Nomogram for Predicting Brain Metastases in Lung Squamous Cell Carcinoma Patients: A SEER -Based Study

BackgroundThe incidence of brain metastasis (BM) in patients suffering from lung squamous cell carcinoma (LUSC) is lower than that in those suffering from non squamous cell carcinoma (NSCC). The purpose of this investigation is to ascertain the risk factors of LUSC as well as to establish a nomogram prognostic model to predict the incidence of BM.MethodsData about the patients diagnosed with LUSC between 2010 and 2015 were collected from Surveillance, Epidemiology, and End Results (SEER) database. The patients diagnosed during 2010-2012 were divided into the training cohort, and the remaining diagnosed during 2013-2015 into the test cohort. Using factors screened out through logistic regression analyses, we established the nomogram in the training cohort and then evaluated the discrimination and calibration in the test cohort. The prediction performance of nomogram was quantified by AUC（area under ROC(receiver operating characteristic curve)）and evaluated by calibration curve.Results26154 LUSU patients were included: 16543 in the training cohort and 8611 in the test cohort. Age, marital status, insurance status, histological grade, tumor location, laterality, stage, number of metastatic organs, chemotherapy, surgery and radiotherapy were highly related to the incidence of BM. The AUC of nomogram was 0.810 (95% confidence interval (CI): 0.796-0.823) and 0.805 (95%CI: 0.784-0.825) in the training cohort and the test cohort, respectively. The slope of calibration curve was closed to 1. ConclusionsThe nomogram can accurately predict the incidence of BM, which is helpful for the early identification of high-risk LUSU patients and the establishment of individualized treatment.