Stroke Core Volume Weighs More Than Recanalization Time for Predicting Outcome in Large Vessel Occlusion Recanalized Within 6 h of Symptoms Onset

Combining clinical and imaging data for predicting functional outcomes after acute ischemic stroke: an automated machine learning approach

This study aimed to develop and validate an automated machine learning (ML) system that predicts 3-month functional outcomes in acute ischemic stroke (AIS) patients by combining clinical and neuroimaging features. Functional outcomes were categorized as unfavorable (modified Rankin Scale ≥ 3) or not. A clinical model employing optimal clinical features (Model_A), a convolutional neural network model incorporating imaging data (Model_B), and an integrated model combining both imaging and clinical features (Model_C) were developed and tested to predict unfavorable outcomes. The developed models were compared with each other and with traditional risk-scoring models. The dataset comprised 4147 patients from a multicenter stroke registry, with 1268 (30.6%) experiencing unfavorable outcomes. Age, initial NIHSS, and early neurologic deterioration were identified as the most important clinical features. The ML model prediction achieved an area under the curves of 0.757 (95% CI 0.726-0.789) for Model_A, 0.725 (95% CI 0.693-0.755) for Model_B, and 0.786 (95% CI 0.757-0.814) for Model_C in the test set. The integrated models outperformed traditional risk-scoring models by 0.21 (95% CI 0.16-0.25) for HIAT and 0.15 (95% CI 0.11-0.19) for THRIVE. In conclusion, the integrated ML system enhanced stroke outcome prediction by combining imaging data and clinical features, outperforming traditional risk-scoring models.

Interpretable machine learning for prediction of clinical outcomes in acute ischemic stroke

Background and aims

Predicting the prognosis of acute ischemic stroke (AIS) is crucial in a clinical setting for establishing suitable treatment plans. This study aimed to develop and validate a machine learning (ML) model that predicts the functional outcome of AIS patients and provides interpretable insights.

Methods

We included AIS patients from a multicenter stroke registry in this prognostic study. ML-based methods were utilized to predict 3-month functional outcomes, which were categorized as either favorable [modified Rankin Scale (mRS) ≤ 2] or unfavorable (mRS ≥ 3). The SHapley Additive exPlanations (SHAP) method was employed to identify significant features and interpret their contributions to the predictions of the model.

Results

The dataset comprised a derivation set of 3,687 patients and two external validation sets totaling 250 and 110 patients each. Among them, the number of unfavorable outcomes was 1,123 (30.4%) in the derivation set, and 93 (37.2%) and 32 (29.1%) in external sets A and B, respectively. Among the ML models used, the eXtreme Gradient Boosting model demonstrated the best performance. It achieved an area under the receiver operating characteristic curve (AUC-ROC) of 0.790 (95% CI: 0.775-0.806) on the internal test set and 0.791 (95% CI: 0.733-0.848) and 0.873 (95% CI: 0.798-0.948) on the two external test sets, respectively. The key features for predicting functional outcomes were the initial NIHSS, early neurologic deterioration (END), age, and white blood cell count. The END displayed noticeable interactions with several other features.

Conclusion

ML algorithms demonstrated proficient prediction for the 3-month functional outcome in AIS patients. With the aid of the SHAP method, we can attain an in-depth understanding of how critical features contribute to model predictions and how changes in these features influence such predictions.

Crossed Cerebellar Diaschisis Worsens the Clinical Presentation in Acute Large Vessel Occlusion

INTRODUCTION

Initial NIHSS in anterior large vessel occlusion (LVO) correlates partially with the hypoperfusion volume. We aimed at assessing the contribution of crossed cerebellar diaschisis (CCD) from the hypoperfused territory on LVO initial clinical deficit.

METHODS

CCD was retrospectively identified by brain CT perfusion imaging (CTP) in patients with anterior LVO treated by mechanical thrombectomy from January 2017 to July 2021. CCD was defined by CTP parameter alteration in the contralateral cerebellar hemisphere to the LVO. NIHSS, clinical/perfusion variables, and CCD were included in regression models to assess their interrelationships.

RESULTS

206 patients were included. CCD was present in 90 patients (69%). NIHSS scores were higher on admission and at stroke discharge among patients with CCD (17.90 ± 6.1 vs. 11.4 ± 8.4, p < 0.001; 9.6 ± 7.7 vs. 6.6 ± 7.9, p = 0.049; respectively). Patients with a CCD had higher stroke volumes (118.2 ± 60.3 vs. 69.3 ± 59.7, p < 0.001) and lower rate of known atrial fibrillation (22% vs. 41%, p = 0.021). On multivariable logistic regression, CCD independently worsened the initial NIHSS (OR 4.85 [2.37-7.33]; p < 0.001).

CONCLUSION

CCD is found in 69% of LVO on admission CTP, correlates with stroke volumes, and independently worsens initial NIHSS.

Cerebellar cognitive affective syndrome after acute cerebellar stroke

Introduction

The cerebellum modulates both motor and cognitive behaviors, and a cerebellar cognitive affective syndrome (CCAS) was described after a cerebellar stroke in 1998. Yet, a CCAS is seldom sought for, due to a lack of practical screening scales. Therefore, we aimed at assessing both the prevalence of CCAS after cerebellar acute vascular lesion and the yield of the CCAS-Scale (CCAS-S) in an acute stroke setting.

Materials and methods

All patients admitted between January 2020 and January 2022 with acute onset of a cerebellar ischemic or haemorrhagic first stroke at the CUB-Hôpital Erasme and who could be evaluated by the CCAS-S within a week of symptom onset were included.

Results

Cerebellar acute vascular lesion occurred in 25/1,580 patients. All patients could complete the CCAS-S. A definite CCAS was evidenced in 21/25 patients. Patients failed 5.2 ± 2.12 items out of 8 and had a mean raw score of 68.2 ± 21.3 (normal values 82–120). Most failed items of the CCAS-S were related to verbal fluency, attention, and working memory.

Conclusion

A definite CCAS is present in almost all patients with acute cerebellar vascular lesions. CCAS is efficiently assessed by CCAS-S at bedside tests in acute stroke settings. The magnitude of CCAS likely reflects a cerebello-cortical diaschisis.