Risk Factor Analysis Of The Patients With Solitary Pulmonary Nodules And Establishment Of A Prediction Model For The Probability Of Malignancy

Objective This study aim is to analyze the risk factors of malignancy in patients with solitary pulmonary nodules(diameter≤3cm)using univariate analysis and multivariate logistic regression,and establish a prediction model for the probability of malignancy.Materials and methods Clinical data of 372 patients with solitary pulmonary nodule who underwent surgical resection with definite postoperative pathological diagnosis from August 2011 To January 2017 in Second Affiliated Hospital to Soochow University were retrospectively analyzed.In these cases,we collected clinical and radiologic features including gender,age,smoking history,history of tumor,family history of cancer,the location of lesion,ground-glass opacity,maximum diameter,calcification,vessel convergence sign,vacuole sign,pleural indentation,speculation and lobulation.268 patients got definite diagnosis before December 2015 was grouped as A,and it was intended for building the logistic regression model,the cases after that time were grouped as B,which was planned to validate our model,as well as other three published classical model.Univariate analysis was performed to analyze risk factors of clinical and radiologic features,independent risk factors were screened with multivariate logistic regression analysis,then the mathematical prediction model was established,with an appropriate cut-off value also derived.With the data of B,this model was verified and was compared with the other three classical models(Mayo model,VA model and LiYun model).With the calculated probability values for each model from group B,the statistical software was used to draw the ROC curve,and any two of the AUCs were compared respectively,and the differences were estimated if there were any statistically significant.Results 58.2%of the nodules were malignant,and 41.8%were benign in group A.Logistic regression analysis showed that gender,age,history of tumor,ground-glass opacity,maximum diameter,and speculation were independent predictors of malignancy in patients with SPN(P<0.05).p=e~x/(1+e~x),x=-4.8029+(-0.743×gender)+(0.057×age)+(1.306×history of tumor)+(1.305×ground-glass opacity)+(0.051×maximum diameter)+(1.043×speculation).e was the natural logarithm,cut-off value T=0.403,the positive predictive value was 80.1%,the negative predictive value was 69.6%,positive predictive value 78.6%,and negative predictive value 71.6%,overall prediction accuracy 75.7%.The area under the ROC curve for our model was 0.799±0.027,95%CI:0.745~0.853.When the data of group B was added to the four mathematical prediction model.The area under the curve of our mathematical prediction model was 0.742,which is greater than other models(Mayo 0.696,VA 0.634,LiYun 0.681),while the differences between any two of the four models were not significant(P>0.05).Conclusion Age of patient,gender,history of tumor,ground-glass opacity,maximum diameter and speculation are independent predictors of malignancy in patients with solitary pulmonary nodule.This logistic regression prediction mathematic model can be used as a tool to help guiding clinical decision,which has a widespread applicability compared with other models.