Zhang Chuang, Guan Qiongchan, Qin Jie, Huang Daochao, Wu Jinhong
Department of Emergency, Taizhou Hospital of Zhejiang Province Affiliated to Wenzhou Medical University, Linhai 317000, Zhejiang, China.
Department of Obstetrics and Gynecology, Taizhou Hospital of Zhejiang Province Affiliated to Wenzhou Medical University, Linhai 317000, Zhejiang, China.
Emerg Med Int. 2022 Aug 22;2022:2596839. doi: 10.1155/2022/2596839. eCollection 2022.
The purpose of this study was to explore the establishment of an auxiliary scoring model for patients with acute pulmonary embolism (APE) complicated with atrial fibrillation (AF) based on random forest (RF) and its application effect. A retrospective analysis was performed on the general data, underlying diseases, laboratory indicators, and cardiac indicators of 100 patients with APE admitted to our hospital from 2018 to 2021. The occurrence of atrial fibrillation in patients with pulmonary embolism was taken as a categorical variable, and the general data, underlying diseases, laboratory indicators, and cardiac indicators were taken as input variables. Then, the risk auxiliary scoring model for patients with APE complicated with AF was established based on RF and logistic regression. Finally, the accuracy, sensitivity, specificity, recall rate, accuracy, F1 value, and the receiver operator characteristic (ROC) curve were used to evaluate the predictive value of the models. After statistical analysis, the optimal node value was 3 and the optimal number of decision trees was 500 in the RF model. The importance of predictors in descending order were Hcy, diabetes mellitus, FT3 level, UA level, left atrial diameter, hypertension, and smoking history. The prediction accuracy of the RF model was 0.934, sensitivity 0.966, specificity 0.876, recall rate 0.9660, accuracy 0.934, and F1 value 0.950. The logistic regression model prediction accuracy was 0.816, sensitivity 0.915, specificity 0.125, recall rate 0.902, accuracy 0.811, and F1 value 0.896. The RF model and logistic regression prediction model AUC values were 0.984 and 0.883, respectively. From this, we conclude that the RF model was better than the logistic regression model in predicting AF in APE patients. So, the RF model had the clinical application value.
本研究旨在探索基于随机森林（RF）建立急性肺栓塞（APE）合并心房颤动（AF）患者的辅助评分模型及其应用效果。对2018年至2021年我院收治的100例APE患者的一般资料、基础疾病、实验室指标及心脏指标进行回顾性分析。将肺栓塞患者心房颤动的发生作为分类变量，将一般资料、基础疾病、实验室指标及心脏指标作为输入变量。然后，基于RF和逻辑回归建立APE合并AF患者的风险辅助评分模型。最后，采用准确率、灵敏度、特异度、召回率、精确率、F1值及受试者工作特征（ROC）曲线评估模型的预测价值。经统计分析，RF模型中最优节点值为3，最优决策树数量为500。预测因子重要性从高到低依次为同型半胱氨酸、糖尿病、FT3水平、尿酸水平、左心房内径、高血压及吸烟史。RF模型预测准确率为0.934，灵敏度为0.966，特异度为0.876，召回率为0.9660，精确率为0.934，F1值为0.950。逻辑回归模型预测准确率为0.816，灵敏度为0.915，特异度为0.125，召回率为0.902，精确率为0.811，F1值为0.896。RF模型和逻辑回归预测模型的AUC值分别为0.984和0.883。由此得出结论，RF模型在预测APE患者AF方面优于逻辑回归模型。所以，RF模型具有临床应用价值。
