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

• Published in: Clinical otolaryngology Vol. 43; no. 2; pp. 477 - 482
• Main Authors: Lo, W.‐C., Cheng, P.‐W., Shueng, P.‐W., Hsieh, C.‐H., Chang, Y.‐L., Liao, L.‐J.
• Format: Journal Article
• Language: English
• Published: England Wiley Subscription Services, Inc 01-04-2018
• Subjects: Adult; Aged; Biopsy, Fine-Needle; Cancer; Female; fine‐needle aspiration biopsy; head and neck; Head and Neck Neoplasms - diagnostic imaging; Head and Neck Neoplasms - radiotherapy; Head and Neck Neoplasms - secondary; Humans; Irradiation; Logistic Models; lymph node; Lymph nodes; Lymph Nodes - diagnostic imaging; Lymph Nodes - pathology; Lymphatic Metastasis - diagnosis; Lymphatic system; Male; Mathematical models; Middle Aged; Neck; Patients; prediction model; Prediction models; Predictive Value of Tests; Radiation; radiotherapy; Regression analysis; Residents; ROC Curve; Statistical analysis; Ultrasonography; Ultrasound; fine-needle aspiration biopsy; radiotherapy; head and neck; prediction model; lymph node; ultrasound
• ISSN: 1749-4478; 1749-4486
• DOI: 10.1111/coa.12998

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 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 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 < .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.