慢性阻塞性肺疾病患者一年再入院的临床预测模型构建

Construction of a clinical predictive model for patients with chronic obstructive pulmonary disease re-hospitalized in one year

目的分析影响慢性阻塞性肺疾病患者一年再入院的危险因素,并构建临床预测模型。方法2016年1月至2019年1月期间我院因慢阻肺入院的患者440例,分为训练集(308例)和验证集(132例)。将其中训练集人群,根据患者是否再入院分为再入院组(186例)和非再入院组(122例),记录患者一般信息、检验检查结果、合并症等因素,对相关因子进行Cox回归分析后,建立临床预测模型并绘制Nomogram。采用受试者工作特征(ROC)曲线、校准曲线和拟合优度检验验证模型的区分度和校准度;决策曲线(DCA)评估模型的临床适用性。结果嗜酸性粒细胞百分比、FEV_(1)、吸入药物治疗、既往住院史和神经肌肉疾病是慢阻肺患者再入院的危险因素,绘制Nomogram并构建临床预测模型,结果显示模型的区分度、校准度和临床使用性均较佳。结论慢性阻塞性肺疾病患者一年再入院受多种因素影响,以此建立的临床预测模型,对患者再入院预测具有良好的判别能力,值得临床应用与进一步研究。

Objective To analyze the risk factors that affect patients with chronic obstructive pulmonary disease re-hospitalized in one year and construct a clinical prediction model.Methods From January 2016 to January 2019,440 patients admitted to our hospital for COPD were divided into the training group(308 cases)and the validation group(132 cases).The training group was divided into the re-admission group(186 cases)and the non re-admission group(122 cases)according to whether the patient was re-admitted.The general information of the patients,test results,comorbidities and other factors were recorded,and the relevant factors were analyzed by Cox regression.Then the clinical prediction model was established to draw the Nomogram.The receiver operating characteristic(ROC)curve,calibration curve,and goodness of fit test were used to verify the discrimination and calibration of the model.The decision curve(DCA)was used to evaluate the clinical applicability of the model.Results The percentage of eosinophils,FEV_(1),inhaled drug therapy,previous hospitalization history and neuromuscular disease were risk factors for readmission COPD patients.Nomogram was drawn and a clinical prediction model was constructed.The results showed the discrimination,calibration and clinical applicability of the model was better.Conclusion The one-year re-admission of patients with chronic obstructive pulmonary disease is affected by a variety of factors.The clinical prediction model established by this has a good discriminant ability in predicting patient re-admission,and it is worthy of clinical application and further research.