肿瘤标志物预测孤立性肺结节恶性概率模型的建立与初步评价

发布时间：2019-01-17 07:38

【摘要】：目的利用肿瘤标志物建立预测孤立性肺结节(SPN)恶性概率的数学模型,并评价其临床价值。方法选取250例SPN患者,考察其年龄、性别、吸烟史、症状、结节最大径、结节部位、病理,以及血清癌胚抗原(CEA)、细胞角蛋白19片段抗原(CYFRA21-1)、神经元特异性烯醇化酶(NSE)水平,采用二分类Logistic回归法作影响因素筛选,并建立Logistic回归模型。绘制受试者工作特征曲线(ROC)并计算曲线下面积(AUC)以评价模型准确性,并与梅奥模型比较以评价模型的临床价值。结果 CEA(P=0.002,OR=5.921,95%CI=1.968~17.819),CYFRA21-1(P=0.046,OR=2.500,95%CI=1.018~6.142),症状(P=0.010,OR=2.384,95%CI=1.234~4.607),结节最大径(P=0.001,OR=2.331,95%CI=1.441~3.773)与SPN的良恶性有关;由此建立预测模型:P=ex/(1+ex),X=-1.991+0.869×症状+0.846×结节最大径+1.779×CEA+0.916×CYFRA21-1;采用Hosmer-Lemeshow检验模型的拟合度较好(P=0.691);当截点为0.636时,灵敏度为63.5%,特异度为71.2%;预测模型(AUC:0.734±0.033)与指南推荐的梅奥模型(AUC:0.792±0.047)进行比较,差异无统计学意义(P0.05)。结论 CEA、CYFRA21-1、症状和结节最大径为恶性SPN的独立危险因素;由此建立的Logistic回归模型准确性较高,有较好的临床价值。
[Abstract]:Objective to establish a mathematical model to predict the malignant probability of solitary pulmonary nodules (SPN) by using tumor markers and to evaluate its clinical value. Methods the age, sex, smoking history, symptoms, maximum diameter of nodules, location and pathology of nodules, and serum carcinoembryonic antigen (CEA),) cytokeratin 19 fragment antigen (CYFRA21-1) were studied in 250 patients with SPN. The level of neuron-specific enolase (NSE) was screened by two-class Logistic regression and the Logistic regression model was established. To evaluate the accuracy of the model by drawing the operating characteristic curve (ROC) and calculating the area under the curve (AUC), and comparing with Mayo model to evaluate the clinical value of the model. Results CEA (P0. 002) 5.921 ~ 95CII = 1. 968 ~ 17. 819), CYFRA21-1 (P0. 046) ~ 2.500 ~ 95 ~ 95 CI = 1.018 ~ 6. 142), symptoms (P ~ 0. 010 OR2. 384 ~ 95), nodule maximum diameter (P ~ 0. 001, P ~ 0. 001), nodule diameter (P ~ 0. 001, P ~ 0. 001), symptom (P ~ 0. 010 ~ 0. 010 OR2. 384 ~ 95 CI = 1. 234 ~ 4.607). OR=2.331,95%CI=1.441~3.773) is associated with benign and malignant SPN. The prediction model was established as follows: P=ex/ (1 ex), XML-1.991 0.869 脳 symptom 0.846 脳 CEA 0.916 脳 CYFRA21-1;) fitted well with Hosmer-Lemeshow test model (P0. 691); When the cut-off point was 0.636, the sensitivity was 63.5 and the specificity was 71.2; The predictive model (AUC:0.734 卤0.033) was compared with the Mayo model (AUC:0.792 卤0.047) recommended by the guidelines. The difference was not statistically significant (P0.05). Conclusion CEA,CYFRA21-1, symptoms and the maximum diameter of nodules are independent risk factors for malignant SPN, and the Logistic regression model established from this model has high accuracy and good clinical value.
【作者单位】：滨州医学院烟台附属医院呼吸内科;滨州医学院烟台附属医院统计室;烟台毓璜顶医院血管外科;大连医科大学附属第二医院呼吸内科;
【分类号】：R734.2

【相似文献】