Era-specific prognostic factors and an interpretable machine-learning survival model for renal cell carcinoma brain metastases.
Machine-learning model predicted survival in renal cell carcinoma brain metastases with moderate accuracy
Era-specific prognostic factors and an interpretable machine-learning survival model for renal cell carcinoma brain metastases.
Brain metastases (brain metastases) in renal cell carcinoma (renal cell carcinoma) are associated with poor prognosis and limited clinical guidance.
We aimed to identify prognostic factors for overall survival (OS) in renal cell carcinoma brain metastases and develop an interpretable machine-learning (machine-learning) model for individualized risk prediction.
We retrospectively analyzed 929 patients with histologically confirmed clear cell renal cell carcinoma brain metastases treated with stereotactic radiosurgery or surgical resection and stratified them by treatment era [interferons (interferons), tyrosine kinase inhibitors (tyrosine kinase inhibitors), and immune checkpoint inhibitors (inhibitors)].
moderate accuracy, better than a coin flip but far from perfect
Median OS increased from 0.8 years in the interferons era to 1.1 years in the tyrosine kinase inhibitors era and 2.0 years in the inhibitors era.
This study reports the largest cohort of patients with renal cell carcinoma brain metastases and presents an interpretable machine-learning model for individualized survival prediction to support clinical decision making.