Development of a nomogram for preoperative prediction of lymph node metastasis in non-small cell lung cancer: a SEER-based study

Abstract

Background: Lymph node dissection is an important part of lung cancer surgery. Preoperational evaluation of lymph node metastases decides which dissection pattern should be chosen. The present study aimed to develop a nomogram to predict lymph node metastases on the basis of clinicopathological features of non-small cell lung cancer (NSCLC) patients.

Methods: A total of 35,138 patients diagnosed with NSCLC from 2010-2015 were selected from the Surveillance, Epidemiology, and End Results (SEER) database. Patients were randomly divided into training cohort and validation cohort. Possible risk factors were included and analyzed by logistic regression models. A nomogram was then constructed and validated.

Results: 21.83% of all patients were confirmed with positive lymph node metastasis. Age at diagnosis, sex, stage, T status, tumor size, grade and laterality were identified as predicting factors for lymph node involvement. These variables were included to build the nomogram. The AUC of the model was 0.696 (95% CI, 0.617 to 0.775). The model was further validated in the validation set with AUC 0.693 (95% CI, 0.628 to 0.758). The model presented with good prediction accuracy in both training cohort and validation cohort.

Conclusions: We developed a convenient clinical prediction model for regional lymph node metastases in NSCLC patients. The nomogram will help physicians to determine which patients will receive the most benefit from lymph node dissection.

Keywords: Non-small cell lung cancer (NSCLC); Surveillance, Epidemiology, and End Results (SEER); lymph node metastasis; nomogram.

Figure 1

Flow chart of patient selection from SEER database. Patients included in the study and patients excluded were indicated. NSCLC, non-small cell lung cancer.

Figure 2

Nomogram predicting lymph node metastasis in NSCLC patient. First row presented point assignment for each variable. Row 2–8 showed variables included into this model. When using the nomogram for an individual patient, every variable will be assigned with a point basing on clinicopathological features and all points will be summed up. Every score in total point of row 9 will be corresponding with a probability in the last row of risk. NSCLC, non-small cell lung cancer.

Figure 3

Calibration curve and discrimination curves of the nomogram in training cohort and validation cohort. (A,B) Calibration curves of training cohort and validation curve. The x-axis showed predicted probability of the model and y-axis shows actual probabilities. (C,D) Receiver operating characteristic (ROC) curve for discrimination in the training and validation cohorts. Area under the curve (AUC) was 0.696 (95% CI, 0.617 to 0.775) and 0.693 (95% CI, 0.628 to 0.758) which showed that the model presented with good performance.