A Real-time Prediction Model for Post-irradiation Malignant Cervical Lymph Nodes

Abstract

Objective

To establish a real-time predictive scoring model based on sonographic characteristics for identifying malignant cervical lymph nodes (LNs) in cancer patients after neck irradiation.

Methods

One-hundred-forty-four irradiation-treated patients underwent ultrasonography and ultrasound-guided fine needle aspirations (USgFNAs), and the resultant data were used to construct a real-time and computerized predictive scoring model. This scoring system was further compared with our previously proposed prediction model.

Results

A predictive scoring model, 1.35 x (L axis) + 2.03 x (S axis) + 2.27 x (Margin) + 1.48 x (Echogenic hilum) + 3.7, was generated by stepwise multivariate logistic regression analysis. Neck LNs were considered to be malignant when the score was ≥ 7, corresponding to a sensitivity of 85.5%, specificity of 79.4%, positive predictive value (PPV) of 82.3%, negative predictive value (NPV) of 83.1%, and overall accuracy of 82.6%. When this new model and the original model were compared, the areas under the receiver operating characteristic curve (c-statistic) were 0.89 and 0.81, respectively (p < 0.05).

Conclusions

A real-time sonographic predictive scoring model was constructed to provide prompt and reliable guidance for USgFNA biopsies to manage cervical LNs after neck irradiation.

This article is protected by copyright. All rights reserved.

http://ift.tt/2wyMSal