Objective To construct and validate a nomogram prediction model for poor prognosis in elderly patients with gastrointestinal bleeding.Methods A total of 176 elderly patients with gastrointestinal bleeding were enrolled as the research objects.According to the prognosis during hospitalization,patients were divided into the poor prognosis group(56 cases)and the good prognosis group(120 cases).The clinical data of the two groups of patients were collected.The best variables of poor prognosis were screened by Lasso regression model,and the selected variables were included in the multivariate Logistic regression model to analyze the influencing factors.Nomogram was constructed based on the above influencing factors.Receiver operating characteristic(ROC)curve,clinical calibration curve and decision curve analysis(DCA)were drawn to validate clinical practicability of nomogram prediction model.Results Multivariate Logistic regression analysis showed that urea nitrogen(BUN,OR=2.766,95％CI:1.066-7.175)and high level of shock index(SI,OR=3.853,95％CI:1.028-14.446)were independent risk factors of poor prognosis in elderly patients with gastrointestinal bleeding(P＜0.05),while high levels of albumin(ALB,OR=0.100,95％CI:0.036-0.277)were protective factors(P＜0.05).ROC curve validated that the area under the curve of the prediction model was 0.845(95％CI:0.786-0.904).Calibration curve showed that the model had a relatively high degree of calibration.DCA showed that the model had a clear positive net benefit.Conclusion The nomogram prediction model constructed based on BUN,SI and ALB levels to predict the poor prognosis of elderly patients with gastrointestinal bleeding has a high predictive value.

Objective To construct and validate a nomogram prediction model for poor prognosis in elderly patients with gastrointestinal bleeding.Methods A total of 176 elderly patients with gastrointestinal bleeding were enrolled as the research objects.According to the prognosis during hospitalization,patients were divided into the poor prognosis group(56 cases)and the good prognosis group(120 cases).The clinical data of the two groups of patients were collected.The best variables of poor prognosis were screened by Lasso regression model,and the selected variables were included in the multivariate Logistic regression model to analyze the influencing factors.Nomogram was constructed based on the above influencing factors.Receiver operating characteristic(ROC)curve,clinical calibration curve and decision curve analysis(DCA)were drawn to validate clinical practicability of nomogram prediction model.Results Multivariate Logistic regression analysis showed that urea nitrogen(BUN,OR=2.766,95％CI:1.066-7.175)and high level of shock index(SI,OR=3.853,95％CI:1.028-14.446)were independent risk factors of poor prognosis in elderly patients with gastrointestinal bleeding(P＜0.05),while high levels of albumin(ALB,OR=0.100,95％CI:0.036-0.277)were protective factors(P＜0.05).ROC curve validated that the area under the curve of the prediction model was 0.845(95％CI:0.786-0.904).Calibration curve showed that the model had a relatively high degree of calibration.DCA showed that the model had a clear positive net benefit.Conclusion The nomogram prediction model constructed based on BUN,SI and ALB levels to predict the poor prognosis of elderly patients with gastrointestinal bleeding has a high predictive value.