Objective: To conduct a statistical analysis on the condition of patients with pneumoconiosis complicated with chronic pulmonary heart disease based on the Tei index, and to establish a relevant prediction model. Methods: In March 2022, a retrospective analysis of 226 patients diagnosed with pneumoconiosis in the Department of Occupational Disease of Yantai Yantaishan Hospital from January 2016 to January 2022 was conducted. The patients with pneumoconiosis complicated by pulmonary heart disease were included in the pulmonary heart disease group and others were included in the non-pulmonary heart disease group. logistic regression analysis was used to screen out the relevant factors and establish a risk prediction model. Hosmer-Lemeshow test was applied to determine the goodness of fit of the model, and the receiver operating characteristic (ROC) area under the curve (AUC) was used to evaluate the predictive effect of the model. Results: Among the 226 patients with pneumoconiosis, 58 patients had chronic pulmonary heart disease, accounting for 25.7% of the surveyed population. The logistic analysis showed that the course of disease, pneumoconiosis stage and Tei index were influencing factors of pneumoconiosis complicated with pulmonary heart disease (P<0.05). A risk prediction model for pneumoconiosis patients complicated with pulmonary heart disease was developed: Z=6.253X(1)+1.265X(2)+1.423X(3)+9.264, in which X(1) was the stage of pneumoconiosis, X(2) was the course of disease, and X(3) was the Tei index. Hosmer-Lemeshow test was used to evaluate the goodness of fit of the risk prediction model for pneumoconiosis patients complicated with pulmonary heart disease, the results indicated that the prediction model was in good agreement with the actual situation (χ(2)=11.59, P=0.254). The diagnostic ability of the model was evaluated by the ROC curve, and the results showed that its AUC was 0.897, the sensitivity was 0.947, and the specificity was 0.784. Conclusion: The course of disease, pneumoconiosis stage and Tei index are the influencing factors of pneumoconiosis complicated with pulmonary heart disease. The model constructed based on these factors has a good prediction effect, which can provide a basis for the early detection and intervention of pneumoconiosis complicated with pulmonary heart disease.
目的： 基于Tei指数对尘肺病患者并发慢性肺源性心脏病（肺心病）情况进行统计分析，建立相关预测模型。 方法： 于2022年3月，回顾性分析2016年1月至2022年1月烟台市烟台山医院职业病科诊断的尘肺病患者226例。根据是否并发肺心病分为肺心病组和非肺心病组，利用logistic回归分析筛选出相关因素，建立风险预测模型。利用Hosmer-Lemeshow方程对模型拟合优度进行检测，使用受试者工作特征（ROC）曲线下面积（AUC）评估所建模型的预测效果。 结果： 调查对象中并发肺心病患者占25.7%（58/226）。logistic分析显示，病程、尘肺分期以及Tei指数是尘肺病患者并发肺心病的影响因素（P<0.05），构建尘肺病患者并发肺心病风险预测模型：Z=6.253X(1)+1.265X(2)+1.423X(3)+9.264（X(1)为尘肺分期，X(2)为病程，X(3)为Tei指数）。Hosmer-Lemeshow检验评估尘肺病并发肺心病风险预测模型的拟合优度，结果显示预测模型与实际情况有较好的一致性（χ(2)=11.59，P=0.254）。ROC曲线对模型的诊断能力评估显示，AUC为0.897，灵敏度为0.947，特异度为0.784。 结论： 病程、尘肺分期以及Tei指数是尘肺病患者并发肺心病的独立影响因素，据此构建的预测模型具有良好的预测效果，可为尘肺病并发肺心病的早期发现和干预提供依据。.
Keywords: Influencing factors; Models; Pneumoconiosis; Prediction; Pulmonary heart disease.