Objective To construct a nomogram model for predicting pulmonary hemorrhage associated with the positioning of pulmonary nodules with the new four-hook positioning needle based on clinical-CT imaging features and evaluate its predictive efficacy.Methods We made a retrospective analysis of the clinical,imaging and pathological data of 449 patients with pulmonary nodules positioned by the new four-hook positioning needle.According to the random number table method(7∶3),they were divided into a training set of 314 cases and a validation set of 135 cases.Each data set was further divided into positive group and negative group for pulmonary hemorrhage according to the presence or absence of pulmonary hemorrhage.We evaluated the CT imaging features of pulmonary nodules,including nodule nature(pure ground-glass density,mixed ground-glass density,solid nodule),nodule diameter,distance from the nodule to the pleural surface(hereinafter referred to as length),nodule positioning time,and association with pulmonary hemorrhage.Independent sample t-test,Mann-Whitney U test and x2 test were used to compare the correlations of clinical and CT features of pulmonary nodules with pulmonary hemorrhage.LASSO regression and multivariate Logistic regression were employed to screen the independent risk factors related to pulmonary hemorrhage and construct a nomogram model.The receiver operating characteristic(ROC)curve was used to evaluate the predictive efficacy of the model,and the calibration curve and decision curve were respectively used for the verification of the nomogram model and evaluation of the clinical net benefit.Results The results of LASSO regression showed that the nature of pulmonary nodules,underlying diseases,smoking and length were the characteristic variables related to pulmonary hemorrhage.Based on the minimum akaike information criterion(AIC),the screened characteristic variables were included in the multivariate Logistic backward stepwise regression analysis.The results showed that the nature of pulmonary nodules,underlying diseases,smoking and length were all independent risk factors related to pulmonary hemorrhage.A nomogram was established according to the above independent risk factors and the ROC curve was drawn.The AUC of the training set was 0.86(95％CI:0.80-0.91),and the AUC of the validation set was 0.88(95％CI:0.80-0.96),with no statistically significant difference(P＞0.05).The calibration curve suggested that the predicted values of the nomogram were close to the actual values,and the decision curve analysis showed that the net benefit of the model was good.Conclusion The nomogram model established by combining clinical-CT features such as the nature of pulmonary nodules,underlying diseases,smoking and length can effectively predict pulmonary hemorrhage associated with the positioning of pulmonary nodules with the new four-hook positioning needle.

Objective To construct a nomogram model for predicting pulmonary hemorrhage associated with the positioning of pulmonary nodules with the new four-hook positioning needle based on clinical-CT imaging features and evaluate its predictive efficacy.Methods We made a retrospective analysis of the clinical,imaging and pathological data of 449 patients with pulmonary nodules positioned by the new four-hook positioning needle.According to the random number table method(7∶3),they were divided into a training set of 314 cases and a validation set of 135 cases.Each data set was further divided into positive group and negative group for pulmonary hemorrhage according to the presence or absence of pulmonary hemorrhage.We evaluated the CT imaging features of pulmonary nodules,including nodule nature(pure ground-glass density,mixed ground-glass density,solid nodule),nodule diameter,distance from the nodule to the pleural surface(hereinafter referred to as length),nodule positioning time,and association with pulmonary hemorrhage.Independent sample t-test,Mann-Whitney U test and x2 test were used to compare the correlations of clinical and CT features of pulmonary nodules with pulmonary hemorrhage.LASSO regression and multivariate Logistic regression were employed to screen the independent risk factors related to pulmonary hemorrhage and construct a nomogram model.The receiver operating characteristic(ROC)curve was used to evaluate the predictive efficacy of the model,and the calibration curve and decision curve were respectively used for the verification of the nomogram model and evaluation of the clinical net benefit.Results The results of LASSO regression showed that the nature of pulmonary nodules,underlying diseases,smoking and length were the characteristic variables related to pulmonary hemorrhage.Based on the minimum akaike information criterion(AIC),the screened characteristic variables were included in the multivariate Logistic backward stepwise regression analysis.The results showed that the nature of pulmonary nodules,underlying diseases,smoking and length were all independent risk factors related to pulmonary hemorrhage.A nomogram was established according to the above independent risk factors and the ROC curve was drawn.The AUC of the training set was 0.86(95％CI:0.80-0.91),and the AUC of the validation set was 0.88(95％CI:0.80-0.96),with no statistically significant difference(P＞0.05).The calibration curve suggested that the predicted values of the nomogram were close to the actual values,and the decision curve analysis showed that the net benefit of the model was good.Conclusion The nomogram model established by combining clinical-CT features such as the nature of pulmonary nodules,underlying diseases,smoking and length can effectively predict pulmonary hemorrhage associated with the positioning of pulmonary nodules with the new four-hook positioning needle.

Objective To construct the prediction model of perineural invasion(PNI)in gallbladder carcinoma(GBC)based on preoperative enhanced CT image features and evaluate its prediction efficiency.Methods The clinical,imaging and pathological data of 180 GBC patients undergoing radical operation were retrospectively analyzed.They were divided into positive and negative groups according to the presence or absence of PNI.Preoperative enhanced CT imaging features(including presence of gallstones,imaging hepatic invasion,vascular invasion,T-stage,and hilar or retroperitoneal lymph node metastases)were evaluated by two radiologists.Independent sample t-test,Mann Whitney U test,and X2 test were used to compare the correlation between CT signs and PNI.Logistics regression analysis was used to screen independent risk factors and establish the prediction model formula.ROC curve was used to evaluate the prediction efficiency of the prediction model and the corresponding area under the curve(AUC)was calculated.Hosmer-Lemeshow goodness of fit test was used to verify the prediction model.Results Unifactorial analysis showed that CA199,CA125,imaging hepatic invasion,vascular invasion(hepatic artery or portal vein),T-stage,and hilar or retroperitoneal lymph node metastasis were correlated with nerve invasion(P＜0.05).Logistics multi-factor analysis results showed that CA199,imaging vascular invasion(hepatic artery or portal vein),and imaging T stage were independent risk factors for PNI.Based on the above independent risk factors,a prediction model formula was established and ROC curve was drawn,with an AUC of 0.807(95％CI:0.734～0.879),sensitivity of 0.792,specificity of 0.697,and the chi-square value of Hosmer-Lemeshow goodness of fit test of 0.594(P=0.997),indicating that the predicted value of the model was close to the actual value.Conclusion Combining CA199,imaging vascular invasion,T-stage,and other preoperative clinically-enhanced CT features to establish a prediction model can effectively predict postoperative PNI of GBC.