目的:探讨急性心肌梗死（AMI）患者发生非计划性再入院的危险因素，并构建风险预测模型。方法:采用便利抽样法，选取2020年3月至2021年3月于天津市人民医院心内科住院治疗的270例AMI患者为研究对象，通过医院电子病历系统收集患者资料，按1年内是否发生非计划性再入院分为非计划性再入院组81例及非再入院组189例。应用Logistic回归分析筛选AMI患者非计划性再入院的独立危险因素，并构建其风险预测模型。结果:Logistic回归模型显示，AMI患者非计划性再入院的独立危险因素包括吸烟史（n X1）、合并高血压（n X2）、婚姻状况（n X3）、住院天数（n X4）、既往PCI史（n X5）和合并心力衰竭（n X6）共计6个变量，ROC曲线下面积为0.840，约登指数最大值为0.560，对应的灵敏度为85.2%，特异度为70.8%，截断值为0.377。AMI患者非计划性再入院风险预测模型表达式为Logit(p/1-p)=-4.012+1.172 n X1+1.104 n X2+0.992 n X3+0.118 n X4+1.191 n X5+1.093 n X6。n 结论:本研究构建的AMI患者非计划性再入院的风险预测模型拟合效能良好，推荐将其模型应用于临床干预，借助模型早期识别AMI后非计划性再入院的高危人群，同时结合再入院发生的风险因素，制订针对性的干预措施。“,”Objective:To explore the risk factors of unplanned readmission in patients with acute myocardial infarction, and to construct a risk prediction model.Methods:This study used cross-sectional survey method. A total of 270 acute myocardial infarction patients admitted from Tianjin Union Medical Cencer from March 2020 to March 2021 were evaluated in a cardiology department. We used the electronic medical record system to collect the patients′ data. Patients were divided into two groups according to the occurrence of readmission within 1 year or not. Logistic regression analysis was performed to identify risk factors and formulated prediction model.Results:Totally 81 patients (30%) were readmitted. Binary Logistic regression model showed that the independent influencing factors of unplanned readmission in acute myocardial infarction patients included smoking (n X1), hypertension (n X2), marital status (n X3), hospitalization days (n X4), percutaneous coronary intervention (n X5), and heart failure (n X6). Area under ROC curve was 0.840, the maximum value of the Youden index was 0.560, and the sensitivity was 85.2%, the specificity was 70.8%, and the cutoff value was 0.377. Prediction model expression of unplanned readmission risk in patients with acute myocardial infarction was Logit(p/1-p)=-4.012+1.172 n X1+1.104 n X2+0.992 n X3+0.118 n X4+1.191 n X5+1.093 n X6.n Conclusions:The risk prediction model of unplanned readmission in patients with acute myocardial infarction established in this article was with a good predictive effect, and it could be used in early identification of those patients with high-risk in unplanned readmission. At the same time, combined with the risk factors of depression, targeted intervention measures can be formulated.