Abstract
BACKGROUND AND PURPOSE: An accurate and comprehensive assessment of lymph node metastasis in patients with head and neck squamous cell cancer is crucial in daily practice. This study constructed a predictive model with a risk scoring system based on CT characteristics of lymph nodes and tumors for patients with head and neck squamous cell carcinoma to stratify the risk of lymph node metastasis. MATERIALS AND METHODS: Data included 476 cervical lymph nodes from 191 patients with head and neck squamous cell carcinoma from a historical cohort. We analyzed preoperative CT images of lymph nodes, including diameter, ratio of long-to-short axis diameter, necrosis, conglomeration, infiltration to adjacent soft tissue, laterality and T-stage of the primary tumor. The reference standard comprised pathologic results. Multivariable logistic regression analysis was performed to develop the risk scoring system. Internal validation was performed with 1000-iteration bootstrapping. RESULTS: Shortest axial diameter, ratio of long-to-short axis diameter, necrosis, and T-stage were used to develop a 9-point risk scoring system. The risk of malignancy ranged from 7.3% to 99.8%, which was positively associated with increased scores. Areas under the curve of the risk scoring systems were 0.886 (95% CI, 0.881-0.920) and 0.879 (95% CI, 0.845-0.914) in internal validation. The Hosmer-Lemeshow goodness-of-fit test indicated that the risk scoring system was well-calibrated (P = .160). CONCLUSIONS: We developed a comprehensive and simple risk scoring system using CT characteristics in patients with head and neck squamous cell carcinoma to stratify the risk of lymph node metastasis. It could facilitate decision-making in daily practice.