Development and validation of a risk prediction model for unplanned readmission in patients with hematologic malignancies
CUI Yan
CHEN Mingming
SONG Zhen
MA Yueshen
ZHANG Huijuan
WU Guibin
JIN Zhaona
ZHANG Qianqian
XIE Wenjun
Abstract：Objective:To explore the risk factors for unplanned readmission in patients with hematologic malignancies and develop a risk prediction model.Methods:Clinical data from 3 241 patients with hematologic malignancies treated at a tertiary grade A hospital in Tianjin between January 1,2017,and December 31,2021,were retrospectively collected.The patients were randomly divided into a modeling group(2,269 cases)and a validation group(972 cases)in a 7∶3 ratio.Univariate and Logistic regression analysis were used to construct the risk prediction model.The Hosmer-Lemeshow test and receiver operating characteristic(ROC)curve were employed to evaluate the model's calibration and discrimination,and a Nomogram was developed.Results:The incidence of unplanned readmission in the modeling group was 14.50%(329/2 269).Logistic regression analysis showed that the risk factors included in the risk prediction model were disease types,Eastern Cooperative Oncology Group Performance Status(ECOG)score,pulmonary infection,central venous catheterization,and comorbidities.The Hosmer-Lemeshow test result of the modeling group was χ2=8.569,P=0.380,and the area under the ROC curve(AUC)was 0.796,the Youden index was 0.454,the sensitivity was 78.70%,and specificity was 66.60%.The Hosmer-Lemeshow test result of the validation group was χ2=3.491,P=0.900,the AUC was 0.771,with an accuracy of 76.23%.Conclusion:The developed risk prediction model demonstrates good performance and may assist clinical nurses in identifying high-risk patients for targeted interventions.
Keywords：hematologic malignanciesunplanned readmissionsrisk factorsprediction modelnursing
Publication Date：2025-02-27
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 616-621 )