The construction and validation of the model for predicting the incidence and prognosis of brain metastasis in lung cancer patients
Abstract Background: Brain metastasis (BM) causes high morbidity and mortality rate in lung cancer (LC). The present study aims to develop models for predicting the development and prognosis of brain metastasis using a large sample size lung cancer cohort. Methods: A total of 266,522 lung cancer cases that were diagnosed between 2010 and 2016 were selected from the Surveillance, Epidemiology, and End Results Program (SEER) cohort. The risk factors for developing BM and prognosis were calculated by uni and multivariable logistic and Cox regression analysis, respectively and nomograms were constructed basing on the risk factors. The performance of the nomogram was evaluated by receiver operating characteristics curve (ROC) or C-index and calibration curve, respectively. Results: The prevalence of BM was 16.25%, the associated factors for developing BM including advanced age, Asian or Pacific Islander race, uninsured status, primary tumor site, higher T stage, N stage, poorly differentiated grade, the presence of lung, liver and bone metastases and adenocarcinoma histology. The median overall survival (OS) was 4 months; the associated prognosis factors were familiar with risk factors plus female gender, unmarried status, and surgery. The calibration curve showed good agreement between predicted and actual probability and the AUC/C-index were 73.1% (95% CI: 72.6-73.6%) and 0.88 (95 % CI 0.87-0.89) for risk and prognosis predictive models, respectively.