检验医学与临床2024，Vol.21Issue(16)：2345-2350,6.DOI:10.3969/j.issn.1672-9455.2024.16.009
基于检验指标的肺尘埃沉着病患者合并肺炎的影响因素分析及预测模型构建
Analysis of risk factors and construction of prediction model for pneumonia in patients with pneumoconiosis
摘要
Abstract
Objective To explore the risk factors of pneumonia based on laboratory test indexes for pa-tients with pneumoconiosis and construct prediction model to evaluate its feasibility.Methods A total of 243 patients with pneumoconiosis enrolled in the Second Affiliated Hospital of Xuzhou Medical University from September 2021 to August 2023 were selected as the modeling group,which was subdivided into the non-pneu-monia group(n=130)and the pneumonia group(n=113)according to whether they were combined with pneumonia or not,and the inflammatory indexes[C-reactive protein(CRP),interleukin(IL)-2,IL-4,IL-6,IL-8 and IL-10],tumor indexes[carcinoembryonic antigen(CEA),malignant tumor growth factor(TSGF),β2 mi-croglobulin(β2-MG)and squamous carcinoma-associated antigen(SCC)],renal function indexes(creatinine,uric acid,urea and retinol-binding protein)and routine blood indexes(neutrophil count,neutrophil percent-age,lymphocyte count,lymphocyte percentage and white blood cell count)levels in the two groups were com-pared;multivariate Logistic regression was used to analyze the influencing factors of pneumonia in pneumoco-niosis,and a prediction model was constructed.A total of 228 patients with pneumoconiosis admitted to the Second Affiliated Hospital of Xuzhou Medical University from September 2021 to August 2023 were selected as the validation group,and the receiver operating characteristic(ROC)curve was plotted to evaluate the pre-dictive value of the prediction model for pneumonia in patients with pneumoconiosis.Results The differences of CRP,IL-6,IL-8,IL-10,β2-MG,creatinine,urea levels and percentage of neutrophils,lymphocyte count and percentage of lymphocytes between the non-pneumonia group and the pneumonia group were statistically sig-nificant(P＜0.05).The results of multivariate Logistic regression analysis showed that increased levels of CRP,IL-6,IL-8 and β2-MG were independent risk factors for predicting pneumonia in patients with pneumoco-niosis(OR=3.883,1.217,1.215,2.838,P＜0.05),and a prediction model for pneumonia in patients with pneumoconiosis was constructed by combining the above four indexes:Logit(P)=1.357 ×XCRP+0.196× ×IL-6+0.195×X IL-8+1.043×Xβ2-MG-9.772;the results of the ROC curve showed that the area under the curve of the combined model of CRP,IL-6,IL-8,and β2-MG in the modeling group and validation group were 0.909 and 0.848,respectively,with sensitivity of 86.8％and 75.6％,specificity of 77.9％and 85.0％,accura-cy of 82.1％and 79.7％.Conclusion CRP,IL-6,IL-8 and β2-microglobulin are independent risk factors for pneumonia in patients with pneumoconiosis,and the prediction model constructed by the above 4 indexes has good predictive value for pneumonia in patients with pneumoconiosis.关键词
肺尘埃沉着病/肺炎/危险因素/C反应蛋白/白细胞介素-6/白细胞介素-8/β2 微球蛋白/预测模型Key words
pneumoconiosis/pneumonia/risk factors/C-reactive protein/interleukin-6/interleu-kin-8/β2 microglobulin/prediction model分类
医药卫生引用本文复制引用
崔小藏,庄会富,郭毅,徐银海..基于检验指标的肺尘埃沉着病患者合并肺炎的影响因素分析及预测模型构建[J].检验医学与临床,2024,21(16):2345-2350,6.基金项目
江苏省科学技术厅基础研究计划(自然科学基金)青年基金项目(BK20201013). （自然科学基金）
