基于AAT与细胞因子构建活动性肺结核的Nomogram预测模型

  目的   构建AAT及细胞因子在活动性肺结核诊断中的预测模型。  方法   收集昆明市第三人民医院2020年3月至2021年3月收治的96例活动性肺结核患者作为实验组，选择同期82例健康体检者为对照组，比较2组HAP、CRP、AAT及细胞因子水平的差异，基于 Logistic回归分析分析结果，构建Nomogram预测模型，并对模型进行验证与评价。   结果   多因素Logistic回归分析显示，AAT（OR = 0.983，95%CI = 0.968～0.999，P = 0.039），IFN-γ（OR = 0.783，95%CI = 0.659～0.931，P = 0.006），TNF-α（OR = 1.495，95%CI = 1.106～2.020，P = 0.009）均是活动性肺结核的预测因子（P < 0.05）。   结论   该模型拟合度、ROC曲线下面积均良好，证实该模型有较高的预测准确率。基于上述预测因子建立的Nomogram模型具有良好的预测效能，可为活动性肺结核的实验室诊断提供一定的参考价值。

Constructing A Nomogram Prediction Model for Active Pulmonary Tuberculosis Based on AAT and Cytokines

  Objective   To construct a predictive model of AAT and cytokines in the diagnosis of active pulmonary tuberculosis.   Methods   A total of 96 patients with active pulmonary tuberculosis admitted to the Third People’s Hospital of Kunming from March 2020 to March 2021 were collected as the experimental group, and 82 healthy subjects during the same period were selected as the control group. HAP, CRP, AAT and cytokines were compared between the two groups. Based on the results of Logistic regression analysis, a Nomogram prediction model was constructed, and the model was verified and evaluated.   Results   Multivariate logistic regression analysis showed that AAT （OR = 0.983, 95% CI = 0.968-0.999, P = 0.039）, IFN-γ （OR = 0.783, 95% CI = 0.659-0.931, P = 0.006）, TNF-α （OR = 1.495, 95% CI = 1.106-2.020, P = 0.009） are predictors of active pulmonary tuberculosis （P < 0.05）.  Conclusion   The fit of the model and the area under the ROC curve were good, which confirmed that the model had a high prediction accuracy. The Nomogram model established based on the above predictors has good predictive performance and can provide a certain reference value for the laboratory diagnosis of active pulmonary tuberculosis.