A Machine Learning Approach to Predict the Probability of Brain Metastasis in Renal Cell Carcinoma Patients

Patients with brain metastasis (BM) have a better prognosis when it is detected early. However, current guidelines recommend imaging only there are central nervous system symptoms or abnormal experimental values. Therefore, metastases discovered later in asymptomatic patients. As result, need for an algorithm that predicts the possibility of BM using clinical data and machine learning (ML). Data from 3153 patients renal cell carcinoma (RCC) were collected 11-institution Korean Renal Cancer Study group (KRoCS) database. To predict BM, information 1282 was extracted database used to compare performance six ML algorithms. The final model selection based on area under receiver operating characteristic (AUROC) curve. After optimizing hyperparameters each model, adaptive boosting (AdaBoost) outperformed others, AUROC 0.716. We developed probability RCC. Using predictive possible avoid detection delays by performing computed tomography scans potentially