目的 探讨急性冠状动脉综合征（ACS）患者经皮冠状动脉介入治疗（PCI）术后发生一过性心律失常的影响因素，建立风险预测模型并检验预测效果。 方法 选取2022年8月至2024年2月于中国人民解放军西部战区空军医院行PCI术的480例ACS患者为研究对象，按7∶3分为建构组336例与验证组144例，建构组数据用于构建模型，验证组对该模型进行验证。根据术后是否发生一过性心律失常将建构组患者分为发生组84例与未发生组252例，验证组分为发生组36例与未发生组108例。观察两组研究对象的基线资料，采用ROC实验分析连续性变量的预测价值；采用多因素logistic回归分析ACS患者PCI术后发生一过性心律失常的影响因素；采用R语言构建Nomogram预测模型；采用校准曲线和决策曲线对模型进行评价与验证。 结果 建构组单因素分析结果表明，年龄越大、存在糖尿病病史、发病到入院时间≥6 h、BNP水平越高是ACS患者PCI术后发生一过性心律失常的主要危险因素（P < 0.05），据此建立的预测模型AUC为0.865，95%CI：0.804 ~ 0.927，在预测ACS患者PCI术后发生一过性心律失常方面表现良好，其C-index为0.858（0.753 ~ 0.865），当其风险阈值介于0.10 ~ 0.96时，该模型可以较好地提供标准化净收益。验证组ROC曲线和校准曲线结果良好，AUC为0.846，C-index为0.840（0.737 ~ 0.851），提示模型具有较好的外部预测效能。验证组决策曲线分析结果表明，当风险阈值介于0.06 ~ 0.94时，该模型可以较好的提供标准化净收益。 结论 单因素分析结果表明，年龄越大、存在糖尿病病史、发病到入院时间≥ 6 h、BNP水平越高是ACS患者PCI术后发生一过性心律失常的主要危险因素，基于这4个影响因素构建的列线图模型可有效预测ACS患者PCI术后发生一过性心律失常风险。

Objective To explore the factors affecting the occurrence of transient arrhythmia after percutaneous coronary intervention （PCI） in patients with acute coronary syndromes （ACS）， to establish a risk prediction model， and to test the prediction effect. Methods 480 ACS patients who underwent PCI in Western Theater Air Force Hospital of PLA from August 2022 to February 2024 were selected as study subjects and were divided into 336 cases in the construct group and 144 cases in the validation group according to the ratio of 7：3. The data of the construct group were used to construct the model， and the validation group was used to validate the model. The patients in the constructed group were divided into 84 cases in the occurrence group and 252 cases in the non-occurrence group according to whether they had experienced postoperative transient arrhythmia， and the validation group was divided into 36 cases in the occurrence group and 108 cases in the non-occurrence group. The baseline data of the study subjects in the two groups were observed， and the predictive value of continuous variables was analyzed using the ROC experiment； the influencing factors of the occurrence of transient arrhythmia after PCI in ACS patients were analyzed using multifactorial logistic regression； the Nomogram prediction model was constructed using the R language； and the model was evaluated and validated using calibration curves and decision curves. Results The results of a one-way analysis of the constructed group showed that older age， the presence of a history of diabetes mellitus， the time from onset to admission ≥ 6 h， and higher BNP levels were the main risk factors for the occurrence of transient arrhythmia after PCI in patients with ACS （P < 0.05）， and the prediction model established accordingly had an AUC of 0.865 and a 95% CI of 0.804 ~ 0.927， which was effective in predicting the occurrence of transient arrhythmia after PCI in patients with ACS. The model performed well in predicting the occurrence of transient arrhythmia after PCI， with a C-index of 0.858 （0.753 ~ 0.865）， and provided a good standardized net benefit when its risk threshold was between 0.10 to 0.96. The validation group ROC curve and calibration curve results are good， with an AUC of 0.846 and a C-index of 0.840 （0.737 ~ 0.851）， suggesting that the model has a good external predictive efficacy. The results of the validation group decision curve analysis indicated that the model could provide better standardized net returns when the risk threshold was between 0.06 and 0.94. Conclusion The results of univariate analysis showed that older age， the presence of a history of diabetes mellitus， onset-to-admission time ≥6 h， and higher BNP levels were the main risk factors for the occurrence of transient arrhythmia after PCI in patients with ACS， and the Nomogram model constructed on the basis of these four influencing factors could effectively predict the risk of transient arrhythmia after PCI in patients with ACS.