Abstract: Objective To identify the influencing factors of enteral nutrition intolerance in the patients with severe stroke, and to build a dynamic prediction model and to verify the prediction effect. Methods A total of 282 patients with severe stroke admitted to our hospital from January 2018 to June 2020 were enrolled in this study. Single factor analysis and multivariate Logistic regression analysis were used to screen the risk factors of enteral nutrition intolerance, and a nomogram prediction model was established based on the risk factors. Internal and external evaluations of the model's predictive effect were conducted. Results Feeding intolerance occurred in 107 of the 282 patients with severe stroke, with an incidence rate of 37.94%. Based on the results of Logistic regression analysis, four factors including aged ≥60 years old(OR=1.965), use of 2 or more antibacterial drugs (OR=2.749), use of probiotics (OR=0.321), and implementation of mechanical ventilation (OR=3.035) were included in the R software to establish a predictive nomogram model of enteral nutrition intolerance in stroke patients. Internal and external verification showed that the areas under the receiver operating characteristic curve of the model group and the verification group were 0.794 and 0.764 respectively, and the calibration curves were all close to the ideal curve. The model group's maximum Youden index was 0.449, and the corresponding risk predictive value was 0.322, and the predictive threshold value was 200. When the decision curve analysis (DCA) threshold probability ranged 0.10-0.85, the model showed a positive net benefit. Conclusions The nomogram model established based on the risk factors of enteral nutrition intolerance in the patients with severe stroke shows good discrimination, consistency and clinical applicability. High-risk patients with a total score of ≥200 should be given great attention, and preventive care intervention should be implemented as soon as possible to reduce the occurrence of enteral nutrition intolerance.

Key words: stroke, enteral nutrition intolerance, influencing factor, predictive model