patients who received MT at a comprehensive stroke center from February 2020 to June 2022. Using computed tomography perfusion, the HIR was derived from the ratio of tissue volume with a time to maximum (Tmax) > 10 s to that with a Tmax > 6 s. We dichotomized patients based on the occurrence of MBE following MT. The primary outcome, assessed using a multivariable logistic regression model, was the MBE occurrence post MT. The secondary outcome focused on favorable outcomes, defined as achieving a modified Rankin Scale score of 0-2 at 90 days.

RESULTS

Of the 603 included patients, 90 (14.9%) developed MBE after MT. The median HIR exhibited a significantly higher value in the MBE group compared with the non-MBE group (0.5 vs. 0.3; P < 0.001). Multivariable logistic regression analysis indicated that a higher HIR (adjusted odds ratio [aOR] 8.98; 95% confidence interval [CI] 2.85-28.25; P < 0.001), baseline large infarction (Alberta Stroke Program Early Computed Tomography Score < 6; aOR 1.77; 95% CI 1.04-3.01; P = 0.035), internal carotid artery occlusion (aOR 1.80; 95% CI 1.07-3.01; P = 0.028), and unsuccessful recanalization (aOR 8.45; 95% CI 4.75-15.03; P < 0.001) were independently associated with MBE post MT. Among those with successful recanalization, a higher HIR (P = 0.017) and baseline large infarction (P = 0.032) remained as predictors of MBE occurrence. Furthermore, a higher HIR (P = 0.001) and the occurrence of MBE (P < 0.001) both correlated with reduced odds of achieving favorable outcomes.

CONCLUSIONS

The presence of a higher HIR on pretreatment perfusion imaging serves as a robust predictor for MBE occurrence after MT, irrespective of successful recanalization.

The risk and outcome of malignant brain edema in post-mechanical thrombectomy: acute ischemic stroke by anterior circulation occlusion

BACKGROUND AND PURPOSE

Malignant brain edema (MBE) occurring after mechanical thrombectomy (MT) in acute ischemic stroke (AIS) could lead to severe disability and mortality. We aimed to investigate the incidence, predictors, and clinical outcomes of MBE in patients with AIS after MT.

METHODS

The clinical and imaging data of 155 patients with AIS of anterior circulation after MT were studied. Standard non-contrast CT was used to evaluate baseline imaging characteristics at admission. Clinical outcomes were measured using the 90-day modified Rankin Scale (mRS) score. Based on the follow-up CT scans performed within 72 h after MT, the patients were classified into MBE and non-MBE group. MBE was defined as a midline shift of ≥ 5 mm with signs of local brain swelling. Univariate and multivariate regression analyses were used to analyze the relationship between MBE and clinical outcomes and identify the predictors that correlate with MBE.

RESULTS

MBE was observed in 19.4% of the patients who underwent MT and was associated with a lower rate of favorable 90-day clinical outcomes. Significant differences were observed in both MBE and non-MBE groups: baseline Alberta Stroke Program Early CT (ASPECT) score, hyperdense middle cerebral artery sign (HMCAS), baseline signs of early infarct, angiographic favorable collaterals, number of retrieval attempts, and revascularization rate. Multivariate analysis indicated that low baseline ASPECT score, absent HMCAS, angiographic poor collaterals, more retrieval attempt count, and poor revascularization independently influenced the occurrence of MBE in AIS patients with anterior circulation after MT.

CONCLUSION

MBE was associated with a lower rate of favorable 90-day clinical outcomes. Low baseline ASPECT score, absent HMCAS, angiographic poor collaterals, more retrieval attempt count and poor revascularization were independently associated with MBE after MT.

Predicting the emergence of malignant brain oedema in acute ischaemic stroke: a prospective multicentre study with development and validation of predictive modelling

Background

We aimed to develop and validate a prognostic model for predicting malignant brain oedema in patients with acute ischaemic stroke in a real-world setting of practice.

Methods

A prospective multicentre study enrolled adult patients with acute ischaemic stroke with brain CT < 24 h of onset of symptoms admitted to nine tertiary-level hospitals in China between September 2017 and December 2019. Malignant brain oedema was defined as any patient who had decompressive craniectomy, discharge in coma, or in-hospital death attributed to symptomatic brain swelling. The derivation cohort was a consecutive cohort of patients from one centre and the validation cohort was non-consecutive patients from the other centres. Multivariable logistic regression was used to define independent predictors from baseline clinical characteristics, imaging features, complications, and management. A web-based nomogram and a risk score were developed based on the final model. Model performance was assessed for discrimination and calibration in both derivation and validation cohorts. The study is registered, NCT03222024.

Findings

Based on the derivation cohort (n = 1627), the model was developed with seven variables including large infarct (adjusted odds ratio [OR] 40.90, 95% CI 20.20-82.80), National Institutes of Health Stroke Scale (NIHSS) score (OR 1.09, 1.06-1.12), thrombolysis (OR 2.11, 1.18-3.78), endovascular treatment (OR 2.87, 1.47-5.59), pneumonia (OR 2.47, 1.53-3.97), brain atrophy (OR 0.57, 0.37-0.86), and recanalisation (OR 0.36, 0.17-0.75). The classification threshold of a predicted probability ≥0.14 showed good discrimination and calibration in both derivation cohort (area under the receiver-operating curve [AUC] 0.90, 0.87-0.92; sensitivity 0.95, 0.92-0.98) and validation cohort (n = 556, AUC 0.88, 0.82-0.95; sensitivity 0.84, 0.73-0.95). The risk score based on this model had a total point that ranged from -1 to 20, with an optimal score of ≥10 showing good discrimination and calibration in both derivation (AUC 0.89, 0.87-0.92; sensitivity 0.95, 0.92-0.98) and validation (AUC 0.88, 0.82-0.95; sensitivity 0.84, 0.73-0.95) cohorts.

Interpretation

The INTEP-AR model (i.e. large Infarct, NIHSS score, Thrombolysis, Endovascular treatment, Pneumonia, brain Atrophy, and Recanalisation) incorporating multiple clinical and radiological characteristics has shown good prognostic value for predicting malignant brain oedema after acute ischaemic stroke.

Funding

National Natural Science Foundation of China; Science and Technology Department of Sichuan Province; West China Hospital.

Predictors and outcome of malignant cerebral edema after successful reperfusion in anterior circulation stroke

BACKGROUND AND OBJECTIVE

Risk factors and predictors of malignant cerebral edema (MCE) after successful endovascular thrombectomy (EVT) were not fully explored. This study aimed to evaluate the incidence and risk factors of MCE after successful reperfusion.

METHODS

We retrospectively analyzed consecutive ischemic stroke patients who underwent EVT in our institution from November 2015 to April 2022. Patients who failed to achieve successful reperfusion (modified thrombolysis in cerebral infarction [mTICI]<2b) were excluded. Based on multivariate logistic models, the best-fit monogram was established. The discriminative performance was assessed by the receiver operating characteristics curve (ROC).

RESULTS

A total of 307 patients were included and 48 (15.6%) were diagnosed with MCE after successful reperfusion. Patients with MCE after successful reperfusion had a lower 3-month favorable outcome (15.2% versus 59.6%; p<0.001), a lower 3-month good outcome (17.4% versus 68.4%; p<0.001), and a higher rate of mortality at 3-month (54.3% versus 8.8%; p<0.001) compared with patients without MCE. Predictors of MCE after successful reperfusion included admission glucose level, baseline National Institutes of Health Stroke Scale (NIHSS) score, stroke etiology, occlusion site and puncture-to-reperfusion (PTR) time>120 min. The area under the curve (AUC) of the nomogram was 0.805 (95% CI, 0.756-0.847).

CONCLUSIONS

MCE after successful reperfusion is associated with poor outcome and mortality. A nomogram containing admission glucose level, baseline NIHSS score, stroke etiology, occlusion site and PTR time>120 min may predict the risk of MCE after successful reperfusion in patients with acute ischemic stroke and treated successfully with EVT.