Comparing the Prognostic Impact of Age and Baseline National Institutes of Health Stroke Scale in Acute Stroke due to Large Vessel Occlusion

Magnetic resonance imaging-based deep learning imaging biomarker for predicting functional outcomes after acute ischemic stroke

PURPOSE

Clinical risk scores are essential for predicting outcomes in stroke patients. The advancements in deep learning (DL) techniques provide opportunities to develop prediction applications using magnetic resonance (MR) images. We aimed to develop an MR-based DL imaging biomarker for predicting outcomes in acute ischemic stroke (AIS) and evaluate its additional benefit to current risk scores.

METHOD

This study included 3338 AIS patients. We trained a DL model using deep neural network architectures on MR images and radiomics to predict poor functional outcomes at three months post-stroke. The DL model generated a DL score, which served as the DL imaging biomarker. We compared the predictive performance of this biomarker to five risk scores on a holdout test set. Additionally, we assessed whether incorporating the imaging biomarker into the risk scores improved the predictive performance.

RESULTS

The DL imaging biomarker achieved an area under the receiver operating characteristic curve (AUC) of 0.788. The AUCs of the five studied risk scores were 0.789, 0.793, 0.804, 0.810, and 0.826, respectively. The imaging biomarker's predictive performance was comparable to four of the risk scores but inferior to one (p = 0.038). Adding the imaging biomarker to the risk scores improved the AUCs (p-values) to 0.831 (0.003), 0.825 (0.001), 0.834 (0.003), 0.836 (0.003), and 0.839 (0.177), respectively. The net reclassification improvement and integrated discrimination improvement indices also showed significant improvements (all p < 0.001).

CONCLUSIONS

Using DL techniques to create an MR-based imaging biomarker is feasible and enhances the predictive ability of current risk scores.

The Association Between National Institutes of Health Stroke Scale Score and Clinical Outcome in Patients with Large Core Infarctions Undergoing Endovascular Treatment

INTRODUCTION

This study aimed to analyze the association between baseline National Institutes of Health Stroke Scale (NIHSS) scores and clinical outcomes in patients with large core infarctions undergoing endovascular treatment (EVT), a relationship that remains unclear.

METHODS

Data were obtained from the MAGIC study, a prospective multicenter cohort study focusing on patients with acute large core ischemic stroke. This analysis evaluated the impact of NIHSS scores on EVT outcomes in patients with large core infarctions. Primary outcome metrics included favorable outcomes (modified Rankin Scale [mRS] of 0-3 at 90 days), while secondary outcomes encompassed shifts in mRS scores, functional independence (mRS score of 0-2), mRS score of 0-4, and successful recanalization rates. Adverse events considered were symptomatic intracranial hemorrhage (sICH) and mortality.

RESULTS

A total of 490 patients were enrolled in this study. Higher baseline NIHSS scores were inversely correlated with favorable outcomes (adjusted odds ratio [OR] in model 3, 0.848 [0.797-0.903], P < 0.001), particularly in patients with NIHSS scores above 20 (adjusted OR in model 3, 0.518 [0.306-0.878] vs. 0.290 [0.161-0.523]). Regarding adverse events, higher baseline NIHSS scores significantly correlated with increased 90-day mortality rates (adjusted OR in model 3, 1.129 [1.072-1.189], P < 0.001). This correlation became insignificant when baseline NIHSS scores exceeded 22. Additionally, baseline NIHSS scores partially mediated the association between age (indirect effect = - 0.0005, 19.39% mediated) and sex (indirect effect = 0.0457, 25.08% mediated) with the primary outcome.

CONCLUSIONS

The findings indicate that higher baseline NIHSS scores correlate with poorer outcomes and increased mortality, particularly when scores exceed 20. Moreover, age and sex indirectly influence favorable outcomes through their association with baseline NIHSS scores.

Mechanical thrombectomy decision making and prognostication: Stroke treatment Assessments prior to Thrombectomy In Neurointervention (SATIN) study

BACKGROUND

Mechanical thrombectomy (MT) is the standard-of-care treatment for stroke patients with emergent large vessel occlusions. Despite this, little is known about physician decision making regarding MT and prognostic accuracy.

METHODS

A prospective multicenter cohort study of patients undergoing MT was performed at 11 comprehensive stroke centers. The attending neurointerventionalist completed a preprocedure survey prior to arterial access and identified key decision factors and the most likely radiographic and clinical outcome at 90 days. Post hoc review was subsequently performed to document hospital course and outcome.

RESULTS

299 patients were enrolled. Good clinical outcome (modified Rankin Scale (mRS) score of 0-2) was obtained in 38% of patients. The most frequently identified factors influencing the decision to proceed with thrombectomy were site of occlusion (81%), National Institutes of Health Stroke Scale score (74%), and perfusion imaging mismatch (43%). Premorbid mRS score determination in the hyperacute setting accurately matched retrospectively collected data from the hospital admission in only 140 patients (46.8%). Physicians correctly predicted the patient's 90 day mRS tertile (0-2, 3-4, or 5-6) and final modified Thrombolysis in Ischemic Cerebral Infarction score preprocedure in only 44.2% and 44.3% of patients, respectively. Clinicians tended to overestimate the influence of occlusion site and perfusion imaging on outcomes, while underestimating the importance of pre-morbid mRS.

CONCLUSIONS

This is the first prospective study to evaluate neurointerventionalists' ability to accurately predict clinical outcome after MT. Overall, neurointerventionalists performed poorly in prognosticating patient 90 day outcomes, raising ethical questions regarding whether MT should be withheld in patients with emergent large vessel occlusions thought to have a poor prognosis.

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.

7-Day National Institutes of Health Stroke Scale as a surrogate marker predicting ischemic stroke patients' outcome following endovascular therapy

Background

Early neurological deterioration after endovascular thrombectomy (EVT) is associated with poor prognosis. National Institutes of Health Stroke Scale (NIHSS) score measured at 24 h after EVT may be a better outcome predictor than other methods that focus on changes in NIHSS. Nevertheless, clinical fluctuations in ischemic stroke patients during the immediate phase after symptoms onset are well recognized. Therefore, a delayed NIHSS evaluation may improve prognostic accuracy. We evaluate the 7-day NIHSS in predicting long-term patient outcomes after EVT.

Methods

This was a multi-center retrospective cohort study of 300 consecutive ischemic stroke patients with large vessel occlusion who underwent EVT at three-stroke centers in China from August 2018 to March 2022. NIHSS was recorded on admission, pre-EVT, 24 h, and 7 days after EVT.

Results

A total of 236 eligible patients were subdivided into two groups: 7-day NIHSS ≤6 and NIHSS >6 post-EVT. 88.29% achieved a favorable outcome (modified Rankin Scale 0-2) in the NIHSS ≤6 group compared to 15.20% in the NIHSS >6 group at 90 days, and an improved favorable outcome in the former group was observed after adjusting for potential confounding factors (adjusted odds ratio 39.7, 95% confidence interval, 17.5-89.7, p < 0.001).

Conclusion

The 7-day NIHSS score may be a reliable predictor of 90-day stroke patient outcome after EVT.

Predicting functional outcome in acute ischemic stroke patients after endovascular treatment by machine learning

Background

Endovascular therapy (EVT) was the standard treatment for acute ischemic stroke with large vessel occlusion. Prognosis after EVT is always a major concern. Here, we aimed to explore a predictive model for patients after EVT.

Method

A total of 156 patients were retrospectively enrolled. The primary outcome was functional dependence (defined as a 90-day modified Rankin Scale score ≤ 2). Least absolute shrinkage and selection operator and univariate logistic regression were used to select predictive factors. Various machine learning algorithms, including multivariate logistic regression, linear discriminant analysis, support vector machine, k-nearest neighbors, and decision tree algorithms, were applied to construct prognostic models.

Result

Six predictive factors were selected, namely, age, baseline National Institute of Health Stroke Scale (NIHSS) score, Alberta Stroke Program Early CT (ASPECT) score, modified thrombolysis in cerebral infarction score, symptomatic intracerebral hemorrhage (sICH), and complications (pulmonary infection, gastrointestinal bleeding, and cardiovascular events). Based on these variables, various models were constructed and showed good discrimination. Finally, a nomogram was constructed by multivariate logistic regression and showed a good performance.

Conclusion

Our nomogram, which was composed of age, baseline NIHSS score, ASPECT score, recanalization status, sICH, and complications, showed a very good performance in predicting outcome after EVT.

Automated quantification of atrophy and acute ischemic volume for outcome prediction in endovascular thrombectomy

Background

Short- and long-term outcomes from endovascular thrombectomy (EVT) for large vessel occlusion stroke remain variable. Numerous relevant predictors have been identified, including severity of neurological deficits, age, and imaging features. The latter is typically defined as acute changes (most commonly Alberta Stroke Programme Early CT Score, ASPECTS, at presentation), but there is little information on the impact of imaging assessment of premorbid brain health as a determinant of outcome.

Aims

To examine the impact of automated measures of stroke severity and underlying brain frailty on short- and long-term outcomes in acute stroke treated with EVT.

Methods

In 215 patients with anterior circulation stroke, who subsequently underwent EVT, automated analysis of presenting non-contrast CT scans was used to determine acute ischemic volume (AIV) and e-ASPECTS as markers of stroke severity, and cerebral atrophy as a marker of brain frailty. Univariate and multivariate logistic regression were used to identify significant predictors of NIHSS improvement, modified Rankin scale (mRS) at 90 and 30 days, mortality at 90 days and symptomatic intracranial hemorrhage (sICH) following successful EVT.

Results

For long-term outcome, atrophy and presenting NIHSS were significant predictors of mRS 0-2 and death at 90 days, whereas age did not reach significance in multivariate analysis. Conversely, for short-term NIHSS improvement, AIV and age were significant predictors, unlike presenting NIHSS. The interaction between age and NIHSS was similar to the interaction of AIV and atrophy for mRS 0-2 at 90 days.

Conclusion

Combinations of automated software-based imaging analysis and clinical data can be useful for predicting short-term neurological outcome and may improve long-term prognostication in EVT. These results provide a basis for future development of predictive tools built into decision-aiding software in stroke.

Thrombectomy in large vessel occlusion stroke-Does age matter?

OBJECTIVES

Endovascular treatment (EVT) is the gold standard treatment for emergent large vessel occlusion (LVO). The benefit of EVT for emergent LVO in elderly patients (>80 years old) is still debated as they have been under-represented in randomized controlled trials. Elderly patients with an emergent LVO are a growing population warranting further study.

MATERIALS & METHODS

We included 225 consecutive patients treated with EVT for LVO either in the anterior or posterior circulation. The clinical outcome was assessed using the National Institute of Health Stroke Scale (NIHSS). Long-term functional outcome was assessed using 90-day modified ranking scale (mRS).

RESULTS

Neurological improvement: A five-year higher age predicted a 0.43 higher mean NIHSS score after EVT (p = .027). After adjusting for confounders (influencing variables), the association between age and post-interventional NIHSS was reduced and non-significant (p = .17). At discharge, a five-year higher age predicted a 0.74 higher mean NIHSS (p = .003). After adjusting for confounders this association was reduced and non-significant (p = .06). Long-term functional outcome: A five-year higher age predicted a 0.20 higher mRS at three months (p < .001). When adjusting for confounders this number was reduced to 0.16, yet still highly significant (p < .001).

CONCLUSIONS

Age seems to have a minor role in predicting neurological improvement after EVT but has an impact on long-term functional outcome. The decision to perform or withhold EVT should therefore not solely be based on age.

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

Introduction

Current guidelines suggest that perfusion imaging should only be performed > 6 h after symptom onset. Pathophysiologically, brain perfusion should matter whatever the elapsed time. We aimed to compare relative contribution of recanalization time and stroke core volume in predicting functional outcome in patients treated by endovascular thrombectomy within 6-h of stroke-onset.

Methods

Consecutive patients presenting between January 2015 and June 2021 with (i) an acute ischaemic stroke due to an anterior proximal occlusion, (ii) a successful thrombectomy (TICI >2a) within 6-h of symptom-onset and (iii) CT perfusion imaging were included. Core stroke volume was automatically computed using RAPID software. Two linear regression models were built that included in the null hypothesis the pre-treatment NIHSS score and the hypoperfusion volume (Tmax > 6 s) as confounding variables and 24 h post-recanalization NIHSS and 90 days mRS as outcome variables. Time to recanalization was used as covariate in one model and stroke core volume as covariate in the other.

Results

From a total of 377 thrombectomies, 94 matched selection criteria. The Model null hypothesis explained 37% of the variability for 24 h post-recanalization NIHSS and 42% of the variability for 90 days MRS. The core volume as covariate increased outcome variability prediction to 57 and 56%, respectively. Time to recanalization as covariate marginally increased outcome variability prediction from 37 and 34% to 40 and 42.6%, respectively.

Conclusion

Core stroke volume better explains outcome variability in comparison to the time to recanalization in anterior large vessel occlusion stroke with successful thrombectomy done within 6 h of symptoms onset. Still, a large part of outcome variability prediction fails to be explained by the usual predictors.