Machine learning studies for predicting 5-year renal cell cancer survival: a multicenter study
Mingchao Wang1, Yiming Ding1, Zhenwei Zhou1
1Department of Urology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, China.
Translational Andrology and Urology
|December 10, 2025
Summary
This study developed a machine learning model to predict 5-year survival in renal cell carcinoma (RCC) patients. The gradient boosting machine model showed high accuracy, aiding clinical decision-making for RCC management.
Area of Science:
- Oncology
- Medical Informatics
- Biostatistics
Background:
- Renal cell carcinoma (RCC) exhibits significant biological heterogeneity, presenting challenges in accurate prognosis and effective treatment strategies.
- Understanding prognostic factors is crucial for improving patient outcomes and guiding clinical decisions in RCC management.
Purpose of the Study:
- To identify key prognostic factors for 5-year survival in renal cell carcinoma (RCC) patients.
- To develop and validate machine learning models for predicting 5-year survival in RCC.
- To support evidence-based clinical decision-making in RCC management.
Main Methods:
- Analysis of clinical data from the Surveillance, Epidemiology, and End Results (SEER) database (2010-2021).
- Prognostic factor selection using least absolute shrinkage and selection operator (LASSO) regression and Boruta.
- Development and evaluation of seven machine learning algorithms for 5-year survival prediction, including Gradient Boosting Machine (GBM).
- Interpretation of model predictions using Shapley Additive Explanations (SHAP) analysis.
Main Results:
- The Gradient Boosting Machine (GBM) model demonstrated superior performance in predicting 5-year survival for RCC patients, achieving an AUC of 0.841.
- The GBM model exhibited the lowest Brier score (0.127) and Estimated Calibration Index (ECI) (0.005), indicating high accuracy and reliability.
- SHAP analysis identified significant clinical factors influencing RCC patient survival, confirming their prognostic importance.
Conclusions:
- A robust machine learning model, particularly GBM, was developed for accurate prediction of 5-year survival in RCC patients.
- The predictive model and identified prognostic factors can assist clinicians in making more informed decisions for RCC patient care.
- This study highlights the potential of machine learning in enhancing prognostic accuracy and guiding treatment strategies for renal cell carcinoma.
Keywords:
5-year survivalMachine learningSurveillance, Epidemiology, and End Results Program (SEER)renal cell cancerMore Related Videos
Related Concept Videos
01:21Cancer Survival Analysis
629
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
629
01:28Drug Dosing in Renal Diseases: Estimation of Glomerular Filtration Rate Based on Serum Creatinine Concentration
171
Glomerular filtration rate (GFR) can be estimated from serum creatinine using the modification of diet in renal disease (MDRD) formula or the chronic kidney disease–epidemiology collaboration (CKD–EPI) equation. Both methods are widely used in clinical practice to assess kidney function and guide treatment decisions.The MDRD equation does not require weight or height measurements and is normalized to the body surface area of 1.73 m², considered the average adult surface area.
171