目的:采用回归分析法建立慢性阻塞性肺疾病急性加重（AECOPD）风险预测模型，并进行验证。方法:回顾性分析前期4项已完成的多中心大样本随机对照试验中1 326例慢性阻塞性肺疾病（COPD）患者进入稳定期、随访6个月时的危险因素及急性加重情况。应用转换-随机数字生成器从1 326例病例中随机抽取约80%为模型组（n n＝1 074），约20%为验证组（n n＝252）。选取模型组数据，采用Logistic回归分析法筛选AECOPD的独立危险因素，并建立AECOPD风险预测模型；将模型组与验证组数据分别代入模型，绘制受试者工作特征曲线（ROC曲线），对风险预测模型预测AECOPD的效能进行验证。n 结果:模型组与验证组患者在一般资料（性别、吸烟情况、合并症、文化程度等）、体重指数（BMI）分级、肺功能〔1秒用力呼气容积（FEV1）、用力肺活量（FVC）等〕、疾病情况（近1年急性加重次数及持续时间、病程等）、生存质量量表〔COPD评估量表（CAT）等〕和临床症状（咳嗽、胸闷等）方面差异均无统计学意义，说明两组数据有较好的同质性，可以用验证组病例验证通过模型组数据建立的风险预测模型预测AECOPD的效能。Logistic回归分析显示，性别〔优势比（n OR）＝1.679，95%可信区间（95%n CI）为1.221～2.308，n P＝0.001〕、BMI分级（n OR＝0.576，95%n CI为0.331～1.000，n P＝0.050）、FEV1（n OR＝0.551，95%n CI为0.352～0.863，n P＝0.009）、急性加重次数（n OR＝1.344，95%n CI为1.245～1.451，n P＝0.000）和急性加重持续时间（n OR＝1.018，95%n CI为1.002～1.034，n P＝0.024）是AECOPD的独立危险因素；根据回归分析结果构建AECOPD风险预测模型：急性加重概率n P＝1/（1+n e-n x），n x＝-3.274 + 0.518×性别-0.552×BMI分级+ 0.296×急性加重次数+ 0.018×急性加重持续时间-0.596×FEV1。经ROC曲线分析验证，模型组ROC曲线下面积（AUC）为0.740，验证组AUC为0.688；模型的约登指数最大值为0.371，对应预测概率的最佳临界值为0.197，敏感度为80.1%，特异度为57.0%。n 结论:基于回归分析法建立的AECOPD风险预测模型对COPD患者急性加重风险具有中等水平的预测效能，可在一定程度上辅助临床诊疗决策。“,”Objective:To establish a risk prediction model for acute exacerbation of chronic obstructive pulmonary disease (AECOPD) using regression analysis and verify the model.Methods:The risk factors and acute exacerbation of 1 326 patients with chronic obstructive pulmonary disease (COPD) who entered the stable phase and followed up for 6 months in the four completed multi-center large-sample randomized controlled trials were retrospectively analyzed. Using the conversion-random number generator, about 80% of the 1 326 cases were randomly selected as the model group (n n = 1 074), and about 20% were the verification group (n n = 252). The data from the model group were selected, and Logistic regression analysis was used to screen independent risk factors for AECOPD, and an AECOPD risk prediction model was established; the model group and validation group data were substituted into the model, respectively, and the receiver operating characteristic (ROC) curve was drawn to verify the effectiveness of the risk prediction model in predicting AECOPD.n Results:There were no statistically significant differences in general information (gender, smoking status, comorbidities, education level, etc.), body mass index (BMI) classification, lung function [forced expiratory volume in 1 second (FEV1), forced vital capacity (FVC), etc.], disease status (the number and duration of acute exacerbation in the past year, duration of disease, etc.), quality of life scale [COPD assessment test (CAT), etc.] and clinical symptoms (cough, chest tightness, etc.) between the model group and the validation group. It showed that the two sets of data had good homogeneity, and the cases in the validation group could be used to verify the effectiveness of the risk prediction model established through the model group data to predict AECOPD. Logistic regression analysis showed that gender [odds ratio (n OR) = 1.679, 95% confidence interval (95%n CI) was 1.221-2.308, n P = 0.001], BMI classification (n OR = 0.576, 95%n CI was 0.331-1.000, n P = 0.050), FEV1 (n OR = 0.551, 95%n CI was 0.352-0.863, n P = 0.009), number of acute exacerbation (n OR = 1.344, 95%n CI was 1.245-1.451, n P = 0.000) and duration of acute exacerbation (n OR = 1.018, 95%n CI was 1.002-1.034, n P = 0.024) were independent risk factors for AECOPD. A risk prediction model for AECOPD was constructed based on the results of regression analysis: probability of acute exacerbation (n P) = 1/(1+n e-n x), n x = -3.274 + 0.518×gender-0.552×BMI classification + 0.296×number of acute exacerbation + 0.018×duration of acute exacerbation-0.596×FEV1. The ROC curve analysis verified that the area under ROC curve (AUC) of the model group was 0.740, the AUC of the verification group was 0.688; the maximum n Youden index of the model was 0.371, the corresponding best cut-off value of prediction probability was 0.197, the sensitivity was 80.1%, and the specificity was 57.0%.n Conclusion:The AECOPD risk prediction model based on the regression analysis method had a moderate predictive power for the acute exacerbation risk of COPD patients, and could assist clinical diagnosis and treatment decision in a certain degree.