孤立性肺结节良恶性判断数学预测模型的建立及临床对比验证分析

Establishment and clinical verification of a mathematical model for predicting the probability of malignancy or begin in patients with solitary pulmonary nodules

目的遴选判断孤立性肺结节(SPN)性质的影响因素,构建SPN良恶性数学预测模型,并验证其准确性。方法回顾分析2008年1月—2013年9月本院收治的诊断明确的SPN患者405例,其中男220例,女185例。通过逻辑回归分析遴选出判断SPN性质的独立影响因素,建立数学预测模型。另收集2013年10月—2015年9月诊断明确的SPN患者168例,验证该预测模型对SPN良恶性判断的敏感性和特异性。通过Hosmer-Lemeshow(H-L)检验判断数学模型的校准度,绘制ROC曲线,通过曲线下面积(AUC)检验其预测能力。结果多因素Logistic回归分析显示,患者年龄、既往肿瘤病史、肿瘤家族史、结节大小、毛刺、分叶、边界模糊、胸膜牵拉征等8项因素在良恶性SPN之间的差异有统计学意义(P<0.05),是判断SPN良恶性的独立影响因素。应用本模型预测良SPN恶性的灵敏度为94.7%,特异度为76.4%,阳性预测值为89.2%,阴性预测值为87.5%。本数学预测模型的AUC为0.809±0.017。结论本数学预测模型对判断SPN良恶性具有较高的准确性。

Objective To establish a mathematical model for estimating the probability of malignancy in patients with solitary pulmonary nodule, and to verify the accuracy of this model. Methods A retrospective cohort study included 405 patients （220 males and 174 females） with definite pathological diagnosis of SPN from January 2008 to September 2013 （ group A）. Clinical and imaging features were analyzed, and a clinical prediction model was built with multivariate Logistic regression analysis. The other 168 SPN patients （ group B） with definite pathological diagnosis from October 2013 to September 2015 were selected to estimate the accuracy of the model. Calibration of this model was assessed by Hosmer-Lemeshow （H-L） test. The area under curve （AUC） after receive operating characteristic （ROC） curve was drawn. Results Logistic regression analysis showed that age, previous cancer history, family history of cancer, diameter, speculation, lobulation, border, pleural retraction sign were independent predictors of malignancy in SPN patients （P 〈 0.05 ）. The sensitivity in group B was 94.7%, specificity was 76.4%, positive predictive value was 89.2%, and negative predictive value was 87.5%. The AUC of this model was 0. 809 ±0. 017. Conclusion The clinical prediction model that we established by retrospective study has a higher clinical value in predicting the probability of malignancy or begin in patients with solitary pulmonary nodules.