Objective To construct a prediction model of deep vein thrombosis in ICU patients based on the Caprini risk assessment scale.Methods From January 2020 to December 2022,362 critically ill patients were retrospectively collected.According to whether deep vein thrombosis occurred or not,the patients were divided into the deep vein thrombosis group and the control group.The clinical characteristics and the Caprini risk assessment scale score between the two groups were compared,the risk factors of deep vein thrombosis were analyzed,and a prediction model according to the relevant risk factors was built.Results There were significant differences in diabetes,Caprini risk assessment scale score and surgical operation rate between the two groups(P<0.05).Multivariate Logistic regression analysis showed that diabetes,surgery and Caprini score≥5 were independent risk factors for deep vein thrombosis in critically ill patients(P<0.05).Substituting the training and validation set data into the constructed predictive model.The area under the ROC curve of the training set was 0.768,and the area under the ROC curve of the validation set was 0.870.In the validation set,the model was subjected to the Hosmer Limeshow Goodness of Fit Test,with a chi square value of 4.856 and a P-value of 0.773,indicating that the model had good reliability.Conclusion The prediction model based on the Caprini risk assessment scale has good predictive value and reliability for deep vein thrombosis in ICU patients.
Caprini risk assessment scaleCritically illDeep vein thrombosisPrediction model
万方数据
维普
