AUTHOR=Li Jingwei , Zhu Wencheng , Zhou Junshan , Yun Wenwei , Li Xiaobo , Guan Qiaochu , Lv Weiping , Cheng Yue , Ni Huanyu , Xie Ziyi , Li Mengyun , Zhang Lu , Xu Yun , Zhang Qingxiu 

TITLE=A Presurgical Unfavorable Prediction Scale of Endovascular Treatment for Acute Ischemic Stroke

JOURNAL=Frontiers in Aging Neuroscience

VOLUME=Volume 14 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2022.942285

DOI=10.3389/fnagi.2022.942285

ISSN=1663-4365

ABSTRACT=Objective-In order to develop a prognostic prediction model of EVT for AIS induced by LVO, the current study applied machine learning classification model light gradient boosting machine (LightGBM) to construct a unique prediction model.
Methods-A total of 973 patients were enrolled and primary outcome was assessed with modified Rankin Scale (mRS) at 90 days and favorable outcome was defined using mRS 0-2 scores. Besides, LightGBM algorithm and Logistic regression (LR) were used to construct a prediction model. Then a prediction scale was further established and verified by both internal data and other external data. 
Results-Twenty pre-surgical variables were analyzed using LR and LightGBM. The results of LightGBM algorithm indicated that the accuracy and precision of the prediction model was 73.77% and 73.16%, respectively. The area under the curves (AUC) was 0.824. Furthermore, the top 5 variables suggesting unfavorable outcomes were namely fasting blood glucose levels, age, onset to EVT time, onset to hospital time, and NIHSS scores (importance=130.9, 102.6, 96.5, 89.5 and 84.4, respectively). According to AUC curve, we established the key cut-off points and constructed prediction scale based on their respective weightings. Then, the established prediction scale was verified in raw and external data and the sensitivity was 80.4% and 83.5%, respectively. Finally, the scores over 3 demonstrated better accuracy in predicting unfavorable outcomes. 
Conclusions-In conclusion, pre-surgical prediction scale is feasible and accurate in identifying unfavorable outcomes of AIS after EVT.