恶性血液病病人非计划性再入院风险预测模型的构建与验证  

Development and validation of a risk prediction model for unplanned readmission in patients with hematologic malignancies

作　　者：崔岩 陈明明 宋振 马跃申 张会娟 吴桂彬 靳兆娜 张倩倩 解文君 CUI Yan;CHEN Mingming;SONG Zhen;MA Yueshen;ZHANG Huijuan;WU Guibin;JIN Zhaona;ZHANG Qianqian;XIE Wenjun(State Key Laboratory of Experimental Hematology,National Clinical Research Center for Blood Diseases,Haihe Laboratory of Cell Ecosystem,Institute of Hematology and Blood Diseases Hospital,Chinese Academy of Medical Sciences and Peking Union Medical College,Tianjin 300020 China)

机构地区：[1]中国医学科学院血液病医院(中国医学科学院血液学研究所),300020

出　　处：《全科护理》2025年第4期616-621,共6页Chinese General Practice Nursing

基　　金：天津市护理学会科研项目,编号:tjhlky2022YB02。

摘　　要：目的:探讨恶性血液病病人非计划性再入院的危险因素,并构建其风险预测模型。方法:回顾性收集2017年1月1日—2021年12月31日在天津市某三级甲等医院接受治疗的3241例恶性血液病病人的临床资料。按7∶3的比例随机分为建模组(2269例)和验证组(972例)。应用单因素和多因素Logistic回归分析构建风险预测模型,采用Homser-Lemeshow检验及受试者工作特征(receiver operating characteristic,ROC)曲线检验模型的拟合度和区分度,并绘制列线图。结果:建模组恶性血液病病人非计划性再入院发生率为14.50%(329/2269)。Logistic回归分析结果显示,纳入风险预测模型的危险因素有疾病类型、美国东部肿瘤协作组体能状态评分(ECOG)、肺部感染、中心静脉置管以及合并基础疾病。建模组Hosmer-Lemeshow检验结果为χ^(2)=8.569,P=0.380;ROC曲线下面积(AUC)为0.796,约登指数为0.454,灵敏度和特异度分别为78.70%和66.60%;验证组Hosmer-Lemeshow检验结果为χ^(2)=3.491,P=0.900;AUC为0.771,准确率为76.23%。结论:构建的风险预测模型效果良好,可为临床护理人员识别中高风险病人提供参考。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 χ^(2) =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 χ^(2) =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.

关 键 词：恶性血液病 非计划性再入院 危险因素 预测模型 护理 

分 类 号：R473.73[医药卫生—护理学]