^(18)F-DGPET/CT诊断孤立性肺结节数学模型的临床验证

Clinical verification of a mathematical model for diagnosing SPN with ^(18)F-DG PET/CT

目的对前期建立的应用18F-DG PET/CT诊断肺孤立性结节(solitary pulmonary nodule,SPN)良、恶性的数学模型加以临床验证。方法采用前瞻性试验方法,连续收集自2011年1月~2012年6月间于我中心行18 F-DG PET/CT检查的SPN患者共109例(恶性67例,良性42例)。根据前期模型所需,收集患者年龄、密度、瘤肺交界情况、分叶、血管集束征、胸膜牵拉征和FDG摄取程度作为诊断SPN的影响因子,输入数学模型,计算诊断效率,并与2名具有丰富PET/CT阅片经验的高年资医师诊断结果对比,比较其临床应用价值。结果应用前期数学模型判断SPN良、恶性的诊断灵敏度为95.52%、特异度69.05%、阳性预测值83.12%、阴性预测值90.63%、准确率85.32%;医师的诊断灵敏度为97.01%、特异度52.38%、阳性预测值76.47%、阴性预测值91.67%、准确率79.82%;数学模型诊断SPN良、恶性的的ROC曲线下面积(AUC,area under curve)为0.887±0.034,明显高于医师的诊断结果(AUC 0.747±0.05)。结论利用二元Logistic回归建立的18F-DG PET/CT诊断SPN良、恶性的数学模型诊断准确率高,具有较高的临床应用价值。

Objective To verify earlier established mathematical model for the diagnosis of the solitary pulmonary nod- ules （SPN） with SF-DG PET/CT. Methods A prospective cohort study in our PET/CT center included 109 patients with SPN （67 malignance, 42 benign） from Jan 2011 to Jun 2012. Clinical data including 7 items （age, density, border of tumor and parenchyma, lobulation, pleural retraction sign, vascular convergence sign, FDG uptake） were incorporated into the mathematical model. The diagnostic results were compared between the model and 2 senior doctors with rich experi- ence in reading PET/CT imaging. Results The clinical value for diagnosing the SPN with mathematical model was veri- fied with sensitivity of 95.52%, specificity of 69.05%, positive predictive value of 83.12%, negative predictive value of 90.63 %, accuracy of 85.320/00. The diagnostic efficiency from doctors was also obtained with sensitivity of 97.01%, spe cificity of 52.38%, positive predictive value of 76.47%, negative predictive value of 91.67%, accuracy of 79.82%. The AUCs of mathematical model were 0. 887 ±0. 034, which was better than the AUCs of the diagnostic results from the doctors （AUC=0. 747±0. 053, P d0.05）. Conclusion The earlier mathematical model established by binary Logistic regression has high diagnostic value for estimating the character of SPN and will be used in clinical practice well.