Brain metastases (BMs) in extensive-stage small cell lung cancer (ES-SCLC) are often associated with poor survival rates and quality of life, making the timely identification of high-risk patients for BMs in ES-SCLC crucial. Patients diagnosed with ES-SCLC between 2010 and 2018 were screened from the Surveillance, Epidemiology, and End Results (SEER) database. Four different machine learning (ML) algorithms were used to create prediction models for BMs in ES-SCLC patients. The accuracy, sensitivity, specificity, AUROC, and AUPRC were compared among these models and traditional logistic regression (LR). The random forest (RF) model demonstrated the best performance and was chosen for further analysis. The AUROC and AUPRC were calculated and compared. The findings from the RF model were utilized to identify the risk factors linked to BMs in patients diagnosed with ES-SCLC. Examining 4,716 instances of ES-SCLC, the research conducted an analysis, with brain metastases arising in 1,900 cases. Through evaluation of the ROC curve and PRC concerning the RF Model, results depicted an AUROC of 0.896 (95% CI: 0.889-0.899) and AUPRC of 0.900 (95% CI: 0.895-0.904). Test accuracy measured at 0.810 (95% CI: 0.784-0.833), sensitivity at 0.797 (95% CI: 0.756-0.841), and specificity at 0.819 (95% CI: 0.754-0.879). Based on the SHAP analysis of the RF predictive model, the top 10 most relevant features were identified and ranked in order of relative importance: bone metastasis, liver metastasis, radiation, age, tumor size, primary tumor location, N-stage, race, T-stage, and chemotherapy. The research developed and validated a predictive RF model using clinical and pathological data to predict the risk of BMs in patients with ES-SCLC. This model may assist physicians in making clinical decisions that could delay the onset of BMs and improve patient survival rates.
Keywords: Brain metastasis; Extensive-stage small cell lung cancer; Machine learning; Random Forest.
© 2024. The Author(s).