Early neurological stability predicts adverse outcome after acute ischemic stroke

Irvine, Hannah; Battey, Thomas W.K.; Ostwaldt, Ann-Christin; Campbell, Bruce; Davis, Stephen M.; Donnan, Geoffrey A; Sheth, Kevin N; Kimberly, W. Taylor

doi:10.1177/1747493016654484

Cited by 27 publications

(24 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The option to use the semiautomatic edge‐finding tool makes it easier to segment regions of interest, like acute stroke lesions and hemisphere volumes. For determination of lesional swelling volumes, we used a method described in detail previously . Briefly, DWI lesion volumes were determined on the baseline (BL) and the follow‐up (FU) images independently, and stroke lesion expansion (∆DWI) was calculated.…”

Section: Methodsmentioning

confidence: 99%

“…For determination of lesional swelling volumes, we used a method described in detail previously. [9][10][11] Briefly, DWI lesion volumes were determined on the baseline (BL) and the follow-up (FU) images independently, and stroke lesion expansion (DWI) was calculated. Subsequently, the FU image was coregistered onto the BL DWI and the mask for the BL lesion was superimposed onto the FU image ( Fig 1B).…”

Section: Imaging Analysis Midline Shiftmentioning

confidence: 99%

“…The presence of lesional swelling as determined with this method independently predicted poor outcome and mortality . Lesional swelling is also associated with early neurological deterioration after stroke . It has also been shown that lower lesional swelling volume was associated with early reperfusion …”

Section: Introductionmentioning

confidence: 97%

“…9 Lesional swelling is also associated with early neurological deterioration after stroke. 11 It has also been shown that lower lesional swelling volume was associated with early reperfusion. 10 To determine which imaging measures of mass effect are most suitable to predict outcome across a range of stroke volumes, we evaluated the relative performance of each marker in the Echoplanar Imaging Thrombolysis Evaluation Trial (EPITHET) cohort.…”

Section: Introductionmentioning

confidence: 98%

See 3 more Smart Citations

Comparative Analysis of Markers of Mass Effect after Ischemic Stroke

Ostwaldt

Battey

Irvine

et al. 2018

Journal of Neuroimaging

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Imaging Analysis Midline Shiftmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 98%

See 2 more Smart Citations

Comparative Analysis of Markers of Mass Effect after Ischemic Stroke

Ostwaldt

Battey

Irvine

et al. 2018

Journal of Neuroimaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…5 It considers age, NIHSS, and chronic disorders-hypertension, diabetes mellitus, and atrial fibrillation. Additionally, the clinician is frequently engaged in the prediction of disability of the patient in the immediate post-intervention period, which could be enhanced by more clues form the patient's clinical, 12 imaging, 13 and hemodynamic trends. Additionally, the ASTRAL score estimates mortality and the THRIVE score was tested to measure the whole range of mRS classes by ordinal shift analysis.…”

Section: And the Totaled Health Risks In Vascularmentioning

confidence: 99%

Prognostic yield of imaging before and after recanalization treatments in ischemic stroke

et al. 2020

View full text Add to dashboard Cite

Objectives:The scores to predict outcome in ischemic stroke were validated prior to the approval of modern revascularization treatments. We evaluated the accuracy of pre and post-treatment models in a recent recanalization therapy cohort and whether radiological and ultrasound findings could improve their accuracy. Material & Methods:We included 375 anterior circulation ischemic stroke patients treated with intravenous thrombolysis or thrombectomy during 2017 and 2018.We collected demographic, clinical, and imaging data. We built pre and post-treatment logistic regression models to predict independence (modified Rankin Scale 0-2) at 3 months. The models included the Alberta Stroke Program Early CT Score (ASPECTS), infarct volume (ABC/2 method), and the Thrombolysis in Brain Ischemia (TIBI) ultrasonographic grade of recanalization. We compared areas under the receiver operating characteristic curve (AUC).Results: Our preintervention model, combining neurological deficit severity, age, and admission glycemia, was not improved by the inclusion of ASPECTS (AUC 0.80 vs 0.79, P = .28). Early neurological recovery at 24-hour significantly increased prognostic performance (AUC = 0.85, P < .01), which did not change by adding final infarct volume or the persistence of arterial occlusion of the affected territory (AUC = 0.86 and 0.85, P > .05).Conclusions: Models that combine simple variables such as neurological deficit severity, age, and admission glycemia were the most useful for predicting functional outcome in ischemic stroke patients submitted to revascularization treatments. Pre and post-treatment imaging findings did not enhance prognostic accuracy when compared to the patient's clinical improvement.

show abstract

Predicting Functional Outcome Using 24‐Hour Post‐Treatment Characteristics: Application of Machine Learning Algorithms in the STRATIS Registry

Castonguay

Zoghi

Zaidat

et al. 2022

Annals of Neurology

View full text Add to dashboard Cite

Objective: Machine learning (ML) algorithms have emerged as powerful predictive tools in the field stroke. Here, we examine the predictive accuracy of ML models for predicting functional outcomes using 24-hour post-treatment characteristics in the Systematic Evaluation of Patients Treated With Neurothrombectomy Devices for Acute Ischemic Stroke (STRATIS) Registry. Methods: ML models, adaptive boost, random forest (RF), classification and regression trees (CART), C5.0 decision tree (C5.0), support vector machine (SVM), least absolute shrinkage and selection operator (LASSO), and logistic regression (LR), and traditional LR models were used to predict 90-day functional outcome (modified Rankin Scale score 0-2). Twenty-four-hour National Institutes of Health Stroke Scale (NIHSS) was examined as a continuous or dichotomous variable in all models. Model accuracy was assessed using the area under characteristic curve (AUC). Results: The 24-hour NIHSS score was a top-predictor of functional outcome in all models. ML models using the continuous 24-hour NIHSS scored showed moderate-to-good predictive performance (range mean AUC: 0.76-0.92); however, RF (AUC: 0.92 AE 0.028) outperformed all ML models, except LASSO (AUC: 0.89 AE 0.023, p = 0.0958). Importantly, RF demonstrated a significantly higher predictive value than LR (AUC: 0.87 AE 0.031, p = 0.048) and traditional LR (AUC: 85 AE 0.06, p = 0.035) when using the 24-hour continuous NIHSS score. Predictive accuracy was similar between the 24-hour NIHSS score dichotomous and continuous ML models. Interpretation: In this substudy, we found similar predictive accuracy for functional outcome when using the 24-hour NIHSS score as a continuous or dichotomous variable in ML models. ML models had moderate-to-good predictive accuracy, with RF outperforming LR models. External validation of these ML models is warranted.

show abstract

Early neurological stability predicts adverse outcome after acute ischemic stroke

Cited by 27 publications

References 36 publications

Comparative Analysis of Markers of Mass Effect after Ischemic Stroke

Comparative Analysis of Markers of Mass Effect after Ischemic Stroke

Prognostic yield of imaging before and after recanalization treatments in ischemic stroke

Predicting Functional Outcome Using 24‐Hour Post‐Treatment Characteristics: Application of Machine Learning Algorithms in the STRATIS Registry

Contact Info

Product

Resources

About