A real‐time prediction model for post‐irradiation malignant cervical lymph nodes

Objective To establish a real‐time predictive scoring model based on sonographic characteristics for identifying malignant cervical lymph nodes ( LN s) in cancer patients after neck irradiation. Methods One‐hundred forty‐four irradiation‐treated patients underwent ultrasonography and ultrasound‐guided fine‐needle aspirations ( US g FNA s), and the resultant data were used to construct a real‐time and computerised predictive scoring model. This scoring system was further compared with our previously proposed prediction model. Results A predictive scoring model, 1.35 × (L axis) + 2.03 × (S axis) + 2.27 × (margin) + 1.48 × (echogenic hilum) + 3.7, was generated by stepwise multivariate logistic regression analysis. Neck LN s 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 < .05). Conclusions A real‐time sonographic predictive scoring model was constructed to provide prompt and reliable guidance for US g FNA biopsies to manage cervical LN s after neck irradiation.