Impact of Pretreatment Ischemic Location on Functional Outcome after Thrombectomy

Abstract

Pretreatment ischemic location may be an important determinant for functional outcome prediction in acute ischemic stroke. In total, 143 anterior circulation ischemic stroke patients in the THRACE study were included. Ischemic lesions were semi-automatically segmented on pretreatment diffusion-weighted imaging and registered on brain atlases. The percentage of ischemic tissue in each atlas-segmented region was calculated. Statistical models with logistic regression and support vector machine were built to analyze the predictors of functional outcome. The investigated parameters included: age, baseline National Institutes of Health Stroke Scale score, and lesional volume (three-parameter model), together with the ischemic percentage in each atlas-segmented region (four-parameter model). The support vector machine with radial basis functions outperformed logistic regression in prediction accuracy. The support vector machine three-parameter model demonstrated an area under the curve of 0.77, while the four-parameter model achieved a higher area under the curve (0.82). Regions with marked impacts on outcome prediction were the uncinate fasciculus, postcentral gyrus, putamen, middle occipital gyrus, supramarginal gyrus, and posterior corona radiata in the left hemisphere; and the uncinate fasciculus, paracentral lobule, temporal pole, hippocampus, inferior occipital gyrus, middle temporal gyrus, pallidum, and anterior limb of the internal capsule in the right hemisphere. In conclusion, pretreatment ischemic location provided significant prognostic information for functional outcome in ischemic stroke.

Pre-thrombectomy prognostic prediction of large-vessel ischemic stroke using machine learning: A systematic review and meta-analysis

“…Regarding the testing sample, two studies used hold-out test sets, respectively containing 208 patients ( 30 ) and 100 patients ( 35 ). The remaining studies performed cross-validation ( 23 – 26 , 28 , 29 , 31 – 34 , 36 , 37 ) or bootstrap approach ( 22 , 27 ). The five studies ( 23 , 29 , 31 , 34 , 35 ) used data obtained from MR CLEAN Registry ( 38 ).…”

“…Tree models ( 22 , 24 , 31 ), random forests ( 23 , 26 , 27 ), and support vector machines ( 28 , 30 , 33 ) were each proposed by three studies, regularized logistic regression by two studies ( 25 , 32 ), and artificial neural networks by one study ( 29 ). To accommodate missing values, two studies used multiple imputation ( 23 , 29 ) and one used singular imputation ( 31 ), while other studies excluded participants with missing data in either predictive or outcome variables (complete-case analysis) ( 22 , 24 – 28 , 30 , 32 , 33 ). The number of predictive variables used for model construction varied from 4 ( 32 ) to 53 ( 23 ).…”

“…The National Institutes of Health Stroke Scale and age were commonly ranked as the important predictors. All studies conducted internal validation, either by bootstrapping ( 22 , 27 ), hold-out validation ( 30 ), or k-fold cross-validation ( 23 – 26 , 28 , 29 , 31 – 33 ).…”

“…Three ML-based studies ( 23 , 29 , 31 ) and one DL-based study ( 34 ) were considered at low risk of bias in all domains ( Supplementary Table S5 ). The remaining studies were at high risk of bias in at least one domain ( 22 , 24 – 28 , 30 , 32 , 33 , 35 – 37 ). Risk of bias mostly occurred in handling missing data.…”

Outcome Prediction Based on Automatically Extracted Infarct Core Image Features in Patients with Acute Ischemic Stroke

“…Future studies could potentially perform activation visualization to study which information about the brain was most important for the classifier [ 26 ]. In addition, ischemic lesion location could be a feature of interest for predicting functional outcome [ 27 ].…”