Construction and evaluation of a risk prediction model for preoperative lymph node metastasis in non-small cell lung cancer using spectral CT and multiple factors

Objective To investigate the value of a risk prediction model constructed by spectral CT and multiple factors for preoperative lymph node metastasis (LNM) in non-small cell lung cancer (NSCLC).Methods Retrospective analysis was conducted on 150 patients who were underwent spectral CT examination and pathologically diagnosed with NSCLC at the Second Affiliated Hospital of Xuzhou Medical University from January 2023 to January 2025. Their clinical characteristics, pathological and imaging data were collected. Based on postoperative pathological results, the patients were divided into a metastatic group and a non-metastatic group. Spectral CT parameters of the tumor at arterial and venous phases were measured. Statistical analysis was performed to identify independent factors influencing LNM in NSCLC patients, and a prediction model was constructed. The predictive value of this model for LNM was evaluated.Results The established nomogram model exhibited significant predictive value for preoperative LNM in NSCLC patients (χ²=104.094, P<0.001). The area under the curve (AUC) of the model was 0.933 (95%CI: 0.883-0.982), with a specificity of 0.766 and a sensitivity of 0.990.Conclusions The combined nomogram model based on spectral CT parameters and tumor markers has high clinical application value in predicting LNM in NSCLC patients, providing a certain basis for the selection of clinical treatment regimens.