A risk-scoring model based on endobronchial ultrasound multimodal imaging for predicting metastatic lymph nodes in lung cancer patients

Abstract

Endobronchial ultrasound (EBUS) imaging is a valuable tool for predicting lymph node (LN) metastasis in lung cancer patients. This study aimed to develop a risk-scoring model based on EBUS multimodal imaging (grayscale, Doppler mode, elastography) to predict LN metastasis in lung cancer patients. This retrospective study analyzed 350 metastatic LNs in 314 patients with lung cancer and 124 reactive LNs in 96 patients with nonspecific inflammation. The sonographic findings were compared with the final pathology results and clinical follow-up. Univariate and multivariate logistic regression analyses were performed to evaluate the independent risk factors of metastatic LNs. According to the β coefficients of corresponding indicators in logistic regression analysis, a risk-scoring model was established. Receiver operating characteristic curve was applied to evaluate the predictive capability of model. Multivariate analysis showed that short axis >10 mm, distinct margin, absence of central hilar structure, presence of necrosis, nonhilar vascularity, and elastography score 4 to 5 were independent predictors of metastatic LNs. Both short axis and margin were scored 1 point, and the rest of independent predictors were scored 2 points. The combination of 3 EBUS modes had the highest area under the receiver operating characteristic and accuracy of 0.884 (95% confidence interval, 0.846–0.922) and 87.55%, respectively. The risk stratification was as follows: 0 to 2 points, malignancy rate of 11.11%, low suspicion; 3 to 10 points, malignancy rate of 86.77%, high suspicion. The risk-scoring model based on EBUS multimodal imaging can effectively evaluate metastatic LNs in lung cancer patients to support clinical decision making.