“…To sum up, considering the problems of statistical efficacy, p -value, and multicollinearity, we finally selected 11 variables from the results of Univariate analysis, including age, ethnicity, heart rate, RR, SpO 2 , blood glucose, WBC, Charlson comorbidity index, Cr, endovascular therapy, and GCS. Although univariate analysis showed no significant association between sex and in-hospital mortality (HR: 0.86, 95%CI: 0.61,1.23, p = 0.411), as an important demographic feature, has been included in the Multivariate analysis Model in other published relevant literature (although there is no correlation in univariate analysis) 23 – 25 , so we also take sex as one of the covariables. Therefore, a total of 12 covariates are adjusted in Model II.…”