Outcome prediction for patients with anterior circulation acute ischemic stroke following endovascular treatment: A single‑center study

Wu, Xiao; Liu, Guoqing; Zhou, Wu; Ou, Aihua; Lu, Xian; Wang, Yuhan; Zhou, Sifan; Luo, Wenting; Liu, Bo

doi:10.3892/etm.2019.8054

Cited by 9 publications

(16 citation statements)

References 39 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although several predictors have been identified, such as age, NIHSS score, and preoperative glucose level, 13 14 postoperative laboratory indices, comprising serum glucose level and indictors of liver function (AGR, albumin), renal function (eGFR), and inflammation (blood neutrophil count, CRP), were strong predictors that have been neglected by existing prediction models. [3][4][5][6][7][8][9][10][11][12][13][14][15] In our study, we found that the predictive ability of postoperative laboratory indices outperformed that of preoperative indices and accounted for over half of the selected features in our model, highlighting the significant effects of postoperative conditions on outcomes following MT and suggesting that it should be evaluated in future studies. These factors are all from frequently recorded blood biochemistry tests or routine blood tests and, more importantly, are potentially modifiable.…”

Section: Discussionmentioning

confidence: 91%

An explainable machine learning model for predicting the outcome of ischemic stroke after mechanical thrombectomy

Yao

Mao

et al. 2022

J NeuroIntervent Surg

View full text Add to dashboard Cite

BackgroundThere is high variability in the clinical outcomes of patients with acute ischemic stroke (AIS) after mechanical thrombectomy (MT).Methods217 consecutive patients with anterior circulation large vessel occlusion who underwent MT between August 2018 and January 2022 were analysed. The primary outcome was functional independence defined as a modified Rankin Scale score of 0–2 at 3 months. In the derivation cohort (August 2018 to December 2020), 7 ensemble ML models were trained on 70% of patients and tested on the remaining 30%. The model’s performance was further validated on the temporal validation cohort (January 2021 to January 2022). The SHapley Additive exPlanations (SHAP) framework was applied to interpret the prediction model.ResultsDerivation analyses generated a 9-item score (PFCML-MT) comprising age, National Institutes of Health Stroke Scale score, collateral status, and postoperative laboratory indices (albumin-to-globulin ratio, estimated glomerular filtration rate, blood neutrophil count, C-reactive protein, albumin and serum glucose levels). The area under the curve was 0.87 for the test set and 0.84 for the temporal validation cohort. SHAP analysis further determined the thresholds for the top continuous features. This model has been translated into an online calculator that is freely available to the public (https://zhelvyao-123-60-sial5s.streamlitapp.com).ConclusionsUsing ML and readily available features, we developed an ML model that can potentially be used in clinical practice to generate real-time, accurate predictions of the outcome of patients with AIS treated with MT.

show abstract

Section: Discussionmentioning

confidence: 91%

An explainable machine learning model for predicting the outcome of ischemic stroke after mechanical thrombectomy

Yao

Mao

et al. 2022

J NeuroIntervent Surg

View full text Add to dashboard Cite

show abstract

“…Clinical and MR factors also play an important role in outcome prediction of AIS. Previous studies have reported that the clinical variables, such as gender, age, and admission NIHSS, could be used as factors for predicting the outcome of AIS patients ( Kim and Vemuganti, 2015 ; Wu et al, 2019 ). To validate these results, we used the 90-day mRS > 2 as an unfavorable outcome criteria.…”

Section: Discussionmentioning

confidence: 99%

FLAIR and ADC Image-Based Radiomics Features as Predictive Biomarkers of Unfavorable Outcome in Patients With Acute Ischemic Stroke

Guanmin

Ban

Ren³

et al. 2021

Front. Neurosci.

View full text Add to dashboard Cite

At present, it is still challenging to predict the clinical outcome of acute ischemic stroke (AIS). In this retrospective study, we explored whether radiomics features extracted from fluid-attenuated inversion recovery (FLAIR) and apparent diffusion coefficient (ADC) images can predict clinical outcome of patients with AIS. Patients with AIS were divided into a training (n = 110) and an external validation (n = 80) sets. A total of 753 radiomics features were extracted from each FLAIR and ADC image of the 190 patients. Interquartile range (IQR), Wilcoxon rank sum test, and least absolute shrinkage and selection operator (LASSO) were used to reduce the feature dimension. The six strongest radiomics features were related to an unfavorable outcome of AIS. A logistic regression analysis was employed for selection of potential predominating clinical and conventional magnetic resonance imaging (MRI) factors. Subsequently, we developed several models based on clinical and conventional MRI factors and radiomics features to predict the outcome of AIS patients. For predicting unfavorable outcome [modified Rankin scale (mRS) > 2] in the training set, the area under the receiver operating characteristic curve (AUC) of ADC radiomics model was 0.772, FLAIR radiomics model 0.731, ADC and FLAIR radiomics model 0.815, clinical model 0.791, and clinical and conventional MRI model 0.782. In the external validation set, the AUCs for the prediction with ADC radiomics model was 0.792, FLAIR radiomics model 0.707, ADC and FLAIR radiomics model 0.825, clinical model 0.763, and clinical and conventional MRI model 0.751. When adding radiomics features to the combined model, the AUCs for predicting unfavorable outcome in the training and external validation sets were 0.926 and 0.864, respectively. Our results indicate that the radiomics features extracted from FLAIR and ADC can be instrumental biomarkers to predict unfavorable clinical outcome of AIS and would additionally improve predictive performance when adding to combined model.

show abstract

“…Patients who received first-line SR or the ADAPT therapy only were a prognosticator detected in our cohort. Many other predictive factors of good functional outcome have been proposed in previous studies, including age, successful revascularization, parenchymal hemorrhage, baseline NIHSS score, anterior choroidal artery infarction, stroke subtype (intracranial atherosclerotic disease or embolism), posterior circulation Acute Stroke Prognosis Early CT Score, diffusion-weighted imaging lesion volume, glucose on admission, and hypersensitive C-reactive protein ( 31 – 35 ). The difference in reported factors may result from the heterogeneity of the study designs and patient demographics.…”

Section: Discussionmentioning

confidence: 99%

Added Value of Rescue Devices in Intra-Arterial Thrombectomy: When Should We Apply Them?

Cheng

Chen

et al. 2021

Front. Neurol.

View full text Add to dashboard Cite

Introduction: Recent trials have demonstrated the superior efficacy of mechanical thrombectomy over other medical treatments for acute ischemic stroke; however, not every large vessel occlusion (LVO) can be recanalized using a single thrombectomy device. Rescue devices were proved to increase the reperfusion rate, but the efficacy is unclear.Objective: In this retrospective study, we evaluated the efficacy of rescue therapy in different locations of LVO.Methods: We analyzed the outcomes of mechanical thrombectomy from a prospective registry of consecutive 82 patients in Taipei Medical University Hospital. The reperfusion rate and the functional outcome were compared in patients who received first-line therapy only and patients who need rescue therapy.Results: An 84.1% reperfusion rate was achieved in our cohort. We applied first-line stent retriever (SR) treatment in 6 patients, among which 4 (66.6%) achieved successful reperfusion. We applied a direct-aspiration first-pass technique (ADAPT) as the first-line treatment in 76 patients, among which 46 (60.5%) achieved successful reperfusion. Successful reperfusion could not be achieved in 30 cases (39.5%); therefore, we applied a second-line rescue SR for 28 patients, and reperfusion was established in 18 (64.3%) of them. These results revealed that the LVO in anterior circulation has a higher chance to respond to SR rescue therapy than posterior circulation lesions (68 vs. 33.3%, P < 0.001). Patients who received only first-line therapy exhibited significantly better functional outcomes than those who were also treated with rescue SR therapy (41.2 vs. 16.7%, P = 0.001). In addition, patients with LVO in the anterior circulation were found to have a higher probability of achieving functional independence than patients with posterior circulation lesions (10.7 vs. 0.0%, P < 0.001). The adjusted multivariate analysis revealed that successful reperfusion and treatment type (first-line or rescue therapy) were significantly related to a modified Rankin Scale (mRS) score at 90 days.Conclusion: This study reveals that rescue SR therapy improves the reperfusion rate. Patients who require rescue SR therapy have a lower likelihood of functional independence. LVO in the anterior circulation responds better to rescue SR therapy and results in better functional outcomes than posterior circulation lesions.

show abstract

Outcome prediction for patients with anterior circulation acute ischemic stroke following endovascular treatment: A single‑center study

Cited by 9 publications

References 39 publications

An explainable machine learning model for predicting the outcome of ischemic stroke after mechanical thrombectomy

An explainable machine learning model for predicting the outcome of ischemic stroke after mechanical thrombectomy

FLAIR and ADC Image-Based Radiomics Features as Predictive Biomarkers of Unfavorable Outcome in Patients With Acute Ischemic Stroke

Added Value of Rescue Devices in Intra-Arterial Thrombectomy: When Should We Apply Them?

Contact Info

Product

Resources

About